|
1
|
Gim N, Ferguson AN, Blazes M, Lee CS, Lee AY. The March to Harmonized Imaging Standards for Retinal Imaging. Prog Retin Eye Res 2025:101363. [PMID: 40360070 DOI: 10.1016/j.preteyeres.2025.101363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2024] [Revised: 04/15/2025] [Accepted: 05/09/2025] [Indexed: 05/15/2025]
Abstract
The adoption of standardized imaging protocols in retinal imaging is critical to overcoming challenges posed by fragmented data formats across devices and manufacturers. The lack of standardization hinders clinical interoperability, collaborative research, and the development of artificial intelligence (AI) models that depend on large, high-quality datasets. The Digital Imaging and Communication in Medicine (DICOM) standard offers a robust solution for ensuring interoperability in medical imaging. Although DICOM is widely utilized in radiology and cardiology, its adoption in ophthalmology remains limited. Retinal imaging modalities such as optical coherence tomography (OCT), fundus photography, and OCT angiography (OCTA) have revolutionized retinal disease management but are constrained by proprietary and non-standardized formats. This review underscores the necessity for harmonized imaging standards in ophthalmology, detailing DICOM standards for retinal imaging including ophthalmic photography (OP), OCT, and OCTA, and their requisite metadata information. Additionally, the potential of DICOM standardization for advancing AI applications in ophthalmology is explored. A notable example is the Artificial Intelligence Ready and Equitable Atlas for Diabetes Insights (AI-READI) dataset, the first publicly available standards-compliant DICOM retinal imaging dataset. This dataset encompasses diverse retinal imaging modalities, including color fundus photography, infrared, autofluorescence, OCT, and OCTA. By leveraging multimodal retinal imaging, AI-READI provides a transformative resource for studying diabetes and its complications, setting a blueprint for future datasets aimed at harmonizing imaging formats and enabling AI-driven breakthroughs in ophthalmology. Our manuscript also addresses challenges in retinal imaging for diabetic patients, retinal imaging-based AI applications for studying diabetes, and potential advancements in retinal imaging standardization.
Collapse
Affiliation(s)
- Nayoon Gim
- Department of Ophthalmology, University of Washington, Seattle, Washington; Roger and Angie Karalis Johnson Retina Center, Seattle, Washington; University of Washington School of Medicine, Seattle, Washington; Department of Bioengineering, University of Washington, Seattle, Washington
| | - Alina N Ferguson
- Department of Ophthalmology, University of Washington, Seattle, Washington; Roger and Angie Karalis Johnson Retina Center, Seattle, Washington; University of Washington School of Medicine, Seattle, Washington
| | - Marian Blazes
- Department of Ophthalmology, University of Washington, Seattle, Washington; Roger and Angie Karalis Johnson Retina Center, Seattle, Washington
| | - Cecilia S Lee
- Department of Ophthalmology, University of Washington, Seattle, Washington; Roger and Angie Karalis Johnson Retina Center, Seattle, Washington
| | - Aaron Y Lee
- Department of Ophthalmology, University of Washington, Seattle, Washington; Roger and Angie Karalis Johnson Retina Center, Seattle, Washington.
| |
Collapse
|
|
2
|
Ciapponi A, Ballivian J, Gentile C, Mejia JR, Ruiz-Baena J, Bardach A. Diagnostic utility of artificial intelligence software through non-mydriatic digital retinography in the screening of diabetic retinopathy: an overview of reviews. Eye (Lond) 2025:10.1038/s41433-025-03809-y. [PMID: 40301668 DOI: 10.1038/s41433-025-03809-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2024] [Revised: 04/07/2025] [Accepted: 04/08/2025] [Indexed: 05/01/2025] Open
Abstract
OBJECTIVE To evaluate the capability of artificial intelligence (AI) in screening for diabetic retinopathy (DR) utilizing digital retinography captured by non-mydriatic (NM) ≥45° cameras, focusing on diagnosis accuracy, effectiveness, and clinical safety. METHODS We performed an overview of systematic reviews (SRs) up to May 2023 in Medline, Embase, CINAHL, and Web of Science. We used AMSTAR-2 tool to assess the reliability of each SR. We reported meta-analysis estimates or ranges of diagnostic performance figures. RESULTS Out of 1336 records, ten SRs were selected, most deemed low or critically low quality. Eight primary studies were included in at least five of the ten SRs and 125 in less than five SRs. No SR reported efficacy, effectiveness, or safety outcomes. The sensitivity and specificity for referable DR were 68-100% and 20-100%, respectively, with an AUROC range of 88 to 99%. For detecting DR at any stage, sensitivity was 79-100%, and specificity was 50-100%, with an AUROC range of 93 to 98%. CONCLUSIONS AI demonstrates strong diagnostic potential for DR screening using NM cameras, with adequate sensitivity but variable specificity. While AI is increasingly integrated into routine practice, this overview highlights significant heterogeneity in AI models and the cameras used. Additionally, our study enlightens the low quality of existing systematic reviews and the significant challenge of integrating the rapidly growing volume of emerging evidence in this field. Policymakers should carefully evaluate AI tools in specific contexts, and future research must generate updated high-quality evidence to optimize their application and improve patient outcomes.
Collapse
Affiliation(s)
- Agustín Ciapponi
- Instituto de Efectividad Clínica y Sanitaria (IECS), Buenos Aires, Argentina.
| | - Jamile Ballivian
- Instituto de Efectividad Clínica y Sanitaria (IECS), Buenos Aires, Argentina
| | - Carolina Gentile
- Hospital Italiano de Buenos Aires, Servicio de Oftalmología, Buenos Aires, Argentina
| | - Jhonatan R Mejia
- Instituto de Efectividad Clínica y Sanitaria (IECS), Buenos Aires, Argentina
| | - Jessica Ruiz-Baena
- Àrea d'Avaluació i Qualitat, Agència de Qualitat i Avaluació Sanitàries de Catalunya (AQuAS), Catalunya, España
| | - Ariel Bardach
- Instituto de Efectividad Clínica y Sanitaria (IECS), Buenos Aires, Argentina
| |
Collapse
|
|
3
|
Alqahtani AS, Alshareef WM, Aljadani HT, Hawsawi WO, Shaheen MH. The efficacy of artificial intelligence in diabetic retinopathy screening: a systematic review and meta-analysis. Int J Retina Vitreous 2025; 11:48. [PMID: 40264218 PMCID: PMC12012971 DOI: 10.1186/s40942-025-00670-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2025] [Accepted: 04/04/2025] [Indexed: 04/24/2025] Open
Abstract
BACKGROUND To evaluate the efficacy of artificial intelligence (AI) in screening for diabetic retinopathy (DR) using fundus images and optical coherence tomography (OCT) in comparison to traditional screening methods. METHODS This systematic review was registered with PROSPERO (ID: CRD42024560750). Systematic searches were conducted in PubMed Medline, Cochrane Central, ScienceDirect, and Web of Science using keywords such as "diabetic retinopathy," "screening," and "artificial intelligence." Only studies published in English from 2019 to July 22, 2024, were considered. We also manually reviewed the reference lists of relevant reviews. Two independent reviewers assessed the risk of bias using the QUADAS-2 tool, resolving disagreements through discussion with the principal investigator. Meta-analysis was performed using MetaDiSc software (version 1.4). To calculate combined sensitivity, specificity, summary receiver operating characteristic (SROC) plots, forest plots, and subgroup analyses were performed according to clinician type (ophthalmologists vs. retina specialists) and imaging modality (fundus images vs. fundus images + OCT). RESULTS 18 studies were included. Meta-analysis showed that AI systems demonstrated superior diagnostic performance compared to doctors, with the pooled sensitivity, specificity, diagnostic odds ratio, and Cochrane Q index of the AI being 0.877, 0.906, 0.94, and 153.79 accordingly. The Fagan nomogram analysis further confirmed the strong diagnostic value of AI. Subgroup analyses revealed that factors like imaging modality, and doctor expertise can influence diagnostic performance. CONCLUSION AI systems have demonstrated strong diagnostic performance in detecting diabetic retinopathy, with sensitivity and specificity comparable to or exceeding traditional clinicians.
Collapse
Affiliation(s)
- Abdullah S Alqahtani
- Department of Surgery, Division of Ophthalmology, King Abdulaziz Medical City, Ministry of National Guard Health Affairs, Jeddah, Saudi Arabia.
- King Saud Bin Abdulaziz University for Health Sciences, Jeddah, Saudi Arabia.
- King Abdullah International Medical Research Center, Jeddah, Saudi Arabia.
| | - Wasan M Alshareef
- King Saud Bin Abdulaziz University for Health Sciences, Jeddah, Saudi Arabia
| | - Hanan T Aljadani
- King Saud Bin Abdulaziz University for Health Sciences, Jeddah, Saudi Arabia
| | - Wesal O Hawsawi
- King Saud Bin Abdulaziz University for Health Sciences, Jeddah, Saudi Arabia
| | - Marya H Shaheen
- King Saud Bin Abdulaziz University for Health Sciences, Jeddah, Saudi Arabia
| |
Collapse
|
|
4
|
Moannaei M, Jadidian F, Doustmohammadi T, Kiapasha AM, Bayani R, Rahmani M, Jahanbazy MR, Sohrabivafa F, Asadi Anar M, Magsudy A, Sadat Rafiei SK, Khakpour Y. Performance and limitation of machine learning algorithms for diabetic retinopathy screening and its application in health management: a meta-analysis. Biomed Eng Online 2025; 24:34. [PMID: 40087776 PMCID: PMC11909973 DOI: 10.1186/s12938-025-01336-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Accepted: 01/07/2025] [Indexed: 03/17/2025] Open
Abstract
BACKGROUND In recent years, artificial intelligence and machine learning algorithms have been used more extensively to diagnose diabetic retinopathy and other diseases. Still, the effectiveness of these methods has not been thoroughly investigated. This study aimed to evaluate the performance and limitations of machine learning and deep learning algorithms in detecting diabetic retinopathy. METHODS This study was conducted based on the PRISMA checklist. We searched online databases, including PubMed, Scopus, and Google Scholar, for relevant articles up to September 30, 2023. After the title, abstract, and full-text screening, data extraction and quality assessment were done for the included studies. Finally, a meta-analysis was performed. RESULTS We included 76 studies with a total of 1,371,517 retinal images, of which 51 were used for meta-analysis. Our meta-analysis showed a significant sensitivity and specificity with a percentage of 90.54 (95%CI [90.42, 90.66], P < 0.001) and 78.33% (95%CI [78.21, 78.45], P < 0.001). However, the AUC (area under curvature) did not statistically differ across studies, but had a significant figure of 0.94 (95% CI [- 46.71, 48.60], P = 1). CONCLUSIONS Although machine learning and deep learning algorithms can properly diagnose diabetic retinopathy, their discriminating capacity is limited. However, they could simplify the diagnosing process. Further studies are required to improve algorithms.
Collapse
Affiliation(s)
- Mehrsa Moannaei
- School of Medicine, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
| | - Faezeh Jadidian
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Tahereh Doustmohammadi
- Department and Faculty of Health Education and Health Promotion, Student Research Committee, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Amir Mohammad Kiapasha
- Student Research Committee, School of Medicine, Shahid Beheshti University of Medical Science, Tehran, Iran
| | - Romina Bayani
- Student Research Committee, School of Medicine, Shahid Beheshti University of Medical Science, Tehran, Iran
| | | | | | - Fereshteh Sohrabivafa
- Health Education and Promotion, Department of Community Medicine, School of Medicine, Dezful University of Medical Sciences, Dezful, Iran
| | - Mahsa Asadi Anar
- Student Research Committee, Shahid Beheshti University of Medical Science, Arabi Ave, Daneshjoo Blvd, Velenjak, Tehran, 19839-63113, Iran.
| | - Amin Magsudy
- Faculty of Medicine, Islamic Azad University Tabriz Branch, Tabriz, Iran
| | - Seyyed Kiarash Sadat Rafiei
- Student Research Committee, Shahid Beheshti University of Medical Science, Arabi Ave, Daneshjoo Blvd, Velenjak, Tehran, 19839-63113, Iran
| | - Yaser Khakpour
- Faculty of Medicine, Guilan University of Medical Sciences, Rasht, Iran
| |
Collapse
|
|
5
|
Li Y, Jin N, Zhan Q, Huang Y, Sun A, Yin F, Li Z, Hu J, Liu Z. Machine learning-based risk predictive models for diabetic kidney disease in type 2 diabetes mellitus patients: a systematic review and meta-analysis. Front Endocrinol (Lausanne) 2025; 16:1495306. [PMID: 40099258 PMCID: PMC11911190 DOI: 10.3389/fendo.2025.1495306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Accepted: 02/13/2025] [Indexed: 03/19/2025] Open
Abstract
Background Machine learning (ML) models are being increasingly employed to predict the risk of developing and progressing diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). However, the performance of these models still varies, which limits their widespread adoption and practical application. Therefore, we conducted a systematic review and meta-analysis to summarize and evaluate the performance and clinical applicability of these risk predictive models and to identify key research gaps. Methods We conducted a systematic review and meta-analysis to compare the performance of ML predictive models. We searched PubMed, Embase, the Cochrane Library, and Web of Science for English-language studies using ML algorithms to predict the risk of DKD in patients with T2DM, covering the period from database inception to April 18, 2024. The primary performance metric for the models was the area under the receiver operating characteristic curve (AUC) with a 95% confidence interval (CI). The risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist. Results 26 studies that met the eligibility criteria were included into the meta-analysis. 25 studies performed internal validation, but only 8 studies conducted external validation. A total of 94 ML models were developed, with 81 models evaluated in the internal validation sets and 13 in the external validation sets. The pooled AUC was 0.839 (95% CI 0.787-0.890) in the internal validation and 0.830 (95% CI 0.784-0.877) in the external validation sets. Subgroup analysis based on the type of ML showed that the pooled AUC for traditional regression ML was 0.797 (95% CI 0.777-0.816), for ML was 0.811 (95% CI 0.785-0.836), and for deep learning was 0.863 (95% CI 0.825-0.900). A total of 26 ML models were included, and the AUCs of models that were used three or more times were pooled. Among them, the random forest (RF) models demonstrated the best performance with a pooled AUC of 0.848 (95% CI 0.785-0.911). Conclusion This meta-analysis demonstrates that ML exhibit high performance in predicting DKD risk in T2DM patients. However, challenges related to data bias during model development and validation still need to be addressed. Future research should focus on enhancing data transparency and standardization, as well as validating these models' generalizability through multicenter studies. Systematic Review Registration https://inplasy.com/inplasy-2024-9-0038/, identifier INPLASY202490038.
