1
|
Ebigbo A, Messmann H, Lee SH. Artificial Intelligence Applications in Image-Based Diagnosis of Early Esophageal and Gastric Neoplasms. Gastroenterology 2025:S0016-5085(25)00471-8. [PMID: 40043857 DOI: 10.1053/j.gastro.2025.01.253] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/15/2024] [Revised: 01/14/2025] [Accepted: 01/22/2025] [Indexed: 04/03/2025]
Abstract
Artificial intelligence (AI) holds the potential to transform the management of upper gastrointestinal (GI) conditions, such as Barrett's esophagus, esophageal squamous cell cancer, and early gastric cancer. Advancements in deep learning and convolutional neural networks offer improved diagnostic accuracy and reduced diagnostic variability across different clinical settings, particularly where human error or fatigue may impair diagnostic precision. Deep learning models have shown the potential to improve early cancer detection and lesion characterization, predict invasion depth, and delineate lesion margins with remarkable accuracy, all contributing to effective treatment planning. Several challenges, however, limit the broad application of AI in GI endoscopy, particularly in the upper GI tract. Subtle lesion morphology and restricted diversity in training datasets, which are often sourced from specialized centers, may constrain the generalizability of AI models in various clinical settings. Furthermore, the "black box" nature of some AI systems can impede explainability and clinician trust. To address these issues, efforts are underway to incorporate multimodal data, such as combining endoscopic and histopathologic imaging, to bolster model robustness and transparency. In the future, AI promises substantial advancements in automated real-time endoscopic guidance, personalized risk assessment, and optimized biopsy decision making. As it evolves, it would substantially impact not only early diagnosis and prognosis, but also the cost-effectiveness of managing upper GI diseases, ultimately leading to improved patient outcomes and more efficient health care delivery.
Collapse
Affiliation(s)
- Alanna Ebigbo
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany.
| | - Helmut Messmann
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany.
| | - Sung Hak Lee
- Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, South Korea; Seoul St. Mary's Hospital, Seoul, South Korea.
| |
Collapse
|
2
|
Yin K, Liang H, Guo W, Chen YX, Cui ML, Zhang MX. Artificial intelligence and early cancer of the digestive tract: New challenges and new futures. Shijie Huaren Xiaohua Zazhi 2025; 33:1-10. [DOI: 10.11569/wcjd.v33.i1.1] [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: 10/14/2024] [Revised: 11/06/2024] [Accepted: 11/21/2024] [Indexed: 01/22/2025] Open
Abstract
Early gastrointestinal tumors have a good prognosis, but they have insidious onset and no specific manifestations, making their diagnosis difficult. With the rapid development of artificial intelligence technology in the medical field, it has shown great potential in clinical work such as diagnosis and prognosis prediction of early gastrointestinal cancer. In this paper, we systematically review the relevant studies on AI in early esophageal cancer, early gastric cancer, early colon cancer, and hepatobiliary pancreatic cancer, and discuss the challenges and futures of AI application in early gastrointestinal cancer.
Collapse
Affiliation(s)
- Kun Yin
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Hao Liang
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Wen Guo
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Ya-Xin Chen
- Xi'an Medical College, Xi'an 710021, Shaanxi Province, China
| | - Man-Li Cui
- Department of Gastroenterology, First Affiliated Hospital of Xi'an Medical College, Xi'an 710077, Shaanxi Province, China
| | - Ming-Xin Zhang
- Department of Gastroenterology, First Affiliated Hospital of Xi'an Medical College, Xi'an 710077, Shaanxi Province, China
| |
Collapse
|
3
|
Chen HY, Por CR, Hong YK, Kong EQZ, Subramaniyan V. Molecular mechanisms underlying oesophageal cancer development triggered by chronic alcohol consumption. CLINICAL AND TRANSLATIONAL DISCOVERY 2024; 4. [DOI: 10.1002/ctd2.70021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/26/2024] [Accepted: 11/24/2024] [Indexed: 12/27/2024]
Abstract
AbstractThis review explores the mechanisms underlying alcohol‐induced oesophageal carcinogenesis, including DNA damage, oxidative stress, and nutritional deficiencies. Alcohol metabolism primarily involves alcohol dehydrogenase (ADH) converting ethanol to acetaldehyde, which can cause DNA damage, inhibit repair mechanisms, and form DNA adducts thus inhibiting DNA replication. Plus, it delves into the epidemiological evidence, genetic susceptibility, epigenetic modifications, biomarkers, and preventive strategies associated with alcohol‐related oesophageal cancers. Consumption of alcohol increases the risk of gastroesophageal reflux disease thus compromising mucosal integrity of the oesophagus as dysregulation of cytokines such as IL‐18, TNFA, GATA3, TLR4, and CD68 expands the intercellular spaces of epithelial cells. Genetic variants, such as ADH1B rs1229984 and ALDH2 rs671, significantly influence susceptibility to alcohol‐related oesophageal cancers, with these variations affecting acetaldehyde metabolism and cancer risk. Understanding these factors is crucial for early detection, effective treatment, and the development of targeted prevention strategies. Biomarkers, such as miRNA and metabolite markers, offer non‐invasive methods for early detection, while advanced endoscopic techniques provide better diagnostic accuracy. Pharmacological interventions, such as statins and proton pump inhibitors, also show potential for reducing cancer progression in high‐risk individuals. Despite advances, late‐stage oesophageal cancer diagnoses are still common, highlighting the need for better screening and prevention. Further research, including this study, should aim to improve early detection, personalise prevention, and explore new treatments to reduce cases and enhance outcomes in alcohol‐related oesophageal cancers.
