Identifying the risk of psoriasis relapse after discontinuing biologics can help optimize treatment strategies, potentially reducing relapse rates and alleviating the burden of disease management.

To develop and validate a personalized prediction model for psoriasis relapse following the discontinuation of biologics.

This study enrolled patients who achieved remission following biologic therapy. Relapse predictors were identified using the Boruta algorithm combined with multivariate Cox regression. A nomogram and an online calculator were created to aid in the visualization and computation of outcomes. The model's performance was thoroughly assessed using Receiver Operating Characteristic (ROC) curves, Area Under the Curve (AUC), C-statistics, calibration plots, and Decision Curve Analysis (DCA).

The study included 597 patients, with 534 in the derivation cohort and 63 in the validation cohort. Anxiety, disease duration, prior biologic treatments, treatment duration, time to achieve PASI 75, and maximum PASI response were identified as influential factors for relapse and were incorporated into the model. Both internal and external evaluations indicate that the model exhibits good predictive accuracy.

A multivariate model leveraging standard clinical data can relatively accurately predict the risk of psoriasis relapse post-biologic discontinuation, guiding personalized treatment strategies.

Infertility has emerged as a significant public health concern, with assisted reproductive technology (ART) is a last-resort treatment option. However, ART's efficacy is limited by significant financial cost and physical discomfort. The aim of this study is to build Machine learning (ML) decision-support models to predict the optimal range of embryo numbers to transfer, using data from infertile couples identified through literature reviews. Binary classification models were developed to classify cases into two groups: those transferring two or fewer embryos and those transferring three or four. Four popular ML algorithms were used, including random forest (RF), logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN), considering seven criteria: the woman's age, sperm origin, the developmental qualities of four potential embryos, infertility duration, assessment of the woman, morphological qualities of the four best embryos on the day of transfer, and number of oocytes extracted. The stratified 3-fold cross-validation results show that the SVM model obtained the highest average accuracy (95.83%) and demonstrated the best overall performance, closely followed by the ANN and LR models with an average accuracy equal to 91.67%. The RF model achieved a slightly lower average accuracy (88.89%), which demonstrated the lowest variability. Testing on a new dataset revealed all models performed well, with ANN and SVM models classified all test set instances correctly, while the RF and LR models achieved 91.68% accuracy. These results highlight the superior generalization and effectiveness of the ANN and SVM models in guiding ART decisions.

Gastric cancer (GC) occupies the first few places in the world among tumors in terms of incidence and mortality, causing serious harm to human health, and at the same time, its treatment greatly consumes the health care resources of all countries in the world. The diagnosis of GC is usually based on histopathologic examination, and it is very important to be able to detect and identify cancerous lesions at an early stage, but some endoscopists' lack of diagnostic experience and fatigue at work lead to a certain rate of under diagnosis. The rapid and striking development of Artificial intelligence (AI) has helped to enhance the ability to extract abnormal information from endoscopic images to some extent, and more and more researchers are applying AI technology to the diagnosis of GC. This initiative has not only improved the detection rate of early gastric cancer (EGC), but also significantly improved the survival rate of patients after treatment. This article reviews the results of various AI-assisted diagnoses of EGC in recent years, including the identification of EGC, the determination of differentiation type and invasion depth, and the identification of borders. Although AI has a better application prospect in the early diagnosis of ECG, there are still major challenges, and the prospects and limitations of AI application need to be further discussed.

Adequate bowel preparation is crucial for effective colonoscopy, especially in elderly patients who face a high risk of inadequate preparation. This study develops and validates a machine learning model to predict bowel preparation adequacy in elderly patients before colonoscopy.

The study adhered to the TRIPOD AI guidelines. Clinical data from 471 elderly patients collected between February and December 2023 were utilized for developing and internally validating the model, while 221 patients' data from March to June 2024 were used for external validation. The Boruta algorithm was applied for feature selection. Models including logistic regression, light gradient boosting machines, support vector machines (SVM), decision trees, random forests, and extreme gradient boosting were evaluated using metrics such as AUC, accuracy, sensitivity, and specificity. The SHAP algorithm helped rank feature importance. A web-based application was developed using the Streamlit framework to enhance clinical usability.

The Boruta algorithm identified 7 key features. The SVM model excelled with an AUC of 0.895 (95% CI: 0.822-0.969), and high accuracy, sensitivity, and specificity. In external validation, the SVM model maintained robust performance with an AUC of 0.889. The SHAP algorithm further explained the contribution of each feature to model predictions.

The study developed an interpretable and practical machine learning model for predicting bowel preparation adequacy in elderly patients, facilitating early interventions to improve outcomes and reduce resource wastage.

Sepsis is a leading cause of death among patients with HIV, but early diagnosis remains a challenge. This study evaluates the diagnostic performance of monocyte distribution width (MDW) in detecting sepsis in patients with HIV. A prospective observational study was conducted at Shanghai Public Health Center, involving 488 hospitalized patients with HIV aged 18-65 between December 2022 and August 2023. MDW was measured at admission, and its diagnostic accuracy was compared with Sepsis-3 criteria. Survival rates on day 28 and 90 were also recorded. Additionally, five machine learning (ML) models were tested to enhance diagnostic efficacy. Of 488 subjects, 90 were in the sepsis group and 398 in the control group. MDW showed a diagnostic area under the curve (AUC) of 0.82, comparable to C-reactive protein (CRP) and Procalcitonin (PCT) with AUCs of 0.78 and 0.82, respectively. With a cut-off value of 25.25, MDW had a sensitivity of 0.83 and specificity of 0.76. The positive and negative predictive values were 44% and 95%, respectively. When MDW was combined with platelet count, serum albumin, and hemoglobin in a random forest model, the AUC improved to 0.931. The model achieved a sensitivity of 1.00 and specificity of 0.732. MDW is a useful diagnostic marker for sepsis in patients with HIV, with strong sensitivity and specificity. Combining MDW with other lab markers can further enhance diagnostic accuracy.Trial registration: ClinicalTrials.gov identifier: NCT05036928..

Some nonfunctioning pituitary neuroendocrine tumor (NFPitNET) can show invasive growth, which increases the difficulty of surgery and indicates a poor prognosis. However, the molecular mechanism related to invasiveness remains to be further studied. This study is to screen and identify the characteristic biomarkers of invasive NFPitNETs.

Based on the data of 73 NFPitNETs microarray chips in the GSE169498 dataset, this study used weighted gene co-expression network (WGCNA), differential expression analysis, protein-protein interaction (PPI) network analysis and various machine learning methods (XGBOOST, LASSO regression, random forest, support vector machine) to screen candidate biomarkers for invasive NFPitNET. Then, using gene set enrichment analysis (GSEA) to explore the differences in biological activities and signaling pathways between invasive NFPitNET and non-invasive NFPitNET. Single-sample GSEA (ssGSEA) was used to analyze key biomarkers-related signaling pathways. Finally, the expression and function of the key biomarkers were verified by q-RT PCR, immunohistochemical (IHC) experiments and in vitro experiments.