Collapse
Affiliation(s)
- Yihan Li
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
| | - Nan Jin
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
| | - Qiuzhong Zhan
- Faculty of Chinese Medicine, Macau University of Science and Technology, Macao, Macao SAR, China
| | - Yue Huang
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
| | - Aochuan Sun
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
- Graduate School of Beijing University of Chinese Medicine, Beijing, China
| | - Fen Yin
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
- Graduate School of Beijing University of Chinese Medicine, Beijing, China
| | - Zhuangzhuang Li
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
| | - Jiayu Hu
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
| | - Zhengtang Liu
- Department of Geriatrics, Xiyuan Hospital, China Academy of Traditional Chinese Medicine, Beijing, China
| |
Collapse
|
|
6
|
Abdalla MMI, Mohanraj J. Revolutionizing diabetic retinopathy screening and management: The role of artificial intelligence and machine learning. World J Clin Cases 2025; 13:101306. [PMID: 39959767 PMCID: PMC11606367 DOI: 10.12998/wjcc.v13.i5.101306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/10/2024] [Revised: 10/09/2024] [Accepted: 11/05/2024] [Indexed: 11/18/2024] Open
Abstract
Diabetic retinopathy (DR) remains a leading cause of vision impairment and blindness among individuals with diabetes, necessitating innovative approaches to screening and management. This editorial explores the transformative potential of artificial intelligence (AI) and machine learning (ML) in revolutionizing DR care. AI and ML technologies have demonstrated remarkable advancements in enhancing the accuracy, efficiency, and accessibility of DR screening, helping to overcome barriers to early detection. These technologies leverage vast datasets to identify patterns and predict disease progression with unprecedented precision, enabling clinicians to make more informed decisions. Furthermore, AI-driven solutions hold promise in personalizing management strategies for DR, incorporating predictive analytics to tailor interventions and optimize treatment pathways. By automating routine tasks, AI can reduce the burden on healthcare providers, allowing for a more focused allocation of resources towards complex patient care. This review aims to evaluate the current advancements and applications of AI and ML in DR screening, and to discuss the potential of these technologies in developing personalized management strategies, ultimately aiming to improve patient outcomes and reduce the global burden of DR. The integration of AI and ML in DR care represents a paradigm shift, offering a glimpse into the future of ophthalmic healthcare.
Collapse
Affiliation(s)
- Mona Mohamed Ibrahim Abdalla
- Department of Human Biology, School of Medicine, International Medical University, Bukit Jalil 57000, Kuala Lumpur, Malaysia
| | - Jaiprakash Mohanraj
- Department of Human Biology, School of Medicine, International Medical University, Bukit Jalil 57000, Kuala Lumpur, Malaysia
| |
Collapse
|
|
7
|
Tao Y, Xiong M, Peng Y, Yao L, Zhu H, Zhou Q, Ouyang J. Machine learning-based identification and validation of immune-related biomarkers for early diagnosis and targeted therapy in diabetic retinopathy. Gene 2025; 934:149015. [PMID: 39427825 DOI: 10.1016/j.gene.2024.149015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2024] [Revised: 10/07/2024] [Accepted: 10/16/2024] [Indexed: 10/22/2024]
Abstract
The early diagnosis of diabetic retinopathy (DR) is challenging, highlighting the urgent need to identify new biomarkers. Immune responses play a crucial role in DR, yet there are currently no reports of machine learning (ML) algorithms being utilized for the development of immune-related molecular markers in DR. Based on the datasets GSE102485 and GSE160306, differentially expressed genes (DEGs) were screened using Weighted Gene Co-expression Network Analysis (WGCNA). Five ML algorithms including Bayesian, Learning Vector Quantization (LVQ), Wrapper (Boruta), Random Forest (RF), and Logistic Regression were employed to select immune-related genes associated with DR (DR.Sig). Seven ML algorithms including Naive Bayes (NB), RF, Support Vector Machine (SVM), AdaBoost Classification Trees (AdaBoost), Boosted Logistic Regressions (LogitBoost), K-Nearest Neighbors (KNN), and Cancerclass were utilized to construct a predictive model for DR. The relationship between DR.Sig genes and immune cells was analyzed using single-sample Gene Set Enrichment Analysis (ssGSEA). Additionally, drug sensitivity prediction of DR.Sig genes and molecular docking were performed. Through the utilization of 5 ML algorithms, 6 immune-related biomarkers closely related to the occurrence of DR were identified, including FCGR2B, CSRP1, EDNRA, SDC2, TEK, and CIITA. The DR predictive model constructed based on these 6 DR.Sig genes using the Cancerclass algorithm demonstrated superior predictive performance compared to 4 previously published DR-related biomarkers. In vivo and in vitro experiments also provided strong validation of the expression of the 6 genes in DR. Positive correlations were observed between these genes and 22 types of immune cells. Molecular docking results revealed that CSRP1, EDNRA, and TEK exhibited the highest affinities with the small molecule compounds etoposide, FR-139317, and camptothecin, respectively. The models constructed based on various ML algorithms can effectively predict the occurrence of DR events and hold potential for targeted drug therapies, providing a basis for the early diagnosis and targeted treatment of DR.
Collapse
Affiliation(s)
- Yulin Tao
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang 330006, China; Department of Ophthalmology, Jiujiang No 1 Peoples Hospital, Jiujiang 332000, China
| | - Minqi Xiong
- The Chinese University of Hong Kong, Shenzhen 518100, China
| | - Yirui Peng
- School of Life Sciences, Xiamen University, Xiamen 361000, China
| | - Lili Yao
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang 330006, China
| | - Haibo Zhu
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang 330006, China
| | - Qiong Zhou
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang 330006, China.
| | - Jun Ouyang
- Department of Ophthalmology, Jiujiang No 1 Peoples Hospital, Jiujiang 332000, China.
| |
Collapse
|
|
8
|
Wang T, Chen R, Fan N, Zang L, Yuan S, Du P, Wu Q, Wang A, Li J, Kong X, Zhu W. Machine Learning and Deep Learning for Diagnosis of Lumbar Spinal Stenosis: Systematic Review and Meta-Analysis. J Med Internet Res 2024; 26:e54676. [PMID: 39715552 PMCID: PMC11704645 DOI: 10.2196/54676] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Revised: 10/23/2024] [Accepted: 11/11/2024] [Indexed: 12/25/2024] Open
Abstract
BACKGROUND Lumbar spinal stenosis (LSS) is a major cause of pain and disability in older individuals worldwide. Although increasing studies of traditional machine learning (TML) and deep learning (DL) were conducted in the field of diagnosing LSS and gained prominent results, the performance of these models has not been analyzed systematically. OBJECTIVE This systematic review and meta-analysis aimed to pool the results and evaluate the heterogeneity of the current studies in using TML or DL models to diagnose LSS, thereby providing more comprehensive information for further clinical application. METHODS This review was performed under the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines using articles extracted from PubMed, Embase databases, and Cochrane Library databases. Studies that evaluated DL or TML algorithms assessment value on diagnosing LSS were included, while those with duplicated or unavailable data were excluded. Quality Assessment of Diagnostic Accuracy Studies 2 was used to estimate the risk of bias in each study. The MIDAS module and the METAPROP module of Stata (StataCorp) were used for data synthesis and statistical analyses. RESULTS A total of 12 studies with 15,044 patients reported the assessment value of TML or DL models for diagnosing LSS. The risk of bias assessment yielded 4 studies with high risk of bias, 3 with unclear risk of bias, and 5 with completely low risk of bias. The pooled sensitivity and specificity were 0.84 (95% CI: 0.82-0.86; I2=99.06%) and 0.87 (95% CI 0.84-0.90; I2=98.7%), respectively. The diagnostic odds ratio was 36 (95% CI 26-49), the positive likelihood ratio (LR+) was 6.6 (95% CI 5.1-8.4), and the negative likelihood ratio (LR-) was 0.18 (95% CI 0.16-0.21). The summary receiver operating characteristic curves, the area under the curve of TML or DL models for diagnosing LSS of 0.92 (95% CI 0.89-0.94), indicating a high diagnostic value. CONCLUSIONS This systematic review and meta-analysis emphasize that despite the generally satisfactory diagnostic performance of artificial intelligence systems in the experimental stage for the diagnosis of LSS, none of them is reliable and practical enough to apply in real clinical practice. Further efforts, including optimization of model balance, widely accepted objective reference standards, multimodal strategy, large dataset for training and testing, external validation, and sufficient and scientific report, should be made to bridge the distance between current TML or DL models and real-life clinical applications in future studies. TRIAL REGISTRATION PROSPERO CRD42024566535; https://tinyurl.com/msx59x8k.
Collapse
Affiliation(s)
- Tianyi Wang
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Ruiyuan Chen
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Ning Fan
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Lei Zang
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Shuo Yuan
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Peng Du
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Qichao Wu
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Aobo Wang
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Jian Li
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Xiaochuan Kong
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Wenyi Zhu
- Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| |
Collapse
|
|
9
|
Li Y, Liang Z, Li Y, Cao Y, Zhang H, Dong B. Machine learning value in the diagnosis of vertebral fractures: A systematic review and meta-analysis. Eur J Radiol 2024; 181:111714. [PMID: 39241305 DOI: 10.1016/j.ejrad.2024.111714] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2024] [Revised: 07/28/2024] [Accepted: 08/30/2024] [Indexed: 09/09/2024]
Abstract
PURPOSE To evaluate the diagnostic accuracy of machine learning (ML) in detecting vertebral fractures, considering varying fracture classifications, patient populations, and imaging approaches. METHOD A systematic review and meta-analysis were conducted by searching PubMed, Embase, Cochrane Library, and Web of Science up to December 31, 2023, for studies using ML for vertebral fracture diagnosis. Bias risk was assessed using QUADAS-2. A bivariate mixed-effects model was used for the meta-analysis. Meta-analyses were performed according to five task types (vertebral fractures, osteoporotic vertebral fractures, differentiation of benign and malignant vertebral fractures, differentiation of acute and chronic vertebral fractures, and prediction of vertebral fractures). Subgroup analyses were conducted by different ML models (including ML and DL) and modeling methods (including CT, X-ray, MRI, and clinical features). RESULTS Eighty-one studies were included. ML demonstrated a diagnostic sensitivity of 0.91 and specificity of 0.95 for vertebral fractures. Subgroup analysis showed that DL (SROC 0.98) and CT (SROC 0.98) performed best overall. For osteoporotic fractures, ML showed a sensitivity of 0.93 and specificity of 0.96, with DL (SROC 0.99) and X-ray (SROC 0.99) performing better. For differentiating benign from malignant fractures, ML achieved a sensitivity of 0.92 and specificity of 0.93, with DL (SROC 0.96) and MRI (SROC 0.97) performing best. For differentiating acute from chronic vertebral fractures, ML showed a sensitivity of 0.92 and specificity of 0.93, with ML (SROC 0.96) and CT (SROC 0.97) performing best. For predicting vertebral fractures, ML had a sensitivity of 0.76 and specificity of 0.87, with ML (SROC 0.80) and clinical features (SROC 0.86) performing better. CONCLUSIONS ML, especially DL models applied to CT, MRI, and X-ray, shows high diagnostic accuracy for vertebral fractures. ML also effectively predicts osteoporotic vertebral fractures, aiding in tailored prevention strategies. Further research and validation are required to confirm ML's clinical efficacy.
Collapse
Affiliation(s)
- Yue Li
- Pain Ward of Rehabilitation Department, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710054, PR China
| | - Zhuang Liang
- Pain Ward of Rehabilitation Department, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710054, PR China
| | - Yingchun Li
- Pain Ward of Rehabilitation Department, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710054, PR China
| | - Yang Cao
- Pain Ward of Rehabilitation Department, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710054, PR China
| | - Hui Zhang
- Pain Ward of Rehabilitation Department, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710054, PR China
| | - Bo Dong
- Pain Ward of Rehabilitation Department, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province 710054, PR China.
| |
Collapse
|
|
10
|
Li X, Wen X, Shang X, Liu J, Zhang L, Cui Y, Luo X, Zhang G, Xie J, Huang T, Chen Z, Lyu Z, Wu X, Lan Y, Meng Q. Identification of diabetic retinopathy classification using machine learning algorithms on clinical data and optical coherence tomography angiography. Eye (Lond) 2024; 38:2813-2821. [PMID: 38871934 PMCID: PMC11427469 DOI: 10.1038/s41433-024-03173-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2023] [Revised: 04/10/2024] [Accepted: 06/06/2024] [Indexed: 06/15/2024] Open
Abstract
BACKGROUND To apply machine learning (ML) algorithms to perform multiclass diabetic retinopathy (DR) classification using both clinical data and optical coherence tomography angiography (OCTA). METHODS In this cross-sectional observational study, clinical data and OCTA parameters from 203 diabetic patients (203 eye) were used to establish the ML models, and those from 169 diabetic patients (169 eye) were used for independent external validation. The random forest, gradient boosting machine (GBM), deep learning and logistic regression algorithms were used to identify the presence of DR, referable DR (RDR) and vision-threatening DR (VTDR). Four different variable patterns based on clinical data and OCTA variables were examined. The algorithms' performance were evaluated using receiver operating characteristic curves and the area under the curve (AUC) was used to assess predictive accuracy. RESULTS The random forest algorithm on OCTA+clinical data-based variables and OCTA+non-laboratory factor-based variables provided the higher AUC values for DR, RDR and VTDR. The GBM algorithm produced similar results, albeit with slightly lower AUC values. Leading predictors of DR status included vessel density, retinal thickness and GCC thickness, as well as the body mass index, waist-to-hip ratio and glucose-lowering treatment. CONCLUSIONS ML-based multiclass DR classification using OCTA and clinical data can provide reliable assistance for screening, referral, and management DR populations.