Collapse
Affiliation(s)
- Huai Yi Chen
- Jeffrey Cheah School of Medicine and Health Sciences Monash University Jalan Lagoon Selatan Bandar Sunway Subang Jaya Malaysia
| | - Chia Rou Por
- Jeffrey Cheah School of Medicine and Health Sciences Monash University Jalan Lagoon Selatan Bandar Sunway Subang Jaya Malaysia
| | - Yong Kai Hong
- Jeffrey Cheah School of Medicine and Health Sciences Monash University Jalan Lagoon Selatan Bandar Sunway Subang Jaya Malaysia
| | - Eason Qi Zheng Kong
- Jeffrey Cheah School of Medicine and Health Sciences Monash University Jalan Lagoon Selatan Bandar Sunway Subang Jaya Malaysia
| | - Vetriselvan Subramaniyan
- Jeffrey Cheah School of Medicine and Health Sciences Monash University Jalan Lagoon Selatan Bandar Sunway Subang Jaya Malaysia
- School of Medical and Life Sciences Sunway University Jalan Lagoon Selatan Bandar Sunway Petaling Jaya Malaysia
| |
Collapse
|
4
|
Chen Y, Ma Y, Wu H, Wei X, Xu Z, Wang Q. Examining the relationship between preoperative nutritional and symptom assessment and postoperative atrial fibrillation in esophageal squamous cell carcinoma patients: a retrospective cohort study. BMC Surg 2024; 24:298. [PMID: 39385162 PMCID: PMC11463059 DOI: 10.1186/s12893-024-02609-7] [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: 02/16/2024] [Accepted: 10/01/2024] [Indexed: 10/11/2024] Open
Abstract
OBJECTIVE The study aimed to examine the relationship between preoperative nutritional status, symptom burden, and the occurrence of postoperative atrial fibrillation in Esophageal Squamous Cell Carcinoma patients. METHODS The study, conducted in the Department of Thoracic Surgery at the Affiliated Huai'an No. 1 People's Hospital of Nanjing Medical University, applied the NRS 2002, SGA and MSAS scoring systems as measures of nutritional status and symptom occurrence in patients diagnosed with ESCC. Univariate and multivariate logistic regression analysis were performed to evaluate the association between nutritional scores, symptom scores, and postoperative complications. RESULTS The research found a significant correlation between high MSAS scores and postoperative atrial fibrillation. Patients with high symptom burden also tended to have nutritional risk or malnutrition according to the NRS2002 and SGA scores. CONCLUSION There is a need for healthcare providers to pay attention to ESCC patients' physical and psychological symptoms. Close monitoring of nutritional status and timely nutritional interventions should be integrated into these patients' care plans as they have been found to be related to postoperative complications such as atrial fibrillation.