Combined with WGCNA and differential expression analysis, 128 high-expression and 85 low-expression candidate biomarkers were preliminarily obtained. PPI analysis and four machine learning algorithms further identified GALR1, PENK and HOXD9. The receiver operating characteristic (ROC) curve results showed that the three biomarkers had good predictive ability of invasiveness. After combining the validation set data, GALR1 and PENK were the final key biomarkers. Finally, PCR and IHC results verified the decreased expression of GALR1 and PENK in invasive NFPitNET and promotes proliferation and invasive ablity of pituitary tumor cells.

This study confirmed that the reduced expression of GALR1 and PENK is an important molecular feature of invasive NFPitNETs, which may play an important role in inhibiting the development of NFPitNET.

Purpose: To evaluate the clinical performance of a Protocol Recommendation System (PRS) automatic protocolling of chest CT imaging requests. Materials and Methods: 322 387 consecutive historical imaging requests for chest CT between 2017 and 2022 were extracted from a radiology information system (RIS) database containing 16 associated patient information values. Records with missing fields and protocols with <100 occurrences were removed, leaving 18 protocols for training. After freetext pre-processing and applying CLEVER terminology word replacements, the features of a bag-of-words model were used to train a multinomial logistic regression classifier. Four readers protocolled 300 clinically executed protocols (CEP) based on all clinically available information. After their selection was made, the PRS and CEP were unblinded, and the readers were asked to score their agreement (1 = severe error, 2 = moderate error, 3 = disagreement but acceptable, 4 = agreement). The ground truth was established by the readers' majority selection, a judge helped break ties. For the PRS and CEP, the accuracy and clinical acceptability (scores 3 and 4) were calculated. The readers' protocolling reliability was measured using Fleiss' Kappa. Results: Four readers agreed on 203/300 protocols, 3 on 82/300 cases, and in 15 cases, a judge was needed. PRS errors were found by the 4 readers in 1%, 2.7%, 1%, and 0.7% of the cases, respectively. The accuracy/clinical acceptability of the PRS and CEP were 84.3%/98.6% and 83.0%/99.3%, respectively. The Fleiss' Kappa for all readers and all protocols was 0.805. Conclusion: The PRS achieved similar accuracy to human performance and may help radiologists master the ever-increasing workload.

Acute Pancreatitis (AP) is a prevalent clinical pancreatic disorder characterized by acute inflammation of the pancreas, frequently associated with biliary or alcoholic events. If not treated with cholecystectomy after the first episode, patients may experience a recurrence of AP, with consequent need for emergency surgery and increased risk of death. Analyzing the risk factors that may contribute to the recurrence of Biliary and Alcoholic Pancreatitis (BAP and AAP), future research can be driven toward new solutions for preventing and treating this pancreatic disease.

A systematic review was conducted selecting studies from BiomedCentral, PubMed, Scopus and Web of Science by two independent reviewers. Publications were considered only if written in English in the time interval between January 2000 and June 2024 and investigated the risk factors for the recurrence of BAP and AAP. At the end of the selection, a quality assessment phase was conducted using the PROBAST tool.

In this systematic review, 8 articles were selected out of 6.945, involving a total sample of 11.271 patients of which 38.77% developed recurrence episodes. 37.5% of the included studies focus on recurrent acute biliary pancreatitis (RBAP), while 62.5% are dedicated to recurrent acute alcoholic pancreatitis (RAAP). The risk factors for the recurrence of AP showed a clear differentiation between the alcoholic and biliary etiology. Most of the considered studies adopted a retrospective design, characterized by a susceptibility to potential methodological biases. However, the trend indicated a more recent increase in prospective studies, together with a greater focus on identifying and understanding the possible risk factors associated with the recurrence of acute pancreatitis (RAP). This result highlighted the progress in the scientific approach toward a more rigorous and systematic assessment of the causes and dynamics that influence the recurrence of the disease.

Studies highlighted the importance of lifestyle factors, clinical complications, and surgical interventions that can impact the risk of biliary or alcoholic recurrent acute pancreatitis. Increased and systematic adoption of artificial intelligence-based tools could significantly impact future knowledge relating to the risks of recurrence and relative possibilities of prevention.

The incidence of thyroid cancer (TC) is increasing in China, largely due to overdiagnosis from widespread screening and improved ultrasound technology. Identifying precise TC biomarkers is crucial for accurate diagnosis and effective treatment.

TC patient data were obtained from TCGA. DEGs were analyzed using DESeq2, and WGCNA identified gene modules associated with TC. Machine learning algorithms (XGBoost, LASSO, RF) identified key biomarkers, with ROC and AUC > 0.95 indicating strong diagnostic performance. Immune cell infiltration and biomarker correlation were analyzed using CIBERSORT.

Four key genes (P4HA2, TFF3, RPS6KA5, EYA1) were found as potential biomarkers. High P4HA2 expression was associated with suppressed anti-tumor immune responses and promoted disease progression. In vitro studies showed that P4HA2 upregulation increased TC cell growth and migration, while its suppression reduced these activities.

Through bioinformatics and experimental validation, we identified P4HA2 as a key potential thyroid cancer biomarker. This finding provides new molecular targets for diagnosis and treatment. P4HA2 has the potential to be a diagnostic or therapeutic target, which could have significant implications for improving clinical outcomes in thyroid cancer patients.

Can attenuated total reflection-Fourier transform infrared spectroscopy combined with machine learning techniques be used to develop a real-time diagnostic modality for chronic endometritis by analysing endometrial biopsies obtained during hysteroscopy?

Women undergoing hysteroscopy for infertility assessment were enrolled in this prospective study from January 2020 to March 2021. Endometrial biopsies were evaluated using a spectrophotometer, and subsequently via histopathology, including immunohistochemical staining for the multiple myeloma oncogene-1 (MUM-1). Spectroscopy analyses of the positive and the negative chronic endometritis groups were compared across various cut-offs of MUM-1 positive cells per 10 high-power fields (HPF). Machine learning techniques were used to build discrimination models with Matlab and Unscrambler software packages.

Fifty-four women were recruited. Four of the 54 measured spectra were discarded due to high measurement noise. Fifty biopsies were finally assessed, and a discriminant model was developed using the Principal Component Analysis and Linear Discriminant Analysis techniques (machine learning). The model was evaluated for accuracy using different MUM-1 cut-offs. Distinct spectral disparities (p < 0.05) were observed between specimens negative or positive for chronic endometritis. When employing a cut-off of > 7 MUM-1 cells/10 HPF, the model differentiated positive and negative chronic endometritis with 84 % accuracy, 88.8 % sensitivity and 82.9 % specificity.