Collapse
Affiliation(s)
- Xiaoli Li
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Xin Wen
- Department of Ophthalmology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xianwen Shang
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Junbin Liu
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Liang Zhang
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Ying Cui
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Xiaoyang Luo
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Guanrong Zhang
- Statistics Section, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong, China
| | - Jie Xie
- Department of Ophthalmology, Heyuan People's Hospital, Heyuan, China
| | - Tian Huang
- Department of Ophthalmology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Zhifan Chen
- Department of Ophthalmology, The Fourth Affiliated Hospital of Guangzhou Medical University, Guangzhou, China
| | - Zheng Lyu
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Xiyu Wu
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Yuqing Lan
- Department of Ophthalmology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
| | - Qianli Meng
- Department of Ophthalmology, Guangdong Eye Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
| |
Collapse
|
|
11
|
Dos Reis MA, Künas CA, da Silva Araújo T, Schneiders J, de Azevedo PB, Nakayama LF, Rados DRV, Umpierre RN, Berwanger O, Lavinsky D, Malerbi FK, Navaux POA, Schaan BD. Advancing healthcare with artificial intelligence: diagnostic accuracy of machine learning algorithm in diagnosis of diabetic retinopathy in the Brazilian population. Diabetol Metab Syndr 2024; 16:209. [PMID: 39210394 PMCID: PMC11360296 DOI: 10.1186/s13098-024-01447-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/20/2024] [Accepted: 08/12/2024] [Indexed: 09/04/2024] Open
Abstract
BACKGROUND In healthcare systems in general, access to diabetic retinopathy (DR) screening is limited. Artificial intelligence has the potential to increase care delivery. Therefore, we trained and evaluated the diagnostic accuracy of a machine learning algorithm for automated detection of DR. METHODS We included color fundus photographs from individuals from 4 databases (primary and specialized care settings), excluding uninterpretable images. The datasets consist of images from Brazilian patients, which differs from previous work. This modification allows for a more tailored application of the model to Brazilian patients, ensuring that the nuances and characteristics of this specific population are adequately captured. The sample was fractionated in training (70%) and testing (30%) samples. A convolutional neural network was trained for image classification. The reference test was the combined decision from three ophthalmologists. The sensitivity, specificity, and area under the ROC curve of the algorithm for detecting referable DR (moderate non-proliferative DR; severe non-proliferative DR; proliferative DR and/or clinically significant macular edema) were estimated. RESULTS A total of 15,816 images (4590 patients) were included. The overall prevalence of any degree of DR was 26.5%. Compared with human evaluators (manual method of diagnosing DR performed by an ophthalmologist), the deep learning algorithm achieved an area under the ROC curve of 0.98 (95% CI 0.97-0.98), with a specificity of 94.6% (95% CI 93.8-95.3) and a sensitivity of 93.5% (95% CI 92.2-94.9) at the point of greatest efficiency to detect referable DR. CONCLUSIONS A large database showed that this deep learning algorithm was accurate in detecting referable DR. This finding aids to universal healthcare systems like Brazil, optimizing screening processes and can serve as a tool for improving DR screening, making it more agile and expanding care access.
Collapse
Affiliation(s)
- Mateus A Dos Reis
- Graduate Program in Medical Sciences: Endocrinology, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil.
- Universidade Feevale, Novo Hamburgo, RS, Brazil.
| | - Cristiano A Künas
- Institute of Informatics, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Thiago da Silva Araújo
- Institute of Informatics, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Josiane Schneiders
- Graduate Program in Medical Sciences: Endocrinology, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | | | - Luis F Nakayama
- Department of Ophthalmology and Visual Sciences, Universidade Federal de São Paulo, São Paulo, Brazil
- Laboratory for Computational Physiology, Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Dimitris R V Rados
- Graduate Program in Medical Sciences: Endocrinology, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
- TelessaúdeRS Project, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Roberto N Umpierre
- TelessaúdeRS Project, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
- Department of Social Medicine, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil
| | - Otávio Berwanger
- The George Institute for Global Health, Imperial College London, London, UK
| | - Daniel Lavinsky
- Graduate Program in Medical Sciences: Endocrinology, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
- Department of Ophthalmology, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil
| | - Fernando K Malerbi
- Department of Ophthalmology and Visual Sciences, Universidade Federal de São Paulo, São Paulo, Brazil
| | - Philippe O A Navaux
- Institute of Informatics, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
| | - Beatriz D Schaan
- Graduate Program in Medical Sciences: Endocrinology, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
- Institute for Health Technology Assessment (IATS) - CNPq, Porto Alegre, Brazil
- Endocrinology Unit, Hospital de Clínicas de Porto Alegre, Porto Alegre, RS, Brazil
| |
Collapse
|
|
12
|
Riotto E, Gasser S, Potic J, Sherif M, Stappler T, Schlingemann R, Wolfensberger T, Konstantinidis L. Accuracy of Autonomous Artificial Intelligence-Based Diabetic Retinopathy Screening in Real-Life Clinical Practice. J Clin Med 2024; 13:4776. [PMID: 39200918 PMCID: PMC11355215 DOI: 10.3390/jcm13164776] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2024] [Revised: 07/24/2024] [Accepted: 08/08/2024] [Indexed: 09/02/2024] Open
Abstract
Background: In diabetic retinopathy, early detection and intervention are crucial in preventing vision loss and improving patient outcomes. In the era of artificial intelligence (AI) and machine learning, new promising diagnostic tools have emerged. The IDX-DR machine (Digital Diagnostics, Coralville, IA, USA) represents a diagnostic tool that combines advanced imaging techniques, AI algorithms, and deep learning methodologies to identify and classify diabetic retinopathy. Methods: All patients that participated in our AI-based DR screening were considered for this study. For this study, all retinal images were additionally reviewed retrospectively by two experienced retinal specialists. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated for the IDX-DR machine compared to the graders' responses. Results: We included a total of 2282 images from 1141 patients who were screened between January 2021 and January 2023 at the Jules Gonin Eye Hospital in Lausanne, Switzerland. Sensitivity was calculated to be 100% for 'no DR', 'mild DR', and 'moderate DR'. Specificity for no DR', 'mild DR', 'moderate DR', and 'severe DR' was calculated to be, respectively, 78.4%, 81.2%, 93.4%, and 97.6%. PPV was calculated to be, respectively, 36.7%, 24.6%, 1.4%, and 0%. NPV was calculated to be 100% for each category. Accuracy was calculated to be higher than 80% for 'no DR', 'mild DR', and 'moderate DR'. Conclusions: In this study, based in Jules Gonin Eye Hospital in Lausanne, we compared the autonomous diagnostic AI system of the IDX-DR machine detecting diabetic retinopathy to human gradings established by two experienced retinal specialists. Our results showed that the ID-x DR machine constantly overestimates the DR stages, thus permitting the clinicians to fully trust negative results delivered by the screening software. Nevertheless, all fundus images classified as 'mild DR' or greater should always be controlled by a specialist in order to assert whether the predicted stage is truly present.
Collapse
|
|
13
|
Ying B, Chandra RS, Wang J, Cui H, Oatts JT. Machine Learning Models for Predicting Cycloplegic Refractive Error and Myopia Status Based on Non-Cycloplegic Data in Chinese Students. Transl Vis Sci Technol 2024; 13:16. [PMID: 39120886 PMCID: PMC11318358 DOI: 10.1167/tvst.13.8.16] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2024] [Accepted: 06/28/2024] [Indexed: 08/10/2024] Open
Abstract
Purpose To develop and validate machine learning (ML) models for predicting cycloplegic refractive error and myopia status using noncycloplegic refractive error and biometric data. Methods Cross-sectional study of children aged five to 18 years who underwent biometry and autorefraction before and after cycloplegia. Myopia was defined as cycloplegic spherical equivalent refraction (SER) ≤-0.5 Diopter (D). Models were evaluated for predicting SER using R2 and mean absolute error (MAE) and myopia status using area under the receiver operating characteristic (ROC) curve (AUC). Best-performing models were further evaluated using sensitivity/specificity and comparison of observed versus predicted myopia prevalence rate overall and in each age group. Independent data sets were used for training (n = 1938) and validation (n = 1476). Results In the validation dataset, ML models predicted cycloplegic SER with high R2 (0.913-0.935) and low MAE (0.393-0.480 D). The AUC for predicting myopia was high (0.984-0.987). The best-performing model for SER (XGBoost) had high sensitivity and specificity (91.1% and 97.2%). Random forest (RF), the best-performing model for myopia, had high sensitivity and specificity (92.2% and 96.9%). Within each age group, difference between predicted and actual myopia prevalence was within 4%. Conclusions Using noncycloplegic refractive error and ocular biometric data, ML models performed well for predicting cycloplegic SER and myopia status. When measuring cycloplegic SER is not feasible, ML may provide a useful tool for estimating cycloplegic SER and myopia prevalence rate in epidemiological studies. Translational Relevance Using ML to predict cycloplegic refraction based on noncycloplegic data is a powerful tool for large, population-based studies of refractive error.
Collapse
Affiliation(s)
- Bole Ying
- Lower Merion High School, Ardmore, PA, USA
| | - Rajat S. Chandra
- University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
| | - Jianyong Wang
- Department of Ophthalmology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, P. R. China
| | - Hongguang Cui
- Department of Ophthalmology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, P. R. China
| | - Julius T. Oatts
- Department of Ophthalmology, University of California San Francisco, San Francisco, CA, USA
| |
Collapse
|
|
14
|
Richardson A, Kundu A, Henao R, Lee T, Scott BL, Grewal DS, Fekrat S. Multimodal Retinal Imaging Classification for Parkinson's Disease Using a Convolutional Neural Network. Transl Vis Sci Technol 2024; 13:23. [PMID: 39136960 PMCID: PMC11323992 DOI: 10.1167/tvst.13.8.23] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2024] [Accepted: 06/23/2024] [Indexed: 08/16/2024] Open
Abstract
Purpose Changes in retinal structure and microvasculature are connected to parallel changes in the brain. Two recent studies described machine learning algorithms trained on retinal images and quantitative data that identified Alzheimer's dementia and mild cognitive impairment with high accuracy. Prior studies also demonstrated retinal differences in individuals with PD. Herein, we developed a convolutional neural network (CNN) to classify multimodal retinal imaging from either a Parkinson's disease (PD) or control group. Methods We trained a CNN to receive retinal image inputs of optical coherence tomography (OCT) ganglion cell-inner plexiform layer (GC-IPL) thickness color maps, OCT angiography 6 × 6-mm en face macular images of the superficial capillary plexus, and ultra-widefield (UWF) fundus color and autofluorescence photographs to classify the retinal imaging as PD or control. The model consists of a shared pretrained VGG19 feature extractor and image-specific feature transformations which converge to a single output. Model results were assessed using receiver operating characteristic (ROC) curves and bootstrapped 95% confidence intervals for area under the ROC curve (AUC) values. Results In total, 371 eyes of 249 control subjects and 75 eyes of 52 PD subjects were used for training, validation, and testing. Our best CNN variant achieved an AUC of 0.918. UWF color photographs were the most effective imaging input, and GC-IPL thickness maps were the least contributory. Conclusions Using retinal images, our pilot CNN was able to identify individuals with PD and serves as a proof of concept to spur the collection of larger imaging datasets needed for clinical-grade algorithms. Translational Relevance Developing machine learning models for automated detection of Parkinson's disease from retinal imaging could lead to earlier and more widespread diagnoses.
Collapse
Affiliation(s)
- Alexander Richardson
- Duke Eye Center, Department of Ophthalmology, Duke University School of Medicine, Durham, NC, USA
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
- Department of Computer Science, Duke University, Durham, NC, USA
| | - Anita Kundu
- Duke Eye Center, Department of Ophthalmology, Duke University School of Medicine, Durham, NC, USA
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
| | - Ricardo Henao
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
- Department of Computer Science, Duke University, Durham, NC, USA
| | - Terry Lee
- Duke Eye Center, Department of Ophthalmology, Duke University School of Medicine, Durham, NC, USA
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
| | - Burton L. Scott
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
- Department of Neurology, Duke University School of Medicine, Durham, NC, USA
| | - Dilraj S. Grewal
- Duke Eye Center, Department of Ophthalmology, Duke University School of Medicine, Durham, NC, USA
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
| | - Sharon Fekrat
- Duke Eye Center, Department of Ophthalmology, Duke University School of Medicine, Durham, NC, USA
- iMIND Research Group, Duke University School of Medicine, Durham, NC, USA
- Department of Neurology, Duke University School of Medicine, Durham, NC, USA
| |
Collapse
|
|
15
|
Wu JH, Lin S, Moghimi S. Big data to guide glaucoma treatment. Taiwan J Ophthalmol 2024; 14:333-339. [PMID: 39430357 PMCID: PMC11488808 DOI: 10.4103/tjo.tjo-d-23-00068] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Accepted: 06/06/2023] [Indexed: 10/22/2024] Open
Abstract
Ophthalmology has been at the forefront of the medical application of big data. Often harnessed with a machine learning approach, big data has demonstrated potential to transform ophthalmic care, as evidenced by prior success on clinical tasks such as the screening of ophthalmic diseases and lesions via retinal images. With the recent establishment of various large ophthalmic datasets, there has been greater interest in determining whether the benefits of big data may extend to the downstream process of ophthalmic disease management. An area of substantial investigation has been the use of big data to help guide or streamline management of glaucoma, which remains a leading cause of irreversible blindness worldwide. In this review, we summarize relevant studies utilizing big data and discuss the application of the findings in the risk assessment and treatment of glaucoma.