Collapse
Affiliation(s)
- Yunyun Chen
- Department of Thoracic Surgery, The Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University, Huaian, 223300, China
| | - Yan Ma
- Department of Thoracic Surgery, The Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University, Huaian, 223300, China
| | - Haiyan Wu
- Department of Thoracic Surgery, The Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University, Huaian, 223300, China
| | - Xinqi Wei
- Department of Thoracic Surgery, The Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University, Huaian, 223300, China
| | - Zhiyun Xu
- Department of Thoracic Surgery, The Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University, Huaian, 223300, China.
| | - Qingmei Wang
- Department of Thoracic Surgery, The Affiliated Huaian No. 1 People's Hospital of Nanjing Medical University, Huaian, 223300, China.
| |
Collapse
|
5
|
Bangolo A, Wadhwani N, Nagesh VK, Dey S, Tran HHV, Aguilar IK, Auda A, Sidiqui A, Menon A, Daoud D, Liu J, Pulipaka SP, George B, Furman F, Khan N, Plumptre A, Sekhon I, Lo A, Weissman S. Impact of artificial intelligence in the management of esophageal, gastric and colorectal malignancies. Artif Intell Gastrointest Endosc 2024; 5:90704. [DOI: 10.37126/aige.v5.i2.90704] [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: 12/12/2023] [Revised: 01/28/2024] [Accepted: 03/04/2024] [Indexed: 05/11/2024] Open
Abstract
The incidence of gastrointestinal malignancies has increased over the past decade at an alarming rate. Colorectal and gastric cancers are the third and fifth most commonly diagnosed cancers worldwide but are cited as the second and third leading causes of mortality. Early institution of appropriate therapy from timely diagnosis can optimize patient outcomes. Artificial intelligence (AI)-assisted diagnostic, prognostic, and therapeutic tools can assist in expeditious diagnosis, treatment planning/response prediction, and post-surgical prognostication. AI can intercept neoplastic lesions in their primordial stages, accurately flag suspicious and/or inconspicuous lesions with greater accuracy on radiologic, histopathological, and/or endoscopic analyses, and eliminate over-dependence on clinicians. AI-based models have shown to be on par, and sometimes even outperformed experienced gastroenterologists and radiologists. Convolutional neural networks (state-of-the-art deep learning models) are powerful computational models, invaluable to the field of precision oncology. These models not only reliably classify images, but also accurately predict response to chemotherapy, tumor recurrence, metastasis, and survival rates post-treatment. In this systematic review, we analyze the available evidence about the diagnostic, prognostic, and therapeutic utility of artificial intelligence in gastrointestinal oncology.
Collapse
Affiliation(s)
- Ayrton Bangolo
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Nikita Wadhwani
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Vignesh K Nagesh
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Shraboni Dey
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Hadrian Hoang-Vu Tran
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Izage Kianifar Aguilar
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Auda Auda
- Department of Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Aman Sidiqui
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Aiswarya Menon
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Deborah Daoud
- Department of Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - James Liu
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Sai Priyanka Pulipaka
- Department of Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Blessy George
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Flor Furman
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Nareeman Khan
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Adewale Plumptre
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Imranjot Sekhon
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Abraham Lo
- Department of Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| | - Simcha Weissman
- Department of Internal Medicine, Palisades Medical Center, North Bergen, NJ 07047, United States
| |
Collapse
|
6
|
Hamada T, Yasaka K, Nakai Y, Fukuda R, Hakuta R, Ishigaki K, Kanai S, Noguchi K, Oyama H, Saito T, Sato T, Suzuki T, Takahara N, Isayama H, Abe O, Fujishiro M. Computed tomography-based prediction of pancreatitis following biliary metal stent placement with the convolutional neural network. Endosc Int Open 2024; 12:E772-E780. [PMID: 38904060 PMCID: PMC11188753 DOI: 10.1055/a-2298-0147] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Accepted: 03/25/2024] [Indexed: 06/22/2024] Open
Abstract
Background and study aims Pancreatitis is a potentially lethal adverse event of endoscopic transpapillary placement of a self-expandable metal stent (SEMS) for malignant biliary obstruction (MBO). Deep learning-based image recognition has not been investigated in predicting pancreatitis in this setting. Patients and methods We included 70 patients who underwent endoscopic placement of a SEMS for nonresectable distal MBO. We constructed a convolutional neural network (CNN) model for pancreatitis prediction using a series of pre-procedure computed tomography images covering the whole pancreas (≥ 120,960 augmented images in total). We examined the additional effects of the CNN-based probabilities on the following machine learning models based on clinical parameters: logistic regression, support vector machine with a linear or RBF kernel, random forest classifier, and gradient boosting classifier. Model performance was assessed based on the area under the curve (AUC) in the receiver operating characteristic analysis, positive predictive value (PPV), accuracy, and specificity. Results The CNN model was associated with moderate levels of performance metrics: AUC, 0.67; PPV, 0.45; accuracy, 0.66; and specificity, 0.63. When added to the machine learning models, the CNN-based probabilities increased the performance metrics. The logistic regression model with the CNN-based probabilities had an AUC of 0.74, PPV of 0.85, accuracy of 0.83, and specificity of 0.96, compared with 0.72, 0.78, 0.77, and 0.96, respectively, without the probabilities. Conclusions The CNN-based model may increase predictability for pancreatitis following endoscopic placement of a biliary SEMS. Our findings support the potential of deep learning technology to improve prognostic models in pancreatobiliary therapeutic endoscopy.