Our findings in this preliminary study support the potential availability of a bedside diagnostic tool based on a model developed using spectroscopy coupled with machine learning. This allowed us to diagnose chronic endometritis in real-time with 84% accuracy, facilitating immediate initiation of appropriate treatment.

This study aimed to develop and validate CT-based radiomics deep learning signatures for the non-invasive prediction of metastatic potential in pheochromocytomas and paragangliomas (PPGLs).

We conducted a retrospective analysis of 249 PPGL patients from three institutions, dividing them into training (n = 138), test1 (n = 71), and test2 (n = 40) sets. Based on the grading system for adrenal pheochromocytoma and paraganglioma (GAPP), patients were classified into low-risk (GAPP < 3) and high-risk (GAPP ≥ 3) groups. Radiomic features were extracted from CT venous phase images and modeled using six machine learning algorithms. The maximum 2D sections and 3D images of each tumor were input into four ResNet models to obtain predictive probabilities. Optimal models were selected based on receiver operating characteristic analysis and integrated with radiological features to develop a combined model, which was evaluated on external datasets, and explored prognostic information.

The support vector machine radiomics and 2D ResNet-50 models demonstrated good performance. By integrating these two models with intratumoral necrosis features, we constructed a combined model that achieved high accuracy, with area under the curve (AUC) values of 0.90 for the training, 0.86 for the test1, and 0.88 for the test2 sets. This model effectively stratified patients based on metastasis-free survival (p = 0.003). Its predictive ability remains robust below the 6 cm threshold, with AUC values exceeding 0.87 across all datasets.

The combined model can predict the metastatic potential of PPGL in the preoperative stage, providing a precise surgical strategy for pheochromocytoma regarding the 6 cm surgical threshold.

The combined model, established based on radiomic and deep learning signatures, shows potential for early preoperative prediction of metastatic potential in PPGL.

Metastatic potential of PPGL affects surgical approaches and prognosis. CT-based radiomics deep learning signatures can predict the metastatic potential in PPGL.3. The combined model's predictive ability remains robust below the 6-cm threshold. The combined model's predictive ability remains robust below the 6-cm threshold.

Since postoperative complications after gastrectomy for gastric cancer are associated with poor clinical outcomes, it is important to predict and prepare for the occurrence of complications preoperatively. Conventional models for predicting complications have limitations, prompting interest in machine learning algorithms. Machine learning models have a superior ability to identify complex interactions among variables and nonlinear relationships, potentially revealing new risk factors. This study aimed to explore previously overlooked risk factors for postoperative complications and compare machine learning models with linear regression.

We retrospectively reviewed data from 865 patients who underwent gastrectomy for gastric cancer from 2018 to 2022. A total of 85 variables, including demographics, clinical features, laboratory values, intraoperative parameters, and pathologic results, were used to conduct the machine learning model. The dataset was partitioned into 80% for training and 20% for validation. To identify the most accurate prediction model, missing data handling, variable selection, and hyperparameter tuning were performed.

Machine learning models performed notably well when using the backward elimination method and a moderate missing data strategy, achieving the highest area under the curve values (0.744). A total of 15 variables associated with postoperative complications were identified using a machine learning algorithm. Operation time was the most impactful variable, followed closely by pre-operative levels of albumin and mean corpuscular hemoglobin. Machine learning models, especially Random Forest and XGBoost, outperformed linear regression.

Machine learning, coupled with advanced variable selection techniques, showed promise in enhancing risk prediction of postoperative complications for gastric cancer surgery.

Pancreatic ductal adenocarcinoma (PDAC) is frequently diagnosed in advanced stage due to the absence of effective diagnostic biomarkers. Small extracellular vesicles (sEVs) have recently emerged as potential clinical biomarkers in liquid biopsy. Our study aimed to explore sEV mRNA biomarkers for PDAC diagnosis and identify relevant markers that could guide the prognosis of PDAC patients.

We analyzed mRNA sequencing of plasma sEVs from 100 participants and employed four machine learning techniques to create and assess the diagnostic models. Partial plasma sEV mRNAs were identified by all four feature extraction methods and used to construct diagnostic model. We also evaluated the predictive value of the model for the survival prognosis of PDAC patients.

Combined with carbohydrate antigen 19-9 (CA19-9), the 4 sEV mRNAs diagnostic signature (d-signature) could well differentiate PDAC patients from non-PDAC individuals, healthy control individuals, and benign pancreatic disease patients with an area under the curve (AUC) of 0.902, 0.971, and 0.845 in training cohort and AUC of 0.803, 0.938, and 0.762 in validation cohort. Furthermore, Cox regression analysis indicated that the score constructed based on the sEV mRNA signature was an independent adverse prognostic factor for survival prognosis of PDAC.

Our study demonstrated the potential utility of the sEV mRNA d-signature in the diagnosis of PDAC via machine learning methods. Simultaneously, the score from this diagnostic model exhibited a significant correlation with adverse outcome in PDAC patients. This provided a novel non-invasive sEV mRNA signature for clinical diagnosis and prognostic evaluation of PDAC patients.

Artificial intelligence (AI), including its subfields of machine learning and deep learning, is a branch of computer science and engineering focused on creating machines capable of tasks requiring human-like intelligence, such as visual perception, decision-making, and natural language processing. AI applications have become increasingly prevalent in dental medicine, generating high expectations as well as raising ethical and practical concerns.

This critical review evaluates the current applications of AI in dentistry, identifying key perspectives, challenges, and limitations in ongoing AI research.

AI models have been applied across various dental specialties, supporting diagnosis, treatment planning, and decision-making, while also reducing the burden of repetitive tasks and optimizing clinical workflows. However, ethical complexities and methodological limitations, such as inconsistent data quality, bias risk, lack of transparency, and limited clinical validation, undermine the quality of AI studies and hinder the effective integration of AI into routine dental practice.

To improve AI research, studies must adhere to standardized methodological and ethical guidelines, particularly in data collection, while ensuring transparency, privacy, and accountability. Developing a comprehensive framework for producing robust, reproducible AI research and clinically validated technologies will facilitate the seamless integration of AI into clinical practice, benefiting both clinicians and patients by improving dental care.