Collapse
Affiliation(s)
- Jo-Hsuan Wu
- Hamilton Glaucoma Center, Shiley Eye Institute and Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla, CA, United States
| | - Shan Lin
- Glaucoma Center of San Francisco, San Francisco, CA, United States
| | - Sasan Moghimi
- Hamilton Glaucoma Center, Shiley Eye Institute and Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla, CA, United States
| |
Collapse
|
|
16
|
Wu JH, Lin S, Moghimi S. Application of artificial intelligence in glaucoma care: An updated review. Taiwan J Ophthalmol 2024; 14:340-351. [PMID: 39430354 PMCID: PMC11488804 DOI: 10.4103/tjo.tjo-d-24-00044] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2024] [Accepted: 06/05/2024] [Indexed: 10/22/2024] Open
Abstract
The application of artificial intelligence (AI) in ophthalmology has been increasingly explored in the past decade. Numerous studies have shown promising results supporting the utility of AI to improve the management of ophthalmic diseases, and glaucoma is of no exception. Glaucoma is an irreversible vision condition with insidious onset, complex pathophysiology, and chronic treatment. Since there remain various challenges in the clinical management of glaucoma, the potential role of AI in facilitating glaucoma care has garnered significant attention. In this study, we reviewed the relevant literature published in recent years that investigated the application of AI in glaucoma management. The main aspects of AI applications that will be discussed include glaucoma risk prediction, glaucoma detection and diagnosis, visual field estimation and pattern analysis, glaucoma progression detection, and other applications.
Collapse
Affiliation(s)
- Jo-Hsuan Wu
- Shiley Eye Institute and Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla, California
- Edward S. Harkness Eye Institute, Department of Ophthalmology, Columbia University Irving Medical Center, New York
| | - Shan Lin
- Glaucoma Center of San Francisco, San Francisco, CA, United States
| | - Sasan Moghimi
- Shiley Eye Institute and Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla, California
| |
Collapse
|
|
17
|
Malerbi FK, Nakayama LF, Melo GB, Stuchi JA, Lencione D, Prado PV, Ribeiro LZ, Dib SA, Regatieri CV. Automated Identification of Different Severity Levels of Diabetic Retinopathy Using a Handheld Fundus Camera and Single-Image Protocol. OPHTHALMOLOGY SCIENCE 2024; 4:100481. [PMID: 38694494 PMCID: PMC11060947 DOI: 10.1016/j.xops.2024.100481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 01/20/2024] [Accepted: 01/25/2024] [Indexed: 05/04/2024]
Abstract
Purpose To evaluate the performance of artificial intelligence (AI) systems embedded in a mobile, handheld retinal camera, with a single retinal image protocol, in detecting both diabetic retinopathy (DR) and more-than-mild diabetic retinopathy (mtmDR). Design Multicenter cross-sectional diagnostic study, conducted at 3 diabetes care and eye care facilities. Participants A total of 327 individuals with diabetes mellitus (type 1 or type 2) underwent a retinal imaging protocol enabling expert reading and automated analysis. Methods Participants underwent fundus photographs using a portable retinal camera (Phelcom Eyer). The captured images were automatically analyzed by deep learning algorithms retinal alteration score (RAS) and diabetic retinopathy alteration score (DRAS), consisting of convolutional neural networks trained on EyePACS data sets and fine-tuned using data sets of portable device fundus images. The ground truth was the classification of DR corresponding to adjudicated expert reading, performed by 3 certified ophthalmologists. Main Outcome Measures Primary outcome measures included the sensitivity and specificity of the AI system in detecting DR and/or mtmDR using a single-field, macula-centered fundus photograph for each eye, compared with a rigorous clinical reference standard comprising the reading center grading of 2-field imaging protocol using the International Classification of Diabetic Retinopathy severity scale. Results Of 327 analyzed patients (mean age, 57.0 ± 16.8 years; mean diabetes duration, 16.3 ± 9.7 years), 307 completed the study protocol. Sensitivity and specificity of the AI system were high in detecting any DR with DRAS (sensitivity, 90.48% [95% confidence interval (CI), 84.99%-94.46%]; specificity, 90.65% [95% CI, 84.54%-94.93%]) and mtmDR with the combination of RAS and DRAS (sensitivity, 90.23% [95% CI, 83.87%-94.69%]; specificity, 85.06% [95% CI, 78.88%-90.00%]). The area under the receiver operating characteristic curve was 0.95 for any DR and 0.89 for mtmDR. Conclusions This study showed a high accuracy for the detection of DR in different levels of severity with a single retinal photo per eye in an all-in-one solution, composed of a portable retinal camera powered by AI. Such a strategy holds great potential for increasing coverage rates of screening programs, contributing to prevention of avoidable blindness. Financial Disclosures F.K.M. is a medical consultant for Phelcom Technologies. J.A.S. is Chief Executive Officer and proprietary of Phelcom Technologies. D.L. is Chief Technology Officer and proprietary of Phelcom Technologies. P.V.P. is an employee at Phelcom Technologies.
Collapse
|
|
18
|
Xie LZ, Dou XY, Ge TH, Han XG, Zhang Q, Wang QL, Chen S, He D, Tian W. Deep learning-based identification of spine growth potential on EOS radiographs. Eur Radiol 2024; 34:2849-2860. [PMID: 37848772 DOI: 10.1007/s00330-023-10308-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Revised: 07/21/2023] [Accepted: 08/15/2023] [Indexed: 10/19/2023]
Abstract
OBJECTIVES To develop an automatic computer-based method that can help clinicians in assessing spine growth potential based on EOS radiographs. METHODS We developed a deep learning-based (DL) algorithm that can mimic the human judgment process to automatically determine spine growth potential and the Risser sign based on full-length spine EOS radiographs. A total of 3383 EOS cases were collected and used for the training and test of the algorithm. Subsequently, the completed DL algorithm underwent clinical validation on an additional 440 cases and was compared to the evaluations of four clinicians. RESULTS Regarding the Risser sign, the weighted kappa value of our DL algorithm was 0.933, while that of the four clinicians ranged from 0.909 to 0.930. In the assessment of spine growth potential, the kappa value of our DL algorithm was 0.944, while the kappa values of the four clinicians were 0.916, 0.934, 0.911, and 0.920, respectively. Furthermore, our DL algorithm obtained a slightly higher accuracy (0.973) and Youden index (0.952) compared to the best values achieved by the four clinicians. In addition, the speed of our DL algorithm was 15.2 ± 0.3 s/40 cases, much faster than the inference speeds of the clinicians, ranging from 177.2 ± 28.0 s/40 cases to 241.2 ± 64.1 s/40 cases. CONCLUSIONS Our algorithm demonstrated comparable or even better performance compared to clinicians in assessing spine growth potential. This stable, efficient, and convenient algorithm seems to be a promising approach to assist doctors in clinical practice and deserves further study. CLINICAL RELEVANCE STATEMENT This method has the ability to quickly ascertain the spine growth potential based on EOS radiographs, and it holds promise to provide assistance to busy doctors in certain clinical scenarios. KEY POINTS • In the clinic, there is no available computer-based method that can automatically assess spine growth potential. • We developed a deep learning-based method that could automatically ascertain spine growth potential. • Compared with the results of the clinicians, our algorithm got comparable results.
Collapse
Affiliation(s)
- Lin-Zhen Xie
- Peking University Fourth School of Clinical Medicine, Beijing, China
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China
| | - Xin-Yu Dou
- Peking University Fourth School of Clinical Medicine, Beijing, China
- Department of Orthopaedics, Peking University Third Hospital, Beijing, China
| | - Teng-Hui Ge
- Peking University Fourth School of Clinical Medicine, Beijing, China
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China
| | - Xiao-Guang Han
- Peking University Fourth School of Clinical Medicine, Beijing, China
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China
| | - Qi Zhang
- Peking University Fourth School of Clinical Medicine, Beijing, China
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China
| | - Qi-Long Wang
- Peking University Fourth School of Clinical Medicine, Beijing, China
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China
| | - Shuo Chen
- Peking University Fourth School of Clinical Medicine, Beijing, China
| | - Da He
- Peking University Fourth School of Clinical Medicine, Beijing, China.
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China.
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China.
| | - Wei Tian
- Peking University Fourth School of Clinical Medicine, Beijing, China.
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China.
- Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China.
| |
Collapse
|
|
19
|
Jiang A, Li J, Wang L, Zha W, Lin Y, Zhao J, Fang Z, Shen G. Multi-feature, Chinese-Western medicine-integrated prediction model for diabetic peripheral neuropathy based on machine learning and SHAP. Diabetes Metab Res Rev 2024; 40:e3801. [PMID: 38616511 DOI: 10.1002/dmrr.3801] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/27/2022] [Revised: 09/18/2023] [Accepted: 03/14/2024] [Indexed: 04/16/2024]
Abstract
BACKGROUND Clinical studies have shown that diabetic peripheral neuropathy (DPN) has been on the rise, with most patients presenting with severe and progressive symptoms. Currently, most of the available prediction models for DPN are derived from general clinical information and laboratory indicators. Several Traditional Chinese medicine (TCM) indicators have been utilised to construct prediction models. In this study, we established a novel machine learning-based multi-featured Chinese-Western medicine-integrated prediction model for DPN using clinical features of TCM. MATERIALS AND METHODS The clinical data of 1581 patients with Type 2 diabetes mellitus (T2DM) treated at the Department of Endocrinology of the First Affiliated Hospital of Anhui University of Chinese Medicine were collected. The data (including general information, laboratory parameters and TCM features) of 1142 patients with T2DM were selected after data cleaning. After baseline description analysis of the variables, the data were divided into training and validation sets. Four prediction models were established and their performance was evaluated using validation sets. Meanwhile, the accuracy, precision, recall, F1 score and area under the curve (AUC) of ROC were calculated using ten-fold cross-validation to further assess the performance of the models. An explanatory analysis of the results of the DPN prediction model was carried out using the SHAP framework based on machine learning-based prediction models. RESULTS Of the 1142 patients with T2DM, 681 had a comorbidity of DPN, while 461 did not. There was a significant difference between the two groups in terms of age, cause of disease, systolic pressure, HbA1c, ALT, RBC, Cr, BUN, red blood cells in the urine, glucose in the urine, and protein in the urine (p < 0.05). T2DM patients with a comorbidity of DPN exhibited diverse TCM symptoms, including limb numbness, limb pain, hypodynamia, thirst with desire for drinks, dry mouth and throat, blurred vision, gloomy complexion, and unsmooth pulse, with statistically significant differences (p < 0.05). Our results showed that the proposed multi-featured Chinese-Western medicine-integrated prediction model was superior to conventional models without characteristic TCM indicators. The model showed the best performance (accuracy = 0.8109, precision = 0.8029, recall = 0.9060, F1 score = 0.8511, and AUC = 0.9002). SHAP analysis revealed that the dominant risk factors that caused DPN were TCM symptoms (limb numbness, thirst with desire for drinks, blurred vision), age, cause of disease, and glycosylated haemoglobin. These risk factors were exerted positive effects on the DPN prediction models. CONCLUSIONS A multi-feature, Chinese-Western medicine-integrated prediction model for DPN was established and validated. The model improves early-stage identification of high-risk groups for DPN in the diagnosis and treatment of T2DM, while also providing informative support for the intelligent management of chronic conditions such as diabetes.