Collapse
Affiliation(s)
- Tsuyoshi Hamada
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
- Department of Hepato-Biliary-Pancreatic Medicine, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
| | - Koichiro Yasaka
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Yousuke Nakai
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
- Department of Endoscopy and Endoscopic Surgery, The University of Tokyo Hospital, Tokyo, Japan
| | - Rintaro Fukuda
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Ryunosuke Hakuta
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Kazunaga Ishigaki
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Sachiko Kanai
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Kensaku Noguchi
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Hiroki Oyama
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Tomotaka Saito
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Tatsuya Sato
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Tatsunori Suzuki
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Naminatsu Takahara
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Hiroyuki Isayama
- Department of Gastroenterology, Graduate School of Medicine, Juntendo University, Tokyo, Japan
| | - Osamu Abe
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Mitsuhiro Fujishiro
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| |
Collapse
|
7
|
Qi JH, Huang SL, Jin SZ. Novel milestones for early esophageal carcinoma: From bench to bed. World J Gastrointest Oncol 2024; 16:1104-1118. [PMID: 38660637 PMCID: PMC11037034 DOI: 10.4251/wjgo.v16.i4.1104] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 01/28/2024] [Accepted: 02/26/2024] [Indexed: 04/10/2024] Open
Abstract
Esophageal cancer (EC) is the seventh most common cancer worldwide, and esophageal squamous cell carcinoma (ESCC) accounts for the majority of cases of EC. To effectively diagnose and treat ESCC and improve patient prognosis, timely diagnosis in the initial phase of the illness is necessary. This article offers a detailed summary of the latest advancements and emerging technologies in the timely identification of ECs. Molecular biology and epigenetics approaches involve the use of molecular mechanisms combined with fluorescence quantitative polymerase chain reaction (qPCR), high-throughput sequencing technology (next-generation sequencing), and digital PCR technology to study endogenous or exogenous biomolecular changes in the human body and provide a decision-making basis for the diagnosis, treatment, and prognosis of diseases. The investigation of the microbiome is a swiftly progressing area in human cancer research, and microorganisms with complex functions are potential components of the tumor microenvironment. The intratumoral microbiota was also found to be connected to tumor progression. The application of endoscopy as a crucial technique for the early identification of ESCC has been essential, and with ongoing advancements in technology, endoscopy has continuously improved. With the advancement of artificial intelligence (AI) technology, the utilization of AI in the detection of gastrointestinal tumors has become increasingly prevalent. The implementation of AI can effectively resolve the discrepancies among observers, improve the detection rate, assist in predicting the depth of invasion and differentiation status, guide the pericancerous margins, and aid in a more accurate diagnosis of ESCC.