Purpose: Acute appendicitis (AA) is a common surgical emergency affecting 7-8% of the population. Timely diagnosis and treatment are crucial for preventing serious morbidity and mortality. Diagnosis typically involves physical examination, laboratory tests, ultrasonography, and computed tomography (CT). This study aimed to evaluate the effectiveness of artificial intelligence (AI) in analyzing CT images for the early diagnosis of AA and prevention of complications. Methods: CT images of patients who underwent surgery for AA at the General Surgery Clinic of Kanuni Sultan Suleyman Health Application and Research Center between January 1, 2019, and June 31, 2023, were analyzed. A total of 1200 CT images were evaluated using four different AI models. The model performance was assessed using a confusion matrix. Results: The median age of the patients was 28 years, with a similar sex distribution. No significant differences were observed in terms of age or sex (P = .168 and P = .881, respectively). Among the AI models, MobileNet v2 showed the highest accuracy (0.7908) and precision (0.8203), whereas Inception v3 had the highest F-score (0.7928). In the receiver operating characteristic analysis, MobileNet v2 achieved an area under the curve (AUC) of 0.8767. Conclusion: AI's role in daily life is expanding. In the present study, the highest sensitivity and specificity were 77% and 86%, respectively. Supporting CT imaging with AI systems can enhance the accuracy of AA diagnoses.

Seizure relapse in pediatric patients with epilepsy after antiseizure medication (ASM) withdrawal is a critical concern, yet the risk factors are not fully understood. Identifying these factors is essential for personalized treatment planning.

In this systematic review and meta-analysis, and prospective cohort study, we conducted a meta-analysis of cohort studies to derive a predictive model for seizure recurrence post-ASM discontinuation, then validated it in a prospective cohort study. The derivation cohort was derived from a systematic, search of PubMed, Web of Science, Embase, and Cochrane Library (from inception to May 1,2024) for English-language cohort studies on risk factors for seizure recurrence after ASM withdrawal in pediatric epilepsy, focusing on children initiating ASM tapering with documented relapse, while excluding case reports, and non-pharmacological interventions. Risk factors were selected and weighted according to the statistical significance of pooled relative risks (RRs), with β coefficients derived from log-transformed RRs to establish weighted scores in the predictive model. The validation cohort included children with epilepsy enrolled between February 16, 2015 and November 15, 2024, from two Chinese hospitals. Inclusion criteria comprised first-time ASM withdrawal candidates aged <18 years with ≥24-month follow-up, while exclusion criteria focused on incomplete data, protocol deviations, and non-pharmacological interventions. This study is registered at https://www.medicalresearch.org.cn/ (MR-50-24-042059).

A total of 26 cohort studies were identified from the systematic review and included in the meta-analysis. The derivation cohort included 4080 children with epilepsy, of whom 959 (23.50%) experienced seizure recurrence. The predictive model identified nine significant risk factors: intellectual disability, abnormal neurological examination or motor deficit, history of febrile seizures, only focal onset seizures, overall number of ASM used, duration of epilepsy ≥3 years, abnormal electroencephalogram (EEG) at the start of ASM tapering, abnormal EEG after ASM tapering, and age at first seizure ≥10 years. β coefficients were derived from the logarithm of pooled relative risks for each factor and converted into weighted scores, yielding a maximum total risk score of 17. The validation cohort comprised 341 patients with a median follow-up duration of 2.84 (0.27-9.75) years, and 122 (35.8%) out of them had seizure relapses. The model demonstrated robust performance in the validation cohort, with an AUC of 0.85 (95% CI: 0.81-0.91), sensitivity of 0.74 (95% CI: 0.68-0.80), and specificity of 0.82 (95% CI: 0.75-0.89).

Our evidence-based predictive model offers a robust tool for estimating the risk of seizure recurrence in pediatric patients with epilepsy after ASM withdrawal, aiding clinicians in personalized treatment decisions. While this tool enhances personalized treatment decisions in epilepsy management, its predictive thresholds require external validation across diverse clinical settings and populations to ensure broad clinical applicability.

Chongqing Medical University (CQMU) Program for Youth Innovation in Future Medicine.

Enteral nutrition is an important clinical nutritional supplementation method, especially for adult patients who are unable to eat normally or require additional nutritional support. However, many patients experience intolerance to enteral nutrition, such as delayed gastric emptying, bloating, and diarrhea, which not only affect the patient's nutritional status but also increase the risk of medical complications. In recent years, medical researchers have been dedicated to identifying and analyzing various factors that contribute to enteral nutrition intolerance, including the patient's disease status, nutritional formula, feeding method, and rate. In addition, research is also exploring the establishment of risk prediction models to more accurately predict which patients may develop enteral nutrition intolerance. These models typically combine clinical parameters, biomarkers, and patient individual characteristics, aiming to assist clinicians in better planning and adjusting nutritional treatment plans, thereby reducing the occurrence of intolerance events. This review summarizes the research progress on enteral nutrition intolerance in adult patients, with a focus on the latest developments in intolerance factors and risk prediction models, providing valuable guidance for clinical practice and helping improve patients' nutritional status and overall health.

Clinical risk prediction models are ubiquitous in many surgical domains. The traditional approach to develop these models involves the use of regression analysis. Machine learning algorithms are gaining in popularity as an alternative approach for prediction and classification problems. They can detect non-linear relationships between independent and dependent variables and incorporate many of them. In our work, we aimed to investigate the potential role of machine learning versus classical logistic regression for the preoperative risk assessment in proctological surgery. We used clinical data from a nationwide audit: the database consisted of 1510 patients affected by Goligher's grade III hemorrhoidal disease who underwent elective surgery. We collected anthropometric, clinical, and surgical data and we considered ten predictors to evaluate model-predictive performance. The clinical outcome was the complication rate evaluated at 30-day follow-up. Logistic regression and three machine learning techniques (Decision Tree, Support Vector Machine, Extreme Gradient Boosting) were compared in terms of area under the curve, balanced accuracy, sensitivity, and specificity. In our setting, machine learning and logistic regression models reached an equivalent predictive performance. Regarding the relative importance of the input features, all models agreed in identifying the most important factor. Combining and comparing statistical analysis and machine learning approaches in clinical field should be a common ambition, focused on improving and expanding interdisciplinary cooperation.

Hepatitis C virus (HCV) infection represents a significant contributor to chronic liver disease on a global scale. The prompt identification and management of HCV are imperative in order to avert complications and to maintain control over the disease. Nowadays, medical decision support systems that incorporate advanced diagnostic methods and effective treatment strategies are of great importance in order to make significant progress in the fight against HCV. Medical decision support systems have undergone a major evolution with the development of computer technologies. In the 2010s, the integration of big data and artificial intelligence technologies into medical decision support systems enabled rapid analysis of patient data. This has created significant synergies in the diagnostic and therapeutic approaches to various diseases. The ever-increasing volume of data on HCV infection offers opportunities to use machine learning techniques to diagnose and predict liver disorders. Although the implementation of machine learning necessitates a degree of proficiency in computer science, which frequently poses a challenge for healthcare practitioners, automated machine learning (AutoML) tools markedly mitigate this obstacle. Such tools empower users to construct highly effective machine learning models without requiring extensive technical expertise. In our investigation concerning HCV prediction, additional features were incorporated into the dataset sourced from the UCI Machine Learning Repository, and class imbalances were rectified. In our study on HCV prediction, which was conducted to address this deficiency, new features were added to the dataset obtained from the UCI Machine Learning Repository to address the deficiencies and inter-class imbalances were corrected. After this process, modeling was performed using 7 AutoML tools and high accuracy rates ranging from 99.29 % to 100 % were obtained. As an important result of this paper, these models may be regarded as a supplementary method for doctors in predicting Hepatitis C and its associated diseases.