Collapse
Affiliation(s)
- Aijuan Jiang
- Anhui University of Chinese Medicine, Hefei, China
| | - Jiajie Li
- Anhui University of Chinese Medicine, Hefei, China
| | - Lujie Wang
- Anhui University of Chinese Medicine, Hefei, China
| | - Wenshu Zha
- Hefei University of Technology, Hefei, China
| | - Yixuan Lin
- The First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China
| | - Jindong Zhao
- The First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China
| | - Zhaohui Fang
- The First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China
| | - Guoming Shen
- Anhui University of Chinese Medicine, Hefei, China
| |
Collapse
|
|
20
|
Guan H, Wang Y, Niu P, Zhang Y, Zhang Y, Miao R, Fang X, Yin R, Zhao S, Liu J, Tian J. The role of machine learning in advancing diabetic foot: a review. Front Endocrinol (Lausanne) 2024; 15:1325434. [PMID: 38742201 PMCID: PMC11089132 DOI: 10.3389/fendo.2024.1325434] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/21/2023] [Accepted: 04/09/2024] [Indexed: 05/16/2024] Open
Abstract
Background Diabetic foot complications impose a significant strain on healthcare systems worldwide, acting as a principal cause of morbidity and mortality in individuals with diabetes mellitus. While traditional methods in diagnosing and treating these conditions have faced limitations, the emergence of Machine Learning (ML) technologies heralds a new era, offering the promise of revolutionizing diabetic foot care through enhanced precision and tailored treatment strategies. Objective This review aims to explore the transformative impact of ML on managing diabetic foot complications, highlighting its potential to advance diagnostic accuracy and therapeutic approaches by leveraging developments in medical imaging, biomarker detection, and clinical biomechanics. Methods A meticulous literature search was executed across PubMed, Scopus, and Google Scholar databases to identify pertinent articles published up to March 2024. The search strategy was carefully crafted, employing a combination of keywords such as "Machine Learning," "Diabetic Foot," "Diabetic Foot Ulcers," "Diabetic Foot Care," "Artificial Intelligence," and "Predictive Modeling." This review offers an in-depth analysis of the foundational principles and algorithms that constitute ML, placing a special emphasis on their relevance to the medical sciences, particularly within the specialized domain of diabetic foot pathology. Through the incorporation of illustrative case studies and schematic diagrams, the review endeavors to elucidate the intricate computational methodologies involved. Results ML has proven to be invaluable in deriving critical insights from complex datasets, enhancing both the diagnostic precision and therapeutic planning for diabetic foot management. This review highlights the efficacy of ML in clinical decision-making, underscored by comparative analyses of ML algorithms in prognostic assessments and diagnostic applications within diabetic foot care. Conclusion The review culminates in a prospective assessment of the trajectory of ML applications in the realm of diabetic foot care. We believe that despite challenges such as computational limitations and ethical considerations, ML remains at the forefront of revolutionizing treatment paradigms for the management of diabetic foot complications that are globally applicable and precision-oriented. This technological evolution heralds unprecedented possibilities for treatment and opportunities for enhancing patient care.
Collapse
Affiliation(s)
- Huifang Guan
- College of Traditional Chinese Medicine, Changchun University of Chinese Medicine, Changchun, China
| | - Ying Wang
- College of Traditional Chinese Medicine, Changchun University of Chinese Medicine, Changchun, China
| | - Ping Niu
- Department of Encephalopathy, The Affiliated Hospital of Changchun University of Chinese Medicine, Changchun, Jilin, China
| | - Yuxin Zhang
- Institute of Metabolic Diseases, Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| | - Yanjiao Zhang
- Institute of Metabolic Diseases, Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| | - Runyu Miao
- Institute of Metabolic Diseases, Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| | - Xinyi Fang
- Institute of Metabolic Diseases, Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| | - Ruiyang Yin
- Institute of Metabolic Diseases, Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| | - Shuang Zhao
- College of Traditional Chinese Medicine, Changchun University of Chinese Medicine, Changchun, China
| | - Jun Liu
- Department of Hand Surgery, Second Hospital of Jilin University, Changchun, China
| | - Jiaxing Tian
- Institute of Metabolic Diseases, Guang’anmen Hospital, China Academy of Chinese Medical Sciences, Beijing, China
| |
Collapse
|
|
21
|
Abstract
Artificial intelligence (AI) is an epoch-making technology, among which the 2 most advanced parts are machine learning and deep learning algorithms that have been further developed by machine learning, and it has been partially applied to assist EUS diagnosis. AI-assisted EUS diagnosis has been reported to have great value in the diagnosis of pancreatic tumors and chronic pancreatitis, gastrointestinal stromal tumors, esophageal early cancer, biliary tract, and liver lesions. The application of AI in EUS diagnosis still has some urgent problems to be solved. First, the development of sensitive AI diagnostic tools requires a large amount of high-quality training data. Second, there is overfitting and bias in the current AI algorithms, leading to poor diagnostic reliability. Third, the value of AI still needs to be determined in prospective studies. Fourth, the ethical risks of AI need to be considered and avoided.
Collapse
Affiliation(s)
- Deyu Zhang
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| | - Chang Wu
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| | - Zhenghui Yang
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| | - Hua Yin
- Department of Gastroenterology, General Hospital of Ningxia Medical University, Yinchuan 750004, Ningxia Hui Autonomous Region, China
| | - Yue Liu
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| | - Wanshun Li
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| | - Haojie Huang
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| | - Zhendong Jin
- Department of Gastroenterology, Changhai hospital, Naval Medical University, Shanghai 200433, China
| |
Collapse
|
|
22
|
Vilela MAP, Arrigo A, Parodi MB, da Silva Mengue C. Smartphone Eye Examination: Artificial Intelligence and Telemedicine. Telemed J E Health 2024; 30:341-353. [PMID: 37585566 DOI: 10.1089/tmj.2023.0041] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/18/2023] Open
Abstract
Background: The current medical scenario is closely linked to recent progress in telecommunications, photodocumentation, and artificial intelligence (AI). Smartphone eye examination may represent a promising tool in the technological spectrum, with special interest for primary health care services. Obtaining fundus imaging with this technique has improved and democratized the teaching of fundoscopy, but in particular, it contributes greatly to screening diseases with high rates of blindness. Eye examination using smartphones essentially represents a cheap and safe method, thus contributing to public policies on population screening. This review aims to provide an update on the use of this resource and its future prospects, especially as a screening and ophthalmic diagnostic tool. Methods: In this review, we surveyed major published advances in retinal and anterior segment analysis using AI. We performed an electronic search on the Medical Literature Analysis and Retrieval System Online (MEDLINE), EMBASE, and Cochrane Library for published literature without a deadline. We included studies that compared the diagnostic accuracy of smartphone ophthalmoscopy for detecting prevalent diseases with an accurate or commonly employed reference standard. Results: There are few databases with complete metadata, providing demographic data, and few databases with sufficient images involving current or new therapies. It should be taken into consideration that these are databases containing images captured using different systems and formats, with information often being excluded without essential detailing of the reasons for exclusion, which further distances them from real-life conditions. The safety, portability, low cost, and reproducibility of smartphone eye images are discussed in several studies, with encouraging results. Conclusions: The high level of agreement between conventional and a smartphone method shows a powerful arsenal for screening and early diagnosis of the main causes of blindness, such as cataract, glaucoma, diabetic retinopathy, and age-related macular degeneration. In addition to streamlining the medical workflow and bringing benefits for public health policies, smartphone eye examination can make safe and quality assessment available to the population.
Collapse
Affiliation(s)
| | - Alessandro Arrigo
- Department of Ophthalmology, Scientific Institute San Raffaele, Milan, Italy
- University Vita-Salute, Milan, Italy
| | - Maurizio Battaglia Parodi
- Department of Ophthalmology, Scientific Institute San Raffaele, Milan, Italy
- University Vita-Salute, Milan, Italy
| | - Carolina da Silva Mengue
- Post-Graduation Ophthalmological School, Ivo Corrêa-Meyer/Cardiology Institute, Porto Alegre, Brazil
| |
Collapse
|
|
23
|
Prashar J, Tay N. Performance of artificial intelligence for the detection of pathological myopia from colour fundus images: a systematic review and meta-analysis. Eye (Lond) 2024; 38:303-314. [PMID: 37550366 PMCID: PMC10810874 DOI: 10.1038/s41433-023-02680-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 07/12/2023] [Accepted: 07/19/2023] [Indexed: 08/09/2023] Open
Abstract
BACKGROUND Pathological myopia (PM) is a major cause of worldwide blindness and represents a serious threat to eye health globally. Artificial intelligence (AI)-based methods are gaining traction in ophthalmology as highly sensitive and specific tools for screening and diagnosis of many eye diseases. However, there is currently a lack of high-quality evidence for their use in the diagnosis of PM. METHODS A systematic review and meta-analysis of studies evaluating the diagnostic performance of AI-based tools in PM was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidance. Five electronic databases were searched, results were assessed against the inclusion criteria and a quality assessment was conducted for included studies. Model sensitivity and specificity were pooled using the DerSimonian and Laird (random-effects) model. Subgroup analysis and meta-regression were performed. RESULTS Of 1021 citations identified, 17 studies were included in the systematic review and 11 studies, evaluating 165,787 eyes, were included in the meta-analysis. The area under the summary receiver operator curve (SROC) was 0.9905. The pooled sensitivity was 95.9% [95.5%-96.2%], and the overall pooled specificity was 96.5% [96.3%-96.6%]. The pooled diagnostic odds ratio (DOR) for detection of PM was 841.26 [418.37-1691.61]. CONCLUSIONS This systematic review and meta-analysis provides robust early evidence that AI-based, particularly deep-learning based, diagnostic tools are a highly specific and sensitive modality for the detection of PM. There is potential for such tools to be incorporated into ophthalmic public health screening programmes, particularly in resource-poor areas with a substantial prevalence of high myopia.
Collapse
Affiliation(s)
- Jai Prashar
- University College London, London, UK.
- Moorfields Eye Hospital NHS Foundation Trust, London, UK.
| | | |
Collapse
|
|
24
|
Kemp O, Bascaran C, Cartwright E, McQuillan L, Matthew N, Shillingford-Ricketts H, Zondervan M, Foster A, Burton M. Real-world evaluation of smartphone-based artificial intelligence to screen for diabetic retinopathy in Dominica: a clinical validation study. BMJ Open Ophthalmol 2023; 8:e001491. [PMID: 38135351 DOI: 10.1136/bmjophth-2023-001491] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Accepted: 12/10/2023] [Indexed: 12/24/2023] Open
Abstract
OBJECTIVE Several artificial intelligence (AI) systems for diabetic retinopathy screening have been validated but there is limited evidence on their performance in real-world settings. This study aimed to assess the performance of an AI software deployed within the diabetic retinopathy screening programme in Dominica. METHODS AND ANALYSIS We conducted a prospective, cross-sectional clinical validation study. Patients with diabetes aged 18 years and above attending the diabetic retinopathy screening in primary care facilities in Dominica from 5 June to 3 July 2021 were enrolled.Grading was done at the point of care by the field grader, followed by counselling and referral to the eye clinic. Images were then graded by an AI system. Sensitivity, specificity with 95% CIs and area under the curve (AUC) were calculated for comparing the AI to field grader as gold standard. RESULTS A total of 587 participants were screened. The AI had a sensitivity and specificity for detecting referable diabetic retinopathy of 77.5% and 91.5% compared with the grader, for all participants, including ungradable images. The AUC was 0.8455. Excluding 52 participants deemed ungradable by the grader, the AI had a sensitivity and specificity of 81.4% and 91.5%, with an AUC of 0.9648. CONCLUSION This study provides evidence that AI has the potential to be deployed to assist a diabetic screening programme in a middle-income real-world setting and perform with reasonable accuracy compared with a specialist grader.
Collapse
Affiliation(s)
- Oliver Kemp
- London School of Hygiene and Tropical Medicine, London, UK
| | | | | | | | - Nanda Matthew
- Dominica China Friendship Hospital, Roseau, Dominica
| | | | | | - Allen Foster
- London School of Hygiene and Tropical Medicine, London, UK
| | - Matthew Burton
- London School of Hygiene and Tropical Medicine, London, UK
- Moorfields Eye Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
|
25
|
Ren Z, Chen B, Hong C, Yuan J, Deng J, Chen Y, Ye J, Li Y. The value of machine learning in preoperative identification of lymph node metastasis status in endometrial cancer: a systematic review and meta-analysis. Front Oncol 2023; 13:1289050. [PMID: 38173835 PMCID: PMC10761539 DOI: 10.3389/fonc.2023.1289050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 12/06/2023] [Indexed: 01/05/2024] Open
Abstract
Background The early identification of lymph node metastasis status in endometrial cancer (EC) is a serious challenge in clinical practice. Some investigators have introduced machine learning into the early identification of lymph node metastasis in EC patients. However, the predictive value of machine learning is controversial due to the diversity of models and modeling variables. To this end, we carried out this systematic review and meta-analysis to systematically discuss the value of machine learning for the early identification of lymph node metastasis in EC patients. Methods A systematic search was conducted in Pubmed, Cochrane, Embase, and Web of Science until March 12, 2023. PROBAST was used to assess the risk of bias in the included studies. In the process of meta-analysis, subgroup analysis was performed according to modeling variables (clinical features, radiomic features, and radiomic features combined with clinical features) and different types of models in various variables. Results This systematic review included 50 primary studies with a total of 103,752 EC patients, 12,579 of whom had positive lymph node metastasis. Meta-analysis showed that among the machine learning models constructed by the three categories of modeling variables, the best model was constructed by combining radiomic features with clinical features, with a pooled c-index of 0.907 (95%CI: 0.886-0.928) in the training set and 0.823 (95%CI: 0.757-0.890) in the validation set, and good sensitivity and specificity. The c-index of the machine learning model constructed based on clinical features alone was not inferior to that based on radiomic features only. In addition, logistic regression was found to be the main modeling method and has ideal predictive performance with different categories of modeling variables. Conclusion Although the model based on radiomic features combined with clinical features has the best predictive efficiency, there is no recognized specification for the application of radiomics at present. In addition, the logistic regression constructed by clinical features shows good sensitivity and specificity. In this context, large-sample studies covering different races are warranted to develop predictive nomograms based on clinical features, which can be widely applied in clinical practice. Systematic review registration https://www.crd.york.ac.uk/PROSPERO, identifier CRD42023420774.