Collapse
Affiliation(s)
- Ji-Han Qi
- Department of Gastroenterology and Hepatology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, Heilongjiang Province, China
| | - Shi-Ling Huang
- Department of Gastroenterology and Hepatology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, Heilongjiang Province, China
| | - Shi-Zhu Jin
- Department of Gastroenterology and Hepatology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, Heilongjiang Province, China
| |
Collapse
|
8
|
Shi M, Zhang H, Ma L, Wang X, Sun D, Feng Z. Innovative prognostic modeling in ESCC: leveraging scRNA-seq and bulk-RNA for dendritic cell heterogeneity analysis. Front Immunol 2024; 15:1352454. [PMID: 38515748 PMCID: PMC10956130 DOI: 10.3389/fimmu.2024.1352454] [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: 12/08/2023] [Accepted: 02/21/2024] [Indexed: 03/23/2024] Open
Abstract
Background Globally, esophageal squamous cell carcinoma (ESCC) stands out as a common cancer type, characterized by its notably high rates of occurrence and mortality. Recent advancements in treatment methods, including immunotherapy, have shown promise, yet the prognosis remains poor. In the context of tumor development and treatment outcomes, the tumor microenvironment (TME), especially the function of dendritic cells (DCs), is significantly influential. Our study aims to delve deeper into the heterogeneity of DCs in ESCC using single-cell RNA sequencing (scRNA-seq) and bulk RNA analysis. Methods In the scRNA-seq analysis, we utilized the SCP package for result visualization and functional enrichment analysis of cell subpopulations. CellChat was employed to identify potential oncogenic mechanisms in DCs, while Monocle 2 traced the evolutionary trajectory of the three DC subtypes. CopyKAT assessed the benign or malignant nature of cells, and SCENIC conducted transcription factor regulatory network analysis, offering a preliminary exploration of DC heterogeneity. In Bulk-RNA analysis, we constructed a prognostic model for ESCC prognosis and immunotherapy response, based on DC marker genes. This model was validated through quantitative PCR (qPCR) and immunohistochemistry (IHC), confirming the gene expression levels. Results In this study, through intercellular communication analysis, we identified GALECTIN and MHC-I signaling pathways as potential oncogenic mechanisms within dendritic cells. We categorized DCs into three subtypes: plasmacytoid (pDC), conventional (cDC), and tolerogenic (tDC). Our findings revealed that pDCs exhibited an increased proportion of cells in the G2/M and S phases, indicating enhanced cellular activity. Pseudotime trajectory analysis demonstrated that cDCs were in early stages of differentiation, whereas tDCs were in more advanced stages, with pDCs distributed across both early and late differentiation phases. Prognostic analysis highlighted a significant correlation between pDCs and tDCs with the prognosis of ESCC (P< 0.05), while no significant correlation was observed between cDCs and ESCC prognosis (P = 0.31). The analysis of cell malignancy showed the lowest proportion of malignant cells in cDCs (17%), followed by pDCs (29%), and the highest in tDCs (48%), with these results being statistically significant (P< 0.05). We developed a robust ESCC prognostic model based on marker genes of pDCs and tDCs in the GSE53624 cohort (n = 119), which was validated in the TCGA-ESCC cohort (n = 139) and the IMvigor210 immunotherapy cohort (n = 298) (P< 0.05). Additionally, we supplemented the study with a novel nomogram that integrates clinical features and risk assessments. Finally, the expression levels of genes involved in the model were validated using qPCR (n = 8) and IHC (n = 16), thereby confirming the accuracy of our analysis. Conclusion This study enhances the understanding of dendritic cell heterogeneity in ESCC and its impact on patient prognosis. The insights gained from scRNA-seq and Bulk-RNA analysis contribute to the development of novel biomarkers and therapeutic targets. Our prognostic models based on DC-related gene signatures hold promise for improving ESCC patient stratification and guiding treatment decisions.
Collapse
Affiliation(s)
- Mengnan Shi
- Department of Gastroenterology, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China
- Hebei Key Laboratory of Gastroenterology, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
- Hebei Clinical Research Center for Digestive Diseases, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
| | - Han Zhang
- Clinical School of Thoracic, Tianjin Medical University, Tianjin, China
| | - Linnan Ma
- Department of Gastroenterology, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China
- Hebei Key Laboratory of Gastroenterology, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
- Hebei Clinical Research Center for Digestive Diseases, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
| | - Xiaoting Wang
- Department of Gastroenterology, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China
- Hebei Key Laboratory of Gastroenterology, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
- Hebei Clinical Research Center for Digestive Diseases, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
| | - Daqiang Sun
- Tianjin Chest Hospital, Tianjin University, Tianjin, China
| | - Zhijie Feng
- Department of Gastroenterology, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China
- Hebei Key Laboratory of Gastroenterology, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
- Hebei Clinical Research Center for Digestive Diseases, Hebei Institute of Gastroenterology, Shijiazhuang, Hebei, China
| |
Collapse
|
9
|