Artificial intelligence (AI) is rapidly advancing our ability to identify and interpret genetic variants associated with coagulation factor deficiencies. This review introduces AI, with a specific focus on machine learning (ML) methods, and examines its applications in the field of coagulation genetics over the past decade. We observed a significant increase in AI-related publications, with a focus on hemophilia A and B. ML approaches have shown promise in predicting the functional impact of genetic variants and establishing genotype-phenotype correlations, exemplified by tools like "Hema-Class" for factor VIII variants. However, some challenges remain, including the need to expand variant selection beyond missense mutations (which is now the standard of most studies). For the future, the integration of AI in calling, detecting, and interpreting genetic variants can significantly improve our ability to process large-scale genomic data. In this frame, we discuss various AI/ML-based tools for genetic variant detection and interpretation, highlighting their strengths and limitations. As the field evolves, the synergistic application of multiple AI models, coupled with rigorous validation strategies, will be crucial in advancing our understanding of coagulation disorders and for personalizing treatment approaches.

The growing global burden of diabetes and stroke poses a significant public health challenge. This study aims to analyze factors and create an interpretable stroke prediction model for diabetic patients.

Data from 20,014 patients were collected from the Affiliated Drum Tower Hospital, Medical School of Nanjing University, between 2021 and 2022. After handling the missing values, feature engineering included LASSO, SVM-RFE, and multi-factor regression techniques. The dataset was split 8:2 for training and testing, with the Synthetic Minority Oversampling Technique (SMOTE) to balance classes. Various machine learning and deep learning techniques, such as Random Forest (RF) and deep neural networks (DNN), have been utilized for model training. SHAP and a dedicated website showed the interpretability and practicality of the model. This study identified 11 factors influencing stroke incidence, with the RF and DNN algorithms achieving AUC values of 0.95 and 0.91, respectively. The Stroke Management and Analysis Risk Tool (SMART) was developed for clinical use.

The predictive performance of SMART in assessing stroke risk in diabetic patients was evaluated using AUC.

Evaluated accuracy (precision, recall, F1-score), interpretability via SHAP values, and clinical utility, emphasizing user interface. Statistical analysis of EHR data using univariate and multivariate methods, with model validation on a separate test set.

An interpretable stroke-predictive model was created for patients with diabetes. This model proposes that standard clinical and laboratory parameters can predict the stroke risk in individuals with diabetes.

Assessment of pulmonary regurgitation (PR) guides treatment for patients with congenital heart disease. Quantitative assessment of PR fraction (PRF) by echocardiography is limited. Cardiac MRI (cMRI) is the reference-standard for PRF quantification. We created an algorithm to predict cMRI-quantified PRF from echocardiography using machine learning (ML). We retrospectively performed echocardiographic measurements paired to cMRI within 3 months in patients with ≥ mild PR from 2009 to 2022. Model inputs were vena contracta ratio, PR index, PR pressure half-time, main and branch pulmonary artery diastolic flow reversal (BPAFR), and transannular patch repair. A gradient boosted trees ML algorithm was trained using k-fold cross-validation to predict cMRI PRF by phase contrast imaging as a continuous number and at > mild (PRF ≥ 20%) and severe (PRF ≥ 40%) thresholds. Regression performance was evaluated with mean absolute error (MAE), and at clinical thresholds with area-under-the-receiver-operating-characteristic curve (AUROC). Prediction accuracy was compared to historical clinician accuracy. We externally validated prior reported studies for comparison. We included 243 subjects (median age 21 years, 58% repaired tetralogy of Fallot). The regression MAE = 7.0%. For prediction of > mild PR, AUROC = 0.96, but BPAFR alone outperformed the ML model (sensitivity 94%, specificity 97%). The ML model detection of severe PR had AUROC = 0.86, but in the subgroup with BPAFR, performance dropped (AUROC = 0.73). Accuracy between clinicians and the ML model was similar (70% vs. 69%). There was decrement in performance of prior reported algorithms on external validation in our dataset. A novel ML model for echocardiographic quantification of PRF outperforms prior studies and has comparable overall accuracy to clinicians. BPAFR is an excellent marker for > mild PRF, and has moderate capacity to detect severe PR, but more work is required to distinguish moderate from severe PR. Poor external validation of prior works highlights reproducibility challenges.

Lung cancer is one of the most prevalent and lethal malignant tumors worldwide. Currently, clinical diagnosis primarily relies on chest X-ray examinations, histopathological analysis, and the detection of tumor markers in blood. However, each of these methods has inherent limitations. The current study aims to explore novel diagnostic approaches for lung cancer by employing attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy in conjunction with multiple machine learning models. Fourier transform infrared spectroscopy can detect subtle differences in the material structures that reflect the carcinogenic process between lung cancer tissues and normal tissues. By applying principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) to analyze infrared spectral data, these subtle differences can be amplified. The study revealed that the combination of spectral bands within the 3500-3000 cm-1 and 1600-1500 cm-1 ranges is particularly significant for differentiating between the two groups. Three classification models-Support Vector Machine (SVM), k-Nearest Neighbor (kNN), and Linear Discriminant Analysis (LDA)-were constructed for spectral analysis of various band combinations. The results indicated that in detecting lung cancer samples, the combination of the 3500-3000 cm-1 and 1600-1500 cm-1 bands offers significant advantages. The analysis of the receiver operating characteristic (ROC) curve demonstrated that the area under the curve (AUC) exceeded 0.95 for all models, with the LDA model achieving an accuracy rate of 99.4% in identifying lung cancer patients compared to healthy individuals. The findings suggest that the integration of ATR-FTIR spectroscopy with multiple machine learning models represents a promising auxiliary diagnostic method for clinical lung cancer diagnosis, enabling detection at the molecular level.