Collapse
Affiliation(s)
- Zhonglian Ren
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| | - Banghong Chen
- Data Science R&D Center of Yanchang Technology, Chengdu, China
| | - Changying Hong
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| | - Jiaying Yuan
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| | - Junying Deng
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| | - Yan Chen
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| | - Jionglin Ye
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| | - Yanqin Li
- Department of Obstetrics and Gynecology, Chengdu Shuangliu Distract Maternal and Child Health Hospital, Chengdu, China
| |
Collapse
|
|
26
|
Zhang YY, Chen BX, Chen Z, Wan Q. Correlation study of renal function indices with diabetic peripheral neuropathy and diabetic retinopathy in T2DM patients with normal renal function. Front Public Health 2023; 11:1302615. [PMID: 38174078 PMCID: PMC10762307 DOI: 10.3389/fpubh.2023.1302615] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Accepted: 11/30/2023] [Indexed: 01/05/2024] Open
Abstract
Background The anticipation of diabetes-related complications remains a challenge for numerous T2DM patients, as there is presently no effective method for early prediction of these complications. This study aims to investigate the association between renal function-related indicators and the occurrence of peripheral neuropathy and retinopathy in individuals diagnosed with type 2 diabetes mellitus (T2DM) who currently have normal renal function. Methods Patients with T2DM who met the criteria were selected from the MMC database and divided into diabetic peripheral neuropathy (DPN) and diabetic retinopathy (DR) groups, with a total of 859 and 487 patients included, respectively. Multivariate logistic regression was used to analyze the relationship between blood urea nitrogen (BUN), creatinine (Cr), uric acid (UA), urine albumin(ALB), albumin-to-creatinine ratio (ACR), estimated glomerular filtration rate (eGFR), and diabetic peripheral neuropathy and retinopathy. Spearman correlation analysis was used to determine the correlation between these indicators and peripheral neuropathy and retinopathy in diabetes. Results In a total of 221 patients diagnosed with DPN, we found positive correlation between the prevalence of DPN and eGFR (18.2, 23.3, 35.7%, p < 0.05). Specifically, as BUN (T1: references; T2:OR:0.598, 95%CI: 0.403, 0.886; T3:OR:1.017, 95%CI: 0.702, 1.473; p < 0.05) and eGFR (T1: references; T2:OR:1.294, 95%CI: 0.857, 1.953; T3:OR:2.142, 95%CI: 1.425, 3.222; p < 0.05) increased, the odds ratio of DPN also increased. Conversely, with an increase in Cr(T1: references; T2:OR:0.86, 95%CI: 0.56, 1.33; T3:OR:0.57, 95%CI: 0.36, 0.91; p < 0.05), the odds ratio of DPN decreased. Furthermore, when considering sensitivity and specificity, eGFR exhibited a sensitivity of 65.2% and specificity of 54.4%, with a 95% confidence interval of 0.568-0.656. Conclusion In this experimental sample, we found a clear positive correlation between eGFR and DPN prevalence.
Collapse
Affiliation(s)
- Yue-Yang Zhang
- Department of Endocrinology and Metabolism, The Affiliated Hospital of Southwest Medical University, Luzhou, China
- Metabolic Vascular Disease Key Laboratory of Sichuan Province, Luzhou, China
- Sichuan Clinical Research Center for Diabetes and Metabolism, Luzhou, China
- Sichuan Clinical Research Center for Nephropathy, Luzhou, China
- Cardiovascular and Metabolic Diseases Key Laboratory of Luzhou, Luzhou, China
- Southwest Medical University, Luzhou, China
| | | | - Zhuang Chen
- Medical Laboratory Centre, The Affiliated Hospital of Southwest Medical University, Luzhou, China
| | - Qin Wan
- Department of Endocrinology and Metabolism, The Affiliated Hospital of Southwest Medical University, Luzhou, China
- Metabolic Vascular Disease Key Laboratory of Sichuan Province, Luzhou, China
- Sichuan Clinical Research Center for Diabetes and Metabolism, Luzhou, China
- Sichuan Clinical Research Center for Nephropathy, Luzhou, China
- Cardiovascular and Metabolic Diseases Key Laboratory of Luzhou, Luzhou, China
| |
Collapse
|
|
27
|
Lee CH. Meta-Analysis and Machine Learning: Advancement of Analytic Methodology. Korean J Neurotrauma 2023; 19:407-408. [PMID: 38222840 PMCID: PMC10782107 DOI: 10.13004/kjnt.2023.19.e63] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Revised: 12/14/2023] [Accepted: 12/14/2023] [Indexed: 01/16/2024] Open
Affiliation(s)
- Chang-Hyun Lee
- Department of Neurosurgery, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, Korea
| |
Collapse
|
|
28
|
He S, Joseph S, Bulloch G, Jiang F, Kasturibai H, Kim R, Ravilla TD, Wang Y, Shi D, He M. Bridging the Camera Domain Gap With Image-to-Image Translation Improves Glaucoma Diagnosis. Transl Vis Sci Technol 2023; 12:20. [PMID: 38133514 PMCID: PMC10746931 DOI: 10.1167/tvst.12.12.20] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2023] [Accepted: 09/15/2023] [Indexed: 12/23/2023] Open
Abstract
Purpose The purpose of this study was to improve the automated diagnosis of glaucomatous optic neuropathy (GON), we propose a generative adversarial network (GAN) model that translates Optain images to Topcon images. Methods We trained the GAN model on 725 paired images from Topcon and Optain cameras and externally validated it using an additional 843 paired images collected from the Aravind Eye Hospital in India. An optic disc segmentation model was used to assess the disparities in disc parameters across cameras. The performance of the translated images was evaluated using root mean square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), 95% limits of agreement (LOA), Pearson's correlations, and Cohen's Kappa coefficient. The evaluation compared the performance of the GON model on Topcon photographs as a reference to that of Optain photographs and GAN-translated photographs. Results The GAN model significantly reduced Optain false positive results for GON diagnosis, with RMSE, PSNR, and SSIM of GAN images being 0.067, 14.31, and 0.64, respectively, the mean difference of VCDR and cup-to-disc area ratio between Topcon and GAN images being 0.03, 95% LOA ranging from -0.09 to 0.15 and -0.05 to 0.10. Pearson correlation coefficients increased from 0.61 to 0.85 in VCDR and 0.70 to 0.89 in cup-to-disc area ratio, whereas Cohen's Kappa improved from 0.32 to 0.60 after GAN translation. Conclusions Image-to-image translation across cameras can be achieved by using GAN to solve the problem of disc overexposure in Optain cameras. Translational Relevance Our approach enhances the generalizability of deep learning diagnostic models, ensuring their performance on cameras that are outside of the original training data set.
Collapse
Affiliation(s)
- Shuang He
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangzhou, China
- Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China
| | - Sanil Joseph
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia
- Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Australia
- Lions Aravind Institute of Community Ophthalmology, Aravind Eye Care System, Madurai, India
| | - Gabriella Bulloch
- Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Australia
| | - Feng Jiang
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangzhou, China
- Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China
| | | | - Ramasamy Kim
- Aravind Eye Hospital and Post Graduate Institute, Madurai, India
| | - Thulasiraj D. Ravilla
- Lions Aravind Institute of Community Ophthalmology, Aravind Eye Care System, Madurai, India
| | - Yueye Wang
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangzhou, China
- Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China
| | - Danli Shi
- School of Optometry, The Hong Kong Polytechnic University, Kowloon, Hong Kong SAR, China
| | - Mingguang He
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangzhou, China
- Aravind Eye Hospital and Post Graduate Institute, Madurai, India
| |
Collapse
|
|
29
|
Wolf RM, Channa R, Lehmann HP, Abramoff MD, Liu TA. Clinical Implementation of Autonomous Artificial Intelligence Systems for Diabetic Eye Exams: Considerations for Success. Clin Diabetes 2023; 42:142-149. [PMID: 38230333 PMCID: PMC10788651 DOI: 10.2337/cd23-0019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/18/2024]
Affiliation(s)
- Risa M. Wolf
- Department of Pediatric Endocrinology and Diabetes, Johns Hopkins University School of Medicine, Baltimore, MD
| | - Roomasa Channa
- Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, WI
| | - Harold P. Lehmann
- Section on Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD
| | - Michael D. Abramoff
- Department of Ophthalmology and Visual Sciences, The University of Iowa, Iowa City, IA
- Digital Diagnostics, Coralville, IA
| | - T.Y. Alvin Liu
- Wilmer Eye Institute at the Johns Hopkins University School of Medicine, Baltimore, MD
| |
Collapse
|
|
30
|
Li Y, Dong B, Yuan P. The diagnostic value of machine learning for the classification of malignant bone tumor: a systematic evaluation and meta-analysis. Front Oncol 2023; 13:1207175. [PMID: 37746301 PMCID: PMC10513372 DOI: 10.3389/fonc.2023.1207175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Accepted: 08/23/2023] [Indexed: 09/26/2023] Open
Abstract
Background Malignant bone tumors are a type of cancer with varying malignancy and prognosis. Accurate diagnosis and classification are crucial for treatment and prognosis assessment. Machine learning has been introduced for early differential diagnosis of malignant bone tumors, but its performance is controversial. This systematic review and meta-analysis aims to explore the diagnostic value of machine learning for malignant bone tumors. Methods PubMed, Embase, Cochrane Library, and Web of Science were searched for literature on machine learning in the differential diagnosis of malignant bone tumors up to October 31, 2022. The risk of bias assessment was conducted using QUADAS-2. A bivariate mixed-effects model was used for meta-analysis, with subgroup analyses by machine learning methods and modeling approaches. Results The inclusion comprised 31 publications with 382,371 patients, including 141,315 with malignant bone tumors. Meta-analysis results showed machine learning sensitivity and specificity of 0.87 [95% CI: 0.81,0.91] and 0.91 [95% CI: 0.86,0.94] in the training set, and 0.83 [95% CI: 0.74,0.89] and 0.87 [95% CI: 0.79,0.92] in the validation set. Subgroup analysis revealed MRI-based radiomics was the most common approach, with sensitivity and specificity of 0.85 [95% CI: 0.74,0.91] and 0.87 [95% CI: 0.81,0.91] in the training set, and 0.79 [95% CI: 0.70,0.86] and 0.79 [95% CI: 0.70,0.86] in the validation set. Convolutional neural networks were the most common model type, with sensitivity and specificity of 0.86 [95% CI: 0.72,0.94] and 0.92 [95% CI: 0.82,0.97] in the training set, and 0.87 [95% CI: 0.51,0.98] and 0.87 [95% CI: 0.69,0.96] in the validation set. Conclusion Machine learning is mainly applied in radiomics for diagnosing malignant bone tumors, showing desirable diagnostic performance. Machine learning can be an early adjunctive diagnostic method but requires further research and validation to determine its practical efficiency and clinical application prospects. Systematic review registration https://www.crd.york.ac.uk/prospero/, identifier CRD42023387057.
Collapse
Affiliation(s)
| | - Bo Dong
- Department of Orthopedics, Xi’an Honghui Hospital, Xi’an Jiaotong University, Xi’an Shaanxi, China
| | | |
Collapse
|
|
31
|
Wang Z, Li Z, Li K, Mu S, Zhou X, Di Y. Performance of artificial intelligence in diabetic retinopathy screening: a systematic review and meta-analysis of prospective studies. Front Endocrinol (Lausanne) 2023; 14:1197783. [PMID: 37383397 PMCID: PMC10296189 DOI: 10.3389/fendo.2023.1197783] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Accepted: 05/23/2023] [Indexed: 06/30/2023] Open
Abstract
Aims To systematically evaluate the diagnostic value of an artificial intelligence (AI) algorithm model for various types of diabetic retinopathy (DR) in prospective studies over the previous five years, and to explore the factors affecting its diagnostic effectiveness. Materials and methods A search was conducted in Cochrane Library, Embase, Web of Science, PubMed, and IEEE databases to collect prospective studies on AI models for the diagnosis of DR from January 2017 to December 2022. We used QUADAS-2 to evaluate the risk of bias in the included studies. Meta-analysis was performed using MetaDiSc and STATA 14.0 software to calculate the combined sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of various types of DR. Diagnostic odds ratios, summary receiver operating characteristic (SROC) plots, coupled forest plots, and subgroup analysis were performed according to the DR categories, patient source, region of study, and quality of literature, image, and algorithm. Results Finally, 21 studies were included. Meta-analysis showed that the pooled sensitivity, specificity, pooled positive likelihood ratio, pooled negative likelihood ratio, area under the curve, Cochrane Q index, and pooled diagnostic odds ratio of AI model for the diagnosis of DR were 0.880 (0.875-0.884), 0.912 (0.99-0.913), 13.021 (10.738-15.789), 0.083 (0.061-0.112), 0.9798, 0.9388, and 206.80 (124.82-342.63), respectively. The DR categories, patient source, region of study, sample size, quality of literature, image, and algorithm may affect the diagnostic efficiency of AI for DR. Conclusion AI model has a clear diagnostic value for DR, but it is influenced by many factors that deserve further study. Systematic review registration https://www.crd.york.ac.uk/prospero/, identifier CRD42023389687.
Collapse
|
|
32
|
Alabdulwahhab KM. Diabetic Retinopathy Screening Using Non-Mydriatic Fundus Camera in Primary Health Care Settings - A Multicenter Study from Saudi Arabia. Int J Gen Med 2023; 16:2255-2262. [PMID: 37304902 PMCID: PMC10255608 DOI: 10.2147/ijgm.s410197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2023] [Accepted: 05/30/2023] [Indexed: 06/13/2023] Open
Abstract
Background Screening of diabetic retinopathy (DR) using the current digital imaging facilities in a primary health care setting is still in its early stages in Saudi Arabia. This study aims to reduce the risk of vision impairment and blindness among known diabetic people through early identification by general practitioners (GP) in a primary health care setting in Saudi Arabia. The objective of this study was to evaluate the accuracy of diabetic retinopathy (DR) detection by general practitioners (GPs) by comparing the agreement of DR assessment between GPs and ophthalmologists' assessment as a gold standard. Methods A hospital-based, six-month cross-sectional study was conducted, and the participants were type 2 diabetic adults from the diabetic registries of seven rural PHCs, in Saudi Arabia. After medical examination, the participants were then evaluated by fundus photography using a non-mydriatic fundus camera without medication for mydriasis. Presence or absence of DR was graded by the trained GPs in the PHCs and then compared with the grading of an ophthalmologist which was taken as a reference or a gold standard. Results A total of 899 diabetic patients were included, and the mean age of the patients was 64.89 ± 11.01 years. The evaluation by the GPs had a sensitivity of 80.69 [95% CI 74.8-85.4]; specificity of 92.23 [88.7-96.3]; positive predictive value, 74.1 [70.4-77.0]; negative predictive value, 73.34 [70.6-77.9]; and an accuracy of 84.57 [81.8-89.88]. For the consensus of agreement the adjusted kappa coefficient was from 0.74 to 0.92 for the DR. Conclusion This study demonstrates that trained GPs in rural health centers are able to provide reliable detection results of DR from fundus photographs. The study highlights the need for early DR screening programs in the rural areas of Saudi Arabia to facilitate early identification of the condition and to lessen impact of blindness due to diabetes.