Liu K, Bai J, Gao L, Zhao X, Dong X, Chen H, Dong J, Niu M, Han Y, Liu Z. The diagnostic performance of V' and U' variables as an objective index of pink-color sign for diagnosing esophageal cancerous lesions. Surg Endosc 2024; 38:148-157. [PMID: 37945708 DOI: 10.1007/s00464-023-10496-x] [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: 07/21/2023] [Accepted: 09/23/2023] [Indexed: 11/12/2023]
Abstract
BACKGROUND The pink-color sign (PCS) has been widely used for diagnosing esophageal squamous cell carcinoma (ESCC) during Lugol's iodine chromoendoscopy. However, the identification of the PCS only relies on the subjective assessments made by the endoscopist, which could lead to bias and disagreement. Previous research has indicated that the V' variable can, as an objective index, define the PCS in the LU'V' color space. We aimed to validate the diagnostic performance of the PCS defined by the V' variable alone and attempt to improve the diagnostic performance by combining the V' and U' variables. METHODS We re-examined 231 subjects with Lugol's unstained lesions (LULs) from a previously reported prospective trial. The diagnostic performance of the method using V' variable alone (V' alone method), the combination method using V' and U' variables (V' + U' method), and the endoscopists were calculated and compared. RESULTS A total of 236 LULs were included, among which 46 were histologically confirmed to be cancerous lesions. The sensitivity, specificity, and accuracy of the V' alone method were 73.91% (95% CI 58.87-85.73%), 79.47% (95% CI 73.03-84.98%), and 78.39% (95% CI 72.59-83.47%) in the external validation cohort, respectively. It is inferior to endoscopists in terms of specificity and accuracy. The V' + U' method demonstrated a diagnostic performance comparable to the experienced endoscopists, with sensitivity, specificity, and accuracy of 76.74% (95% CI 61.37-88.25%), 88.64% (95% CI 83.00-92.92%), and 86.30% (95% CI 81.03-90.56%), respectively. CONCLUSION The V' alone method exhibited lower specificity and accuracy than the experienced endoscopist and the V' + U' method. However, the modified V' + U' method demonstrated a diagnostic performance comparable to experienced endoscopists. Utilizing the objective index of the PCS could provide valuable support in clinical decision-making.
Collapse
Affiliation(s)
- Kai Liu
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Jiawei Bai
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
- School of Medicine, Yan'an University, Yan'an, China
| | - Li Gao
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Xin Zhao
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Xin Dong
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Hui Chen
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Jiaqiang Dong
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Min Niu
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China
| | - Ying Han
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China.
| | - Zhiguo Liu
- Xijing Hospital of Digestive Diseases, Air Force Medical University (Fourth Military Medical University), 127 Changle West Road, Xi'an, 710032, Shaanxi, China.
| |
Collapse
|
10
|
Leggett CL. Endoscopic screening for oesophageal cancer: empowering artificial intelligence with a high-quality examination. Lancet Gastroenterol Hepatol 2024; 9:4-5. [PMID: 37952556 DOI: 10.1016/s2468-1253(23)00377-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Revised: 10/26/2023] [Accepted: 10/27/2023] [Indexed: 11/14/2023]
Affiliation(s)
- Cadman L Leggett
- Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, MN 55905, USA.
| |
Collapse
|
11
|
Wang Y, Xia Y, Ling D, Sun J, Wang Y. A survival prediction model based on PCA-HSIDA-LSSVM for patients with esophageal squamous cell carcinoma. Proc Inst Mech Eng H 2023; 237:1409-1426. [PMID: 37877733 DOI: 10.1177/09544119231205664] [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] [Indexed: 10/26/2023]
Abstract
Esophageal squamous cell carcinoma (ESCC) is a type of cancer and has some of the highest rates of both incidence and mortality globally. Developing accurate models for survival prediction provides a basis clinical judgment and decision making, improving the survival status of ESCC patients. Although many predictive models have been developed, there is still lack of highly accurate survival prediction models for ESCC patients. This study proposes a novel survival prediction model for ESCC patients based on principal component analysis (PCA) and least-squares support vector machine (LSSVM) optimized by an improved dragonfly algorithm with hybrid strategy (HSIDA). The original 17 blood indicators are condensed into five new variables by PCA, reducing data dimensionality and redundancy. An improved dragonfly algorithm based on hybrid strategy is proposed, which addresses the limitations of dragonfly algorithm, such as slow convergence, low search accuracy and insufficient vitality of late search. The proposed HSIDA is used to optimize the regularization parameter and kernel parameter of LSSVM, improving the prediction accuracy of the model. The proposed model is validated on the dataset of 400 patients with ESCC in the clinical database of First Affiliated Hospital of Zhengzhou University and the State Key Laboratory of Esophageal Cancer Prevention and Control of Henan Province. The experiment results demonstrate that the proposed HSIDA-LSSVM has the best prediction performance than LSSVM, HSIDA-BP, IPSO-LSSVM, COA-LSSVM and IBA-LSSVM. The proposed model achieves the accuracy of 96.25%, sensitivity of 95.12%, specificity of 97.44%, precision of 97.50%, and F1 score of 96.30%.
Collapse
Affiliation(s)
| | | | | | | | - Yan Wang
- School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, China
| |
Collapse
|