Objective The present study evaluated the usefulness of machine learning (ML) models with the coronary computed tomography imaging and clinical parameters for predicting major adverse cardiac events (MACEs). Methods The Nationwide Gender-specific Atherosclerosis Determinants Estimation and Ischemic Cardiovascular Disease Prospective Cohort study (NADESICO) of 1,187 patients with suspected coronary artery disease 50-74 years old was used to build a MACE prediction model. The ML random forest (RF) model was compared with a logistic regression analysis. The performance of the ML model was evaluated using the area under the curve (AUC) with the 95% confidence interval (CI). Results Among 1,178 patients from the NADESICO dataset, MACEs occurred in 103 (8.7%) patients during a median follow-up of 4.4 years. The AUC of the RF model for MACE prediction was 0.781 (95% CI: 0.670-0.870), which was significantly higher than that of the conventional logistic regression model [AUC, 0.750 (95% CI: 0.651-0.839)]. The important features in the RF model were coronary artery stenosis (CAS) at any site, CAS in the left anterior descending branch, HbA1c level, CAS in the right coronary artery, and sex. In the external validation cohort, the model accuracy of ensemble ML-RF models that were trained on and tuned using the NADESICO dataset was not similar [AUC: 0.635 (95% CI: 0.599-0.672)]. Conclusion The ML-RF model improved the long-term prediction of MACEs compared to the logistic regression model. However, the selected variables in the internal dataset were not highly predictive of the external dataset. Further investigations are required to validate the usefulness of this model.

The integration of artificial intelligence (AI) into cardiovascular procedures has significantly advanced diagnostic accuracy, outcome prediction, and robotic-assisted surgeries. However, a comprehensive bibliometric analysis of AI's impact in this field is lacking. This study examines research trends, key contributors, and emerging themes in AI-driven cardiovascular interventions.

We retrieved relevant publications from the Web of Science Core Collection and analyzed them using VOSviewer, CiteSpace, and Biblioshiny to map research trends and collaborations.

AI-related cardiovascular research has grown substantially from 1993 to 2024, with a sharp increase from 2020 to 2023, peaking at 93 publications in 2023. The USA (127 papers), China (79), and England (31) were the top contributors, with Harvard University leading institutional output (17 papers). Frontiers in Cardiovascular Medicine was the most prolific journal. Core research themes included "machine learning," "mortality," and "cardiac surgery," with emerging trends in "association," "implantation," and "aortic stenosis," underscoring AI's expanding role in predictive modeling and surgical outcomes.

AI demonstrates transformative potential in cardiovascular procedures, particularly in diagnostic imaging, predictive modeling, and patient management. This bibliometric analysis highlights the growing interest in AI applications and provides a framework for integrating AI into clinical workflows to enhance diagnostic accuracy, treatment strategies, and patient outcomes.

This study aims to develop and validate a machine learning model for identifying individuals within the nursing population experiencing severe subjective cognitive decline (SCD) during the menopause transition, along with their associated factors.

A secondary analysis was performed using cross-sectional data from 1,264 nurses undergoing the menopause transition. The data set was randomly split into training (75%) and validation sets (25%), with the Bortua algorithm employed for feature selection. Seven machine learning models were constructed and optimized. Model performance was assessed using area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, and F1 score. Shapley Additive Explanations analysis was used to elucidate the weights and characteristics of various factors associated with severe SCD.

The average SCD score among nurses in the menopause transition was (5.38 ± 2.43). The Bortua algorithm identified 13 significant feature factors. Among the seven models, the support vector machine exhibited the best overall performance, achieving an area under the receiver operating characteristic curve of 0.846, accuracy of 0.789, sensitivity of 0.753, specificity of 0.802, and an F1 score of 0.658. The two variables most strongly associated with SCD were menopausal symptoms and the stage of menopause.

The machine learning models effectively identify individuals with severe SCD and the related factors associated with severe SCD in nurses during the menopause transition. These findings offer valuable insights for the management of cognitive health in women undergoing the menopause transition.

The prevalence of hearing loss (HL) has emerged as an escalating public health concern globally. The objective of this study was to leverage data from the National Health and Nutritional Examination Survey (NHANES) to develop an interpretable predictive machine learning (ML) model for HL. In accordance with the established inclusion and exclusion criteria, a total of 2814 participants were randomly assigned to one of two distinct groups for the training and validation of the predictive models. We identified the most significant variables using Recursive Feature Elimination and constructed a HL prediction model through various ML models. The generalization ability of the models was evaluated via 10-fold cross-validation. Eight different models were utilized to develop the optimal prediction model for HL. Subsequently, three interpretable methods, Feature importance analysis, Generalized linear model (GLM) and Restricted cubic spline (RCS) were integrated into a pipeline and embedded in ML for model interpretation. In this study, the Random Forest (RF) exhibited superior performance across all evaluation metrics after balancing the data using the Synthetic Minority Oversampling Technique (SMOTE), particularly excelling in AUC, PR-AUC and F1 score. Feature importance analysis uncovered significant correlations between HL and top 10 features, including age, blood lead (Pb) level, urine thallium (Tl) level, BMI, total energy, urine antimon (Sb) level, vitamin E intake, urine cobalt (Co) level, calcium intake and urine cesium (Cs) level. Moreover, both univariate and multivariate GLMs identified blood Pb [OR (95 % CI):1.169 (1.037,1.311)] and vitamin E intake [OR (95 % CI):0.776 (0.641,0.928)] as the main features associated with HL. The RCS analysis further revealed that increased blood Pb level and decreased vitamin E intake correspond to a proportional rise in the anticipated risk of HL after adjusted by confounders. Our ML models identify key factors that, if validated by future studies, will have important implications for hearing conservation. Furthermore, these ML-based point-of-care prediction models will help overcome barriers to hearing healthcare and enable the efficient allocation of resources by accurately identifying individuals who are in dire need of hearing assessment.

Thrombotic events, such as strokes and deep vein thrombosis, remain a significant global health burden, with traditional diagnostic methods often failing to capture the complex, patient-specific nuances of thrombosis risk. This Perspective explores the revolutionary potential of microengineered vessel-on-chip platforms in thrombosis research and personalized medicine. We discuss the evolution from basic microfluidic channels to advanced 3D-printed, patient-specific models that accurately replicate complex vascular geometries, incorporating all elements of Virchow's triad. Integrating these platforms with cutting-edge sensing technologies, including wearable ultrasonic devices and electrochemical biosensors, enables real-time monitoring of thrombosis-related parameters. Crucially, we highlight the transformative role of artificial intelligence and digital twin technology in leveraging vast patient-specific data collected from these models. This integration allows for the development of predictive algorithms and personalized digital twins, offering unprecedented thrombosis risk assessment, treatment optimization, and drug screening capabilities. The clinical relevance and validation of these models are examined, showcasing their potential to predict thrombotic events and guide personalized treatment strategies. While challenges in scalability, standardization, and regulatory approval persist, the convergence of vessel-on-chip platforms, advanced sensing, and AI-driven digital twins promises to revolutionize thrombosis management. This approach paves the way for a new era of precision cardiovascular care, offering noninvasive, predictive, and personalized strategies for thrombosis prevention and treatment, ultimately improving patient outcomes and reducing the global burden of cardiovascular diseases.