Collapse
|
|
33
|
Application of Deep Learning to Retinal-Image-Based Oculomics for Evaluation of Systemic Health: A Review. J Clin Med 2022; 12:jcm12010152. [PMID: 36614953 PMCID: PMC9821402 DOI: 10.3390/jcm12010152] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2022] [Revised: 12/17/2022] [Accepted: 12/22/2022] [Indexed: 12/28/2022] Open
Abstract
The retina is a window to the human body. Oculomics is the study of the correlations between ophthalmic biomarkers and systemic health or disease states. Deep learning (DL) is currently the cutting-edge machine learning technique for medical image analysis, and in recent years, DL techniques have been applied to analyze retinal images in oculomics studies. In this review, we summarized oculomics studies that used DL models to analyze retinal images-most of the published studies to date involved color fundus photographs, while others focused on optical coherence tomography images. These studies showed that some systemic variables, such as age, sex and cardiovascular disease events, could be consistently robustly predicted, while other variables, such as thyroid function and blood cell count, could not be. DL-based oculomics has demonstrated fascinating, "super-human" predictive capabilities in certain contexts, but it remains to be seen how these models will be incorporated into clinical care and whether management decisions influenced by these models will lead to improved clinical outcomes.
Collapse
|
|
34
|
Detection of trachoma using machine learning approaches. PLoS Negl Trop Dis 2022; 16:e0010943. [DOI: 10.1371/journal.pntd.0010943] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 12/19/2022] [Accepted: 11/12/2022] [Indexed: 12/12/2022] Open
Abstract
Background
Though significant progress in disease elimination has been made over the past decades, trachoma is the leading infectious cause of blindness globally. Further efforts in trachoma elimination are paradoxically being limited by the relative rarity of the disease, which makes clinical training for monitoring surveys difficult. In this work, we evaluate the plausibility of an Artificial Intelligence model to augment or replace human image graders in the evaluation/diagnosis of trachomatous inflammation—follicular (TF).
Methods
We utilized a dataset consisting of 2300 images with a 5% positivity rate for TF. We developed classifiers by implementing two state-of-the-art Convolutional Neural Network architectures, ResNet101 and VGG16, and applying a suite of data augmentation/oversampling techniques to the positive images. We then augmented our data set with additional images from independent research groups and evaluated performance.
Results
Models performed well in minimizing the number of false negatives, given the constraint of the low numbers of images in which TF was present. The best performing models achieved a sensitivity of 95% and positive predictive value of 50–70% while reducing the number images requiring skilled grading by 66–75%. Basic oversampling and data augmentation techniques were most successful at improving model performance, while techniques that are grounded in clinical experience, such as highlighting follicles, were less successful.
Discussion
The developed models perform well and significantly reduce the burden on graders by minimizing the number of false negative identifications. Further improvements in model skill will benefit from data sets with more TF as well as a range in image quality and image capture techniques used. While these models approach/meet the community-accepted standard for skilled field graders (i.e., Cohen’s Kappa >0.7), they are insufficient to be deployed independently/clinically at this time; rather, they can be utilized to significantly reduce the burden on skilled image graders.
Collapse
|
|
35
|
Kushwaha S, Srivastava R, Jain R, Sagar V, Aggarwal AK, Bhadada SK, Khanna P. Harnessing machine learning models for non-invasive pre-diabetes screening in children and adolescents. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 226:107180. [PMID: 36279639 DOI: 10.1016/j.cmpb.2022.107180] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/24/2022] [Revised: 10/02/2022] [Accepted: 10/06/2022] [Indexed: 06/16/2023]
Abstract
BACKGROUND AND OBJECTIVES Pre-diabetes has been identified as an intermediate diagnosis and a sign of a relatively high chance of developing diabetes in the future. Diabetes has become one of the most frequent chronic disorders in children and adolescents around the world; therefore, predicting the onset of pre-diabetes allows a person at risk to make efforts to avoid or restrict disease progression. This research aims to create and implement a cross-validated machine learning model that can predict pre-diabetes using non-invasive methods. METHODS We have analysed the national representative dataset of children and adolescents (5-19 years) to develop a machine learning model for non-invasive pre-diabetes screening. Based on HbA1c levels the data (n = 26,567) was segregated into normal (n = 23,777) and pre-diabetes (n = 2790). We have considered eight features, six hyper-tuned machine learning models and different metrics for model evaluation. The final model was selected based on the area under the receiver operator curve (AUC), Cohen's kappa and cross-validation score. The selected model was integrated into the screening tool for automated pre-diabetes prediction. RESULTS The XG boost classifier was the best model, including all eight features. The 10-fold cross-validation score was highest for the XG boost model (90.13%) and least for the support vector machine (61.17%). The AUC was highest for RF (0.970), followed by GB (0.968), XGB (0.959), ETC (0.918), DT (0.908), and SVM (0.574) models. The XGB model was used to develop the screening tool. CONCLUSION We have developed and deployed a machine learning model for automated real-time pre-diabetes screening. The screening tool can be used over computers and can be transformed into software for easy usage. The detection of pre-diabetes in the pediatric age may help avoid its enhancement. Machine learning can also show great competence in determining important features in pre-diabetes.
Collapse
Affiliation(s)
- Savitesh Kushwaha
- Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India
| | - Rachana Srivastava
- Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India
| | - Rachita Jain
- Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India
| | - Vivek Sagar
- Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India
| | - Arun Kumar Aggarwal
- Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India
| | - Sanjay Kumar Bhadada
- Department of Endocrinology, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India
| | - Poonam Khanna
- Department of Community Medicine and School of Public Health, Postgraduate Institute of Medical Education and Research, Chandigarh 160012, India.
| |
Collapse
|
|
36
|
Classification of diabetic retinopathy with feature selection over deep features using nature-inspired wrapper methods. Appl Soft Comput 2022. [DOI: 10.1016/j.asoc.2022.109462] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
|
37
|
Halfpenny W, Baxter SL. Towards effective data sharing in ophthalmology: data standardization and data privacy. Curr Opin Ophthalmol 2022; 33:418-424. [PMID: 35819893 PMCID: PMC9357189 DOI: 10.1097/icu.0000000000000878] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
PURPOSE OF REVIEW The purpose of this review is to provide an overview of updates in data standardization and data privacy in ophthalmology. These topics represent two key aspects of medical information sharing and are important knowledge areas given trends in data-driven healthcare. RECENT FINDINGS Standardization and privacy can be seen as complementary aspects that pertain to data sharing. Standardization promotes the ease and efficacy through which data is shared. Privacy considerations ensure that data sharing is appropriate and sufficiently controlled. There is active development in both areas, including government regulations and common data models to advance standardization, and application of technologies such as blockchain and synthetic data to help tackle privacy issues. These advancements have seen use in ophthalmology, but there are areas where further work is required. SUMMARY Information sharing is fundamental to both research and care delivery, and standardization/privacy are key constituent considerations. Therefore, widespread engagement with, and development of, data standardization and privacy ecosystems stand to offer great benefit to ophthalmology.
Collapse
Affiliation(s)
| | - Sally L. Baxter
- Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, CA, USA
- Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| |
Collapse
|
|
38
|
Wellnhofer E. Real-World and Regulatory Perspectives of Artificial Intelligence in Cardiovascular Imaging. Front Cardiovasc Med 2022; 9:890809. [PMID: 35935648 PMCID: PMC9354141 DOI: 10.3389/fcvm.2022.890809] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Accepted: 06/13/2022] [Indexed: 12/02/2022] Open
Abstract
Recent progress in digital health data recording, advances in computing power, and methodological approaches that extract information from data as artificial intelligence are expected to have a disruptive impact on technology in medicine. One of the potential benefits is the ability to extract new and essential insights from the vast amount of data generated during health care delivery every day. Cardiovascular imaging is boosted by new intelligent automatic methods to manage, process, segment, and analyze petabytes of image data exceeding historical manual capacities. Algorithms that learn from data raise new challenges for regulatory bodies. Partially autonomous behavior and adaptive modifications and a lack of transparency in deriving evidence from complex data pose considerable problems. Controlling new technologies requires new controlling techniques and ongoing regulatory research. All stakeholders must participate in the quest to find a fair balance between innovation and regulation. The regulatory approach to artificial intelligence must be risk-based and resilient. A focus on unknown emerging risks demands continuous surveillance and clinical evaluation during the total product life cycle. Since learning algorithms are data-driven, high-quality data is fundamental for good machine learning practice. Mining, processing, validation, governance, and data control must account for bias, error, inappropriate use, drifts, and shifts, particularly in real-world data. Regulators worldwide are tackling twenty-first century challenges raised by "learning" medical devices. Ethical concerns and regulatory approaches are presented. The paper concludes with a discussion on the future of responsible artificial intelligence.
Collapse
Affiliation(s)
- Ernst Wellnhofer
- Institute of Computer-Assisted Cardiovascular Medicine, Charité University Medicine Berlin, Berlin, Germany
| |
Collapse
|
|
39
|
Lohiniva AL, Nurzhynska A, Hudi AH, Anim B, Aboagye DC. Infodemic Management Using Digital Information and Knowledge Cocreation to Address COVID-19 Vaccine Hesitancy: Case Study From Ghana. JMIR INFODEMIOLOGY 2022; 2:e37134. [PMID: 35854815 PMCID: PMC9281514 DOI: 10.2196/37134] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Revised: 05/24/2022] [Accepted: 06/10/2022] [Indexed: 06/15/2023]
Abstract
Background Infodemic management is an integral part of pandemic management. Ghana Health Services (GHS) together with the UNICEF (United Nations International Children's Emergency Fund) Country Office have developed a systematic process that effectively identifies, analyzes, and responds to COVID-19 and vaccine-related misinformation in Ghana. Objective This paper describes an infodemic management system workflow based on digital data collection, qualitative methodology, and human-centered systems to support the COVID-19 vaccine rollout in Ghana with examples of system implementation. Methods The infodemic management system was developed by the Health Promotion Division of the GHS and the UNICEF Country Office. It uses Talkwalker, a social listening software platform, to collect misinformation on the web. The methodology relies on qualitative data analysis and interpretation as well as knowledge cocreation to verify the findings. Results A multi-sectoral National Misinformation Task Force was established to implement and oversee the misinformation management system. Two members of the task force were responsible for carrying out the analysis. They used Talkwalker to find posts that include the keywords related to COVID-19 vaccine-related discussions. They then assessed the significance of the posts on the basis of the engagement rate and potential reach of the posts, negative sentiments, and contextual factors. The process continues by identifying misinformation within the posts, rating the risk of identified misinformation posts, and developing proposed responses to address them. The results of the analysis are shared weekly with the Misinformation Task Force for their review and verification to ensure that the risk assessment and responses are feasible, practical, and acceptable in the context of Ghana. Conclusions The paper describes an infodemic management system workflow in Ghana based on qualitative data synthesis that can be used to manage real-time infodemic responses.
Collapse
Affiliation(s)
| | | | | | - Bridget Anim
- Health Promotion Division Ghana Health Services Accra Ghana
| | | |
Collapse
|
|
40
|
Miao J, Yu J, Zou W, Su N, Peng Z, Wu X, Huang J, Fang Y, Yuan S, Xie P, Huang K, Chen Q, Hu Z, Liu Q. Deep Learning Models for Segmenting Non-perfusion Area of Color Fundus Photographs in Patients With Branch Retinal Vein Occlusion. Front Med (Lausanne) 2022; 9:794045. [PMID: 35847781 PMCID: PMC9279621 DOI: 10.3389/fmed.2022.794045] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2021] [Accepted: 05/30/2022] [Indexed: 11/17/2022] Open
Abstract
Purpose To develop artificial intelligence (AI)-based deep learning (DL) models for automatically detecting the ischemia type and the non-perfusion area (NPA) from color fundus photographs (CFPs) of patients with branch retinal vein occlusion (BRVO). Methods This was a retrospective analysis of 274 CFPs from patients diagnosed with BRVO. All DL models were trained using a deep convolutional neural network (CNN) based on 45 degree CFPs covering the fovea and the optic disk. We first trained a DL algorithm to identify BRVO patients with or without the necessity of retinal photocoagulation from 219 CFPs and validated the algorithm on 55 CFPs. Next, we trained another DL algorithm to segment NPA from 104 CFPs and validated it on 29 CFPs, in which the NPA was manually delineated by 3 experienced ophthalmologists according to fundus fluorescein angiography. Both DL models have been cross-validated 5-fold. The recall, precision, accuracy, and area under the curve (AUC) were used to evaluate the DL models in comparison with three types of independent ophthalmologists of different seniority. Results In the first DL model, the recall, precision, accuracy, and area under the curve (AUC) were 0.75 ± 0.08, 0.80 ± 0.07, 0.79 ± 0.02, and 0.82 ± 0.03, respectively, for predicting the necessity of laser photocoagulation for BRVO CFPs. The second DL model was able to segment NPA in CFPs of BRVO with an AUC of 0.96 ± 0.02. The recall, precision, and accuracy for segmenting NPA was 0.74 ± 0.05, 0.87 ± 0.02, and 0.89 ± 0.02, respectively. The performance of the second DL model was nearly comparable with the senior doctors and significantly better than the residents. Conclusion These results indicate that the DL models can directly identify and segment retinal NPA from the CFPs of patients with BRVO, which can further guide laser photocoagulation. Further research is needed to identify NPA of the peripheral retina in BRVO, or other diseases, such as diabetic retinopathy.