AI has emerged as a transformative force in clinical medicine, changing the diagnosis, treatment, and management of patients. Tools have been derived for working with ML, DL, and NLP algorithms to analyze large complex medical datasets with unprecedented accuracy and speed, thereby improving diagnostic precision, treatment personalization, and patient care outcomes. For example, CNNs have dramatically improved the accuracy of medical imaging diagnoses, and NLP algorithms have greatly helped extract insights from unstructured data, including EHRs. However, there are still numerous challenges that face AI integration into clinical workflows, including data privacy, algorithmic bias, ethical dilemmas, and problems with the interpretability of "black-box" AI models. These barriers have thus far prevented the widespread application of AI in health care, and its possible trends, obstacles, and future implications are necessary to be systematically explored. The purpose of this paper is, therefore, to assess the current trends in AI applications in clinical medicine, identify those obstacles that are hindering adoption, and identify possible future directions. This research hopes to synthesize evidence from other peer-reviewed articles to provide a more comprehensive understanding of the role that AI plays to advance clinical practices, improve patient outcomes, or enhance decision-making.

A systematic review was done according to the PRISMA guidelines to explore the integration of Artificial Intelligence in clinical medicine, including trends, challenges, and future directions. PubMed, Cochrane Library, Web of Science, and Scopus databases were searched for peer-reviewed articles from 2014 to 2024 with keywords such as "Artificial Intelligence in Medicine," "AI in Clinical Practice," "Machine Learning in Healthcare," and "Ethical Implications of AI in Medicine." Studies focusing on AI application in diagnostics, treatment planning, and patient care reporting measurable clinical outcomes were included. Non-clinical AI applications and articles published before 2014 were excluded. Selected studies were screened for relevance, and then their quality was critically appraised to synthesize data reliably and rigorously.

This systematic review includes the findings of 8 studies that pointed out the transformational role of AI in clinical medicine. AI tools, such as CNNs, had diagnostic accuracy more than the traditional methods, particularly in radiology and pathology. Predictive models efficiently supported risk stratification, early disease detection, and personalized medicine. Despite these improvements, significant hurdles, including data privacy, algorithmic bias, and resistance from clinicians regarding the "black-box" nature of AI, had yet to be surmounted. XAI has emerged as an attractive solution that offers the promise to enhance interpretability and trust. As a whole, AI appeared promising in enhancing diagnostics, treatment personalization, and clinical workflows by dealing with systemic inefficiencies.

The transformation potential of AI in clinical medicine can transform diagnostics, treatment strategies, and efficiency. Overcoming obstacles such as concerns about data privacy, the danger of algorithmic bias, and difficulties with interpretability may pave the way for broader use and facilitate improvement in patient outcomes while transforming clinical workflows to bring sustainability into healthcare delivery.

Emerging evidence underscores the potential application of artificial intelligence (AI) in discovering noninvasive blood biomarkers. However, the diagnostic value of AI-derived blood biomarkers for ovarian cancer (OC) remains inconsistent.

We aimed to evaluate the research quality and the validity of AI-based blood biomarkers in OC diagnosis.

A systematic search was performed in the MEDLINE, Embase, IEEE Xplore, PubMed, Web of Science, and the Cochrane Library databases. Studies examining the diagnostic accuracy of AI in discovering OC blood biomarkers were identified. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-AI tool. Pooled sensitivity, specificity, and area under the curve (AUC) were estimated using a bivariate model for the diagnostic meta-analysis.

A total of 40 studies were ultimately included. Most (n=31, 78%) included studies were evaluated as low risk of bias. Overall, the pooled sensitivity, specificity, and AUC were 85% (95% CI 83%-87%), 91% (95% CI 90%-92%), and 0.95 (95% CI 0.92-0.96), respectively. For contingency tables with the highest accuracy, the pooled sensitivity, specificity, and AUC were 95% (95% CI 90%-97%), 97% (95% CI 95%-98%), and 0.99 (95% CI 0.98-1.00), respectively. Stratification by AI algorithms revealed higher sensitivity and specificity in studies using machine learning (sensitivity=85% and specificity=92%) compared to those using deep learning (sensitivity=77% and specificity=85%). In addition, studies using serum reported substantially higher sensitivity (94%) and specificity (96%) than those using plasma (sensitivity=83% and specificity=91%). Stratification by external validation demonstrated significantly higher specificity in studies with external validation (specificity=94%) compared to those without external validation (specificity=89%), while the reverse was observed for sensitivity (74% vs 90%). No publication bias was detected in this meta-analysis.

AI algorithms demonstrate satisfactory performance in the diagnosis of OC using blood biomarkers and are anticipated to become an effective diagnostic modality in the future, potentially avoiding unnecessary surgeries. Future research is warranted to incorporate external validation into AI diagnostic models, as well as to prioritize the adoption of deep learning methodologies.

PROSPERO CRD42023481232; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023481232.

The early diagnosis of keratoconus (KC) is crucial for making treatment decisions. Therefore, the purpose of this study was to determine the potential disease-specific gene biomarker and landscape the immune environment in KC.

The transcriptome data of KC was obtained from Gene Expression Omnibus (GEO) and ArrayExpress databases for next analysis. The differently expressed mRNAs, microRNAs and lncRNAs between KC and control groups were firstly identified and the disease-specific protein-protein interaction (PPI) network as well as competing endogenous RNA (ceRNA) coregulatory network were constructed to explore the underlying molecular mechanism of KC. Besides, ElasticNet algorithm was used to develop a diagnostic model and associated nomograms to improve diagnosis of KC. Finally, multiple deconvolution methodologies were applied to decode the immune environment of KC patients.

In brief, we constructed the disease-specific PPI and ceRNA networks in KC through integrative analyses. The pathway enrichment manifested that these networks were significantly associated with lipopolysaccharide, chemokine and inflammatory related pathways. Based on the ceRNA network, we constructed a diagnostic model and associated nomogram which manifested a good performance for diagnosis of KC. Moreover, contrasted to control groups, we obviously observed that a distinct immune microenvironment existed in KC patients. Via single-cell sequencing analysis, we found that immune cells (Monocytes, Macrophages, and T cells) were strongly connected with corneal cells in KC patients.

In sum, we systematically constructed a diagnostic model and associated nomogram which provided novel biomarkers for the early detection of KC. Besides, our study comprehensively displayed the immune microenvironment of KC which provided new insights for understanding the molecular mechanism of KC.

Postoperative nausea and vomiting (PONV) is a frequently observed complication in patients undergoing surgery under general anesthesia. Moreover, it is a frequent cause of distress and dissatisfaction in the early postoperative period. Currently, the classical scores used for predicting PONV have not yielded satisfactory results. Therefore, prognostic models for the prediction of early and delayed PONV were developed in this study to achieve satisfactory predictive performance.