Collapse
Affiliation(s)
- Jinxin Miao
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Jiale Yu
- School of Computer Science and Engineering, Nanjing University of Science & Technology, Nanjing, China
| | - Wenjun Zou
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
- Department of Ophthalmology, The Affiliated Wuxi No.2 People's Hospital of Nanjing Medical University, Wuxi, China
| | - Na Su
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Zongyi Peng
- The First School of Clinical Medicine, Nanjing Medical University, Nanjing, China
| | - Xinjing Wu
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Junlong Huang
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Yuan Fang
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Songtao Yuan
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Ping Xie
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Kun Huang
- School of Computer Science and Engineering, Nanjing University of Science & Technology, Nanjing, China
| | - Qiang Chen
- School of Computer Science and Engineering, Nanjing University of Science & Technology, Nanjing, China
| | - Zizhong Hu
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
- *Correspondence: Qinghuai Liu
| | - Qinghuai Liu
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
- Zizhong Hu
| |
Collapse
|
|
41
|
Opportunities of Digital Infrastructures for Disease Management-Exemplified on COVID-19-Related Change in Diagnosis Counts for Diabetes-Related Eye Diseases. Nutrients 2022; 14:nu14102016. [PMID: 35631157 PMCID: PMC9147678 DOI: 10.3390/nu14102016] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2022] [Revised: 05/05/2022] [Accepted: 05/08/2022] [Indexed: 01/20/2023] Open
Abstract
Background: Retrospective research on real-world data provides the ability to gain evidence on specific topics especially when running across different sites in research networks. Those research networks have become increasingly relevant in recent years; not least due to the special situation caused by the COVID-19 pandemic. An important requirement for those networks is the data harmonization by ensuring the semantic interoperability. Aims: In this paper we demonstrate (1) how to facilitate digital infrastructures to run a retrospective study in a research network spread across university and non-university hospital sites; and (2) to answer a medical question on COVID-19 related change in diagnostic counts for diabetes-related eye diseases. Materials and methods: The study is retrospective and non-interventional and runs on medical case data documented in routine care at the participating sites. The technical infrastructure consists of the OMOP CDM and other OHDSI tools that is provided in a transferable format. An ETL process to transfer and harmonize the data to the OMOP CDM has been utilized. Cohort definitions for each year in observation have been created centrally and applied locally against medical case data of all participating sites and analyzed with descriptive statistics. Results: The analyses showed an expectable drop of the total number of diagnoses and the diagnoses for diabetes in general; whereas the number of diagnoses for diabetes-related eye diseases surprisingly decreased stronger compared to non-eye diseases. Differences in relative changes of diagnoses counts between sites show an urgent need to process multi-centric studies rather than single-site studies to reduce bias in the data. Conclusions: This study has demonstrated the ability to utilize an existing portable and standardized infrastructure and ETL process from a university hospital setting and transfer it to non-university sites. From a medical perspective further activity is needed to evaluate data quality of the utilized real-world data documented in routine care and to investigate its eligibility of this data for research.
Collapse
|
|
42
|
WU JOHSUAN, NISHIDA TAKASHI, WEINREB ROBERTN, LIN JOUWEI. Performances of Machine Learning in Detecting Glaucoma Using Fundus and Retinal Optical Coherence Tomography Images: A Meta-Analysis. Am J Ophthalmol 2022; 237:1-12. [PMID: 34942113 DOI: 10.1016/j.ajo.2021.12.008] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2021] [Revised: 11/24/2021] [Accepted: 12/03/2021] [Indexed: 11/01/2022]
Abstract
PURPOSE To evaluate the performance of machine learning (ML) in detecting glaucoma using fundus and retinal optical coherence tomography (OCT) images. DESIGN Meta-analysis. METHODS PubMed and EMBASE were searched on August 11, 2021. A bivariate random-effects model was used to pool ML's diagnostic sensitivity, specificity, and area under the curve (AUC). Subgroup analyses were performed based on ML classifier categories and dataset types. RESULTS One hundred and five studies (3.3%) were retrieved. Seventy-three (69.5%), 30 (28.6%), and 2 (1.9%) studies tested ML using fundus, OCT, and both image types, respectively. Total testing data numbers were 197,174 for fundus and 16,039 for OCT. Overall, ML showed excellent performances for both fundus (pooled sensitivity = 0.92 [95% CI, 0.91-0.93]; specificity = 0.93 [95% CI, 0.91-0.94]; and AUC = 0.97 [95% CI, 0.95-0.98]) and OCT (pooled sensitivity = 0.90 [95% CI, 0.86-0.92]; specificity = 0.91 [95% CI, 0.89-0.92]; and AUC = 0.96 [95% CI, 0.93-0.97]). ML performed similarly using all data and external data for fundus and the external test result of OCT was less robust (AUC = 0.87). When comparing different classifier categories, although support vector machine showed the highest performance (pooled sensitivity, specificity, and AUC ranges, 0.92-0.96, 0.95-0.97, and 0.96-0.99, respectively), results by neural network and others were still good (pooled sensitivity, specificity, and AUC ranges, 0.88-0.93, 0.90-0.93, 0.95-0.97, respectively). When analyzed based on dataset types, ML demonstrated consistent performances on clinical datasets (fundus AUC = 0.98 [95% CI, 0.97-0.99] and OCT AUC = 0.95 [95% 0.93-0.97]). CONCLUSIONS Performance of ML in detecting glaucoma compares favorably to that of experts and is promising for clinical application. Future prospective studies are needed to better evaluate its real-world utility.
Collapse
|
|
43
|
Tucker A, Kannampallil T, Fodeh SJ, Peleg M. New JBI policy emphasizes clinically-meaningful novel machine learning methods. J Biomed Inform 2022; 127:104003. [DOI: 10.1016/j.jbi.2022.104003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Revised: 01/14/2022] [Accepted: 01/19/2022] [Indexed: 10/19/2022]
|
|
44
|
Liu L, Wang M, Li G, Wang Q. Construction of Predictive Model for Type 2 Diabetic Retinopathy Based on Extreme Learning Machine. Diabetes Metab Syndr Obes 2022; 15:2607-2617. [PMID: 36046759 PMCID: PMC9420743 DOI: 10.2147/dmso.s374767] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Accepted: 08/18/2022] [Indexed: 12/02/2022] Open
Abstract
PURPOSE The common cause of blindness in people with type 2 diabetes (T2D) is diabetic retinopathy (DR). Early fundus examinations have been shown to prevent vision loss, but routine ophthalmic screenings for patients with diabetes present significant financial and material challenges to existing health-care systems. The purpose of this study is to build a DR prediction model based on the extreme learning machine (ELM) and to compare the performance with the DR prediction models based on support machine vector (SVM), K proximity (KNN), random forest (RF) and artificial neural network (ANN). METHODS From January 1, 2020 to November 31, 2021, data were collected from electronic inpatient medical records at Lu'an Hospital of Anhui Medical University in China. An extreme learning machine (ELM) algorithm was used to develop a prediction model based on demographic data and blood testing and urine test results. Several metrics were used to evaluate the model's performance: (1) classification accuracy (ACC), (2) sensitivity, (3) specificity, (4) Precision,(5) Negative predictive value (NPV), (6) Training time and (7) area under the receiver operating characteristic (ROC) curve (AUC). RESULTS In terms of ACC, Sensitivity, Specificity, Precision, NPV and AUC, DR prediction model based on SVM and ELM is better than DR prediction model based on ANN, KNN and RF. The prediction model for diabetic retinopathy based on elm is the best among them in terms of ACC, Precision, Specificity, Training time and AUC, with 84.45%, 83.93%, 93.16%,1.24s, and 88.34%, respectively. The DR prediction model based on SVM is the best in terms of sensitivity and NPV, which are, respectively, 70.82% and 85.60%. CONCLUSION According to the findings of this study, the model based on the extreme learning machine presents an outstanding performance in predicting diabetic retinopathy thus providing technological assistance for screening of diabetic retinopathy.
Collapse
Affiliation(s)
- Lei Liu
- Graduate School of Bengbu Medical College, Bengbu Medical College, Bengbu City, People’s Republic of China
| | - Mengmeng Wang
- Graduate School of Bengbu Medical College, Bengbu Medical College, Bengbu City, People’s Republic of China
| | - Guocheng Li
- School of Finance & Mathematics, West Anhui University, Lu’an City, People’s Republic of China
| | - Qi Wang
- Graduate School of Bengbu Medical College, Bengbu Medical College, Bengbu City, People’s Republic of China
- Department of Endocrinology, Lu’an Hospital of Anhui Medical University, Lu’an City, People’s Republic of China
- Correspondence: Qi Wang, Department of Endocrinology, Lu’an Hospital of Anhui Medical University, No. 21, Wanxi West Road, Lu’an City, People’s Republic of China, Tel +86-13966299858, Email
| |
Collapse
|
|
45
|
Kleinberg G, Diaz MJ, Batchu S, Lucke-Wold B. Racial underrepresentation in dermatological datasets leads to biased machine learning models and inequitable healthcare. JOURNAL OF BIOMED RESEARCH 2022; 3:42-47. [PMID: 36619609 PMCID: PMC9815490] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
Objective Clinical applications of machine learning are promising as a tool to improve patient outcomes through assisting diagnoses, treatment, and analyzing risk factors for screening. Possible clinical applications are especially prominent in dermatology as many diseases and conditions present visually. This allows a machine learning model to analyze and diagnose conditions using patient images and data from electronic health records (EHRs) after training on clinical datasets but could also introduce bias. Despite promising applications, artificial intelligence has the capacity to exacerbate existing demographic disparities in healthcare if models are trained on biased datasets. Methods Through systematic literature review of available literature, we highlight the extent of bias present in clinical datasets as well as the implications it could have on healthcare if not addressed. Results We find the implications are worsened in dermatological models. Despite the severity and complexity of melanoma and other dermatological diseases as well as differing disease presentations based on skin-color, many imaging datasets underrepresent certain demographic groups causing machine learning models to train on images of primarily fair-skinned individuals leaving minorities behind. Conclusion In order to address this disparity, research first needs to be done investigating the extent of the bias present and the implications it may have on equitable healthcare.
Collapse
Affiliation(s)
| | - Michael J Diaz
- University of Florida, College of Medicine, Gainesville, FL, United States
| | | | - Brandon Lucke-Wold
- Department of Neurosurgery, University of Florida, Gainesville, FL, United States
| |
Collapse
|
|
46
|
Jimenez-Carmona S, Alemany-Marquez P, Alvarez-Ramos P, Mayoral E, Aguilar-Diosdado M. Validation of an Automated Screening System for Diabetic Retinopathy Operating under Real Clinical Conditions. J Clin Med 2021; 11:jcm11010014. [PMID: 35011754 PMCID: PMC8745311 DOI: 10.3390/jcm11010014] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Revised: 12/13/2021] [Accepted: 12/16/2021] [Indexed: 12/12/2022] Open
Abstract
Background. Retinopathy is the most common microvascular complication of diabetes mellitus. It is the leading cause of blindness among working-aged people in developed countries. The use of telemedicine in the screening system has enabled the application of large-scale population-based programs for early retinopathy detection in diabetic patients. However, the need to support ophthalmologists with other trained personnel remains a barrier to broadening its implementation. Methods. Automatic diagnosis of diabetic retinopathy was carried out through the analysis of retinal photographs using the 2iRetinex software. We compared the categorical diagnoses of absence/presence of retinopathy issued by family physicians (PCP) with the same categories provided by the algorithm (ALG). The agreed diagnosis of three specialist ophthalmologists is used as the reference standard (OPH). Results. There were 653 of 3520 patients diagnosed with diabetic retinopathy (DR). Diabetic retinopathy threatening to vision (STDR) was found in 82 patients (2.3%). Diagnostic sensitivity for STDR was 94% (ALG) and 95% (PCP). No patient with proliferating or severe DR was misdiagnosed in both strategies. The k-value of the agreement between the ALG and OPH was 0.5462, while between PCP and OPH was 0.5251 (p = 0.4291). Conclusions. The diagnostic capacity of 2iRetinex operating under normal clinical conditions is comparable to screening physicians.
Collapse
Affiliation(s)
- Soledad Jimenez-Carmona
- Ophthalmology Department, Hospital Universitario Puerta del Mar, University of Cadiz, 11009 Cadiz, Spain;
- Correspondence: (S.J.-C.); (P.A.-M.)
| | - Pedro Alemany-Marquez
- Ophthalmology Department, Hospital Universitario Puerta del Mar, University of Cadiz, 11009 Cadiz, Spain;
- Correspondence: (S.J.-C.); (P.A.-M.)
| | - Pablo Alvarez-Ramos
- Ophthalmology Department, Hospital Universitario Puerta del Mar, University of Cadiz, 11009 Cadiz, Spain;
| | - Eduardo Mayoral
- Comprehensive Healthcare Plan for Diabetes, Regional Ministry of Health and Families of Andalusia, Government of Andalusia, 41020 Seville, Spain;
| | | |
Collapse
|