The retrospective data of inpatient adult patients admitted to the post-anesthesia care unit after undergoing surgical procedures under general anesthesia at the Sheba Medical Center, Israel, between September 1, 2018, and September 1, 2023, were used in this study. An ensemble model of machine-learning algorithms trained on the data of 35,003 patients was developed. The k-fold cross-validation method was used followed by splitting the data to train and test sets that optimally preserve the sociodemographic features of the patients.

Among the 35,003 patients, early and delayed PONV were observed in 1,340 (3.82%) and 6,582 (18.80%) patients, respectively. The proposed PONV prediction models correctly predicted early and delayed PONV in 83.6% and 74.8% of cases, respectively, outperforming the second-best PONV prediction score (Koivuranta score) by 13.0% and 10.4%, respectively. Feature importance analysis revealed that the performance of the proposed prediction tools aligned with previous clinical knowledge, indicating their utility.

The machine learning-based models developed in this study enabled improved PONV prediction, thereby facilitating personalized care and improved patient outcomes.

This study aims to develop a comprehensive simulation framework to connect radiation effects from the microscopic to the nanoscopic scale.

The process begins with a Geant4-DNA simulation based on the example "molecularDNA", producing a dataset of twelve different types of early DNA damages within an Escherichia coli (E. coli) bacterium, generated by proton irradiation at different kinetic energies, giving a nano-scale view of the particle-matter interaction. Then we pass to the micro-scale with a Geant4 simulation, based on the example "radiobiology", providing a microscopic view of proton interactions with matter through the Linear Energy Transfer (LET). Then GANDALF (Generative ANsatz for DNA damage evALuation and Forecast) Machine Learning (ML) toolkit, a Neural Network (NN)-based regression system, is employed to correlate the micro-scale LET data with the nano-scale occurrences of DNA damages in the E. coli bacterium.

The trained ML algorithm provides a practical tool to convert LET curves versus depth in a water phantom into DNA damage curves for twelve distinct types of DNA damage. To assess the performance, we evaluated the choice and optimization of the regression system based on its interpolation and extrapolation capabilities, ensuring the model could reliably predict DNA damage under various conditions.

Through the synergistic integration of Geant4, Geant4-DNA and ML, the study provides a tool to easily convert the results at the micro-scale of Geant4 to those at the nano-scale of Geant4-DNA without having to deal with the high CPU time requirements of the latter.

Magnetic resonance imaging (MRI) is routinely used to confirm the suspected diagnosis of anterior cruciate ligament (ACL) injury. Recently, many studies explored the role of artificial intelligence (AI) and deep learning (DL), a sub-category of AI, in the musculoskeletal field and medical imaging. The aim of this study was to review the current applications of DL models to detect ACL injury on MRI, thus providing an updated and critical synthesis of the existing literature and identifying emerging trends and challenges in the field. A total of 23 relevant articles were identified and included in the review. Articles originated from 10 countries, with China having the most contributions (n = 9), followed by the United State of America (n = 4). Throughout the article, we analyzed the concept of DL in ACL tears and provided examples of how these tools can impact clinical practice and patient care. DL models for MRI detection of ACL injury reported high values of accuracy, especially helpful for less experienced clinicians. Time efficiency was also demonstrated. Overall, the deep learning models have proven to be a valid resource, although still requiring technological developments for implementation in daily practice.

Machine learning (ML), a major branch of artificial intelligence, has not only demonstrated the potential to significantly improve numerous sectors of healthcare but has also made significant contributions to the field of solid organ transplantation. ML provides revolutionary opportunities in areas such as donor-recipient matching, post-transplant monitoring, and patient care by automatically analyzing large amounts of data, identifying patterns, and forecasting outcomes.

To conduct a comprehensive bibliometric analysis of publications on the use of ML in transplantation to understand current research trends and their implications.

On July 18, a thorough search strategy was used with the Web of Science database. ML and transplantation-related keywords were utilized. With the aid of the VOS viewer application, the identified articles were subjected to bibliometric variable analysis in order to determine publication counts, citation counts, contributing countries, and institutions, among other factors.

Of the 529 articles that were first identified, 427 were deemed relevant for bibliometric analysis. A surge in publications was observed over the last four years, especially after 2018, signifying growing interest in this area. With 209 publications, the United States emerged as the top contributor. Notably, the "Journal of Heart and Lung Transplantation" and the "American Journal of Transplantation" emerged as the leading journals, publishing the highest number of relevant articles. Frequent keyword searches revealed that patient survival, mortality, outcomes, allocation, and risk assessment were significant themes of focus.

The growing body of pertinent publications highlights ML's growing presence in the field of solid organ transplantation. This bibliometric analysis highlights the growing importance of ML in transplant research and highlights its exciting potential to change medical practices and enhance patient outcomes. Encouraging collaboration between significant contributors can potentially fast-track advancements in this interdisciplinary domain.

Skeletal fluorosis caused by coal-burning type endemic fluorosis greatly affects the health of the population in the affected areas, but large-scale diagnostic work is limited by human and material resources, making it difficult to implement comprehensively. In this study, we investigate adults in coal-burning type endemic skeletal fluorosis areas in Guizhou. The study areas are selected by a comprehensive analysis of the detection rate of dental fluorosis in children aged 8-12 years in Guizhou for the year 2023. We collect information from questionnaires, physical examinations, and diagnostic X-ray Findings of Skeletal Fluorosis (XRF) in adults. The effective number of people investigated in this study was 2276, and the detection rate of XRF was 79.35 %. The top 5 relevant factors for skeletal fluorosis were age, educational background, height, Mini-Mental State Examination (MMSE) score and family population. Among the 8 models, random forest performed the best with an accuracy of 86.00 %, and the performance was more stable in the prevalence of different sizes, which provides a new idea for the prevention and treatment of skeletal fluorosis in coal-burning type of endemic fluorosis. In this study, the screening of the main correlates of XRF can provide an effective reference for the initial screening of skeletal fluorosis, and the practical application value of machine learning in this research field can be further explored.

Parkinson disease (PD) is a common neurodegenerative disease characterized by both motor and nonmotor symptoms. Cognitive impairment often occurs early in the disease and can persist throughout its progression, severely impacting patients' quality of life. The utilization of machine learning (ML) has recently shown promise in identifying cognitive impairment in patients with PD.

This study aims to summarize different ML models applied to cognitive impairment in patients with PD and to identify determinants for improving diagnosis and predictive power for early detection of cognitive impairment.

PubMed, Cochrane, Embase, and Web of Science were searched for relevant articles on March 2, 2024. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Bivariate meta-analysis was used to estimate pooled sensitivity and specificity results, presented as odds ratio (OR) and 95% CI. A summary receiver operator characteristic (SROC) curve was used.