Title: Gastroenterology in the Age of AI: Bridging Technology and Clinical Practice Yagna Mehta, Saumya Mehta, Vishwa Bhayani, Sankalp Parikh, Rajiv Mehta Abstract Integrating artificial intelligence (AI), deep learning, and radiomics is rapidly transforming gastroenterology and hepatology. Advanced technologies, including convolutional neural networks (CNN), recurrent neural networks (RNN), transformers, artificial neural networks (ANN), and support vector machines, are advancing medical research and clinical practice. This review delves into the various applications of AI in Gastroenterology and Hepatology, focusing on patient data management, the development of disease algorithms, and literature mining. Notably, AI - driven computational chemistry is making significant strides in drug discovery, helping to speed up processes like hit identification, lead optimization, and formulation development. With the aid of advanced machine learning algorithms, it ’ s now possible to predict molecular interactio ns and optimize drug - target binding, enhancing the screening efficiency of potential candidates with remarkable precision. AI models play a crucial role in structure - based drug design (SBDD), molecular docking, and pharmacokinetics (ADMET) simulations, whi ch ultimately helps reduce both the time and cost typically linked with conventional experimental approaches. Furthermore, AI - driven predictive analytics offer improvements in excipient selection, stability, and bioavailability, which accelerates the creat ion of optimized drug formulations. The advancements in computer vision (CV), fueled by deep learning, are also transforming ambient intelligence (AmI), contributing to better interpretation of endoscopic images, providing real - time procedural guidance, an d enabling autonomous monitoring systems. In the realm of personalized medicine, AI - based predictive algorithms are enhancing treatment strategies, especially for inflammatory bowel disease (IBD), by anticipating responses to various therapies. AI - enabled remote monitoring is proving to be invaluable for managing high - risk patients, such as those dealing with acute - on - chronic liver failure (ACLF), recent liver transplant recipients, and cirrhotic patients requiring tailored diuretic dosing. Despite its vast potential, AI adoption in gastroenterology faces challenges, including data standardization, ethical considerations, model biases, and privacy concerns. Specifically, privacy concerns include ensuring HIPAA compliance and GDPR adherence. Establishing norm ative standards for data collection, labeling, storage, and processing is essential. Multi - center, high - quality, large - sample databases are needed to drive AI innovation and facilitate data sharing. Furthermore, developing specialized regulatory guidelines will ensure AI ’ s safe and effective clinical integration. Key words: Artificial Intelligence ; Gastroenterology ; Predictive Analytics ; Endoscopy ; Drug Discovery ; Personalized Medicine ; Remote Monitoring Core Tip: Artificial Intelligence (AI) is res haping gastroenterology by improving diagnostic accuracy, supporting personalized treatment, and accelerating drug discovery. This review highlights the integration of AI technologies — such as machine learning, deep learning, convolutional neural networks ( CNNs), and natural language processing (NLP) — into various aspects of gastroenterology and hepatology. Key applications include real - time polyp detection during endoscopy, prediction of disease progression in inflammatory bowel disease, and early risk strat ification in acute pancreatitis. AI is also advancing drug repurposing and de novo molecule design, while assisting in excipient selection and ADMET profiling through computational chemistry. In hepatology, AI enables remote monitoring of patients with cir rhosis and liver failure, and supports clinical decision - making via AI - assisted tumor boards. Additionally, platforms like GastroAGI demonstrate AI ’ s potential in medical education. Despite its promise, challenges such as data quality, model interpretabili ty, ethical use, and clinical validation must be addressed. AI ’ s successful integration into clinical practice will require collaboration among clinicians, data scientists, and regulatory stakeholders. Introduction Artificial Intelligence is reshaping g astroenterology and hepatology by enabling data - driven, precise, and efficient clinical decision - making across the continuum of care. Leveraging machine learning (ML), deep learning (DL), convolutional and recurrent neural networks (CNNs and RNNs), natural language processing (NLP), and large language models (LLMs), AI can interpret complex datasets including electronic health records (EHRs), endoscopic images, capsule endoscopy videos, and genomic or proteomic data. These tools enhance lesion detection, au tomate report generation, and improve disease classification. AI also supports predictive modeling to forecast disease progression and therapeutic response, enabling personalized treatment strategies in conditions like inflammatory bowel disease and chroni c liver disease. In drug discovery, AI accelerates the identification of novel therapeutic targets and facilitates drug repurposing by modeling molecular interactions and clinical outcomes. Remote monitoring technologies integrated with AI — such as wearable biosensors — allow real - time tracking of patient parameters, optimizing management of cirrhosis, acute - on - chronic liver failure (ACLF), and liver transplantation recipient . Furthermore, AI enables continuous assessment of treatment efficacy, guiding timely dose adjustments and improving safety profiles. By streamlining workflows, enhancing diagnostic accuracy, and supporting therapeutic innovation, AI is poised to transform the future of gastrointestinal and hepatic care. AI in Patient Data and Clinical App lications Big Data in Gastroenterology The advent of big data has transformed gastroenterology by enabling the integration and analysis of large - scale, heterogeneous datasets derived from electronic medical records, endoscopic imaging, laboratory tests, and multi - omics platforms. Powered by AI / ML, big data facilitates real - time lesion detection, automated disease classification, and predictive modeling for outcomes such as cancer risk or treatment response. Integration of genomic, proteomic, and metabolom ic data supports precision medicine, while clinical decision support systems enhance diagnostic accuracy and reduce human error. In drug discovery, big data accelerates biomarker identification, phenomapping, and post - marketing safety surveillance. Despite its promise, challenges remain, including data quality variability, privacy concerns, and the need for sophisticated analytic tools and interdisciplinary collaboration. As these hurdles are addressed, big data will continue to advance personalized care, r eal - time monitoring, and population - level health strategies in gastroenterology. Predictive Analytics for Patient Outcomes Predictive analytics in gastroenterology harnesses AI to evaluate disease trajectories, forecast therapeutic efficacy, and stratify patients by complication risk. In hepatology, AI models accurately predict liver disease severity, progression of non - alcoholic fatty liver disease (NAFLD), and decompensation risk in cirrhosis. In inflammatory bowel disease (IBD), machine learning algori thms analyze clinical, laboratory, and imaging data to anticipate treatment responses to biologics or small molecules, enabling precision therapy and minimizing ineffective drug exposure. AI is also valuable in acute pancreatitis, where early prediction of disease severity within the first 12 hours of hospitalization facilitates prompt escalation of care. These models rely on high - dimensional data inputs, including serologic markers, imaging features, and genomic profiles, to deliver individualized, actiona ble insights that enhance clinical decision - making and optimize patient outcomes. Real - time Decision Support Systems AI has become integral to real - time decision support systems (DSS) in gastroenterology and hepatology, enhancing diagnostic precision, op timizing therapeutic strategies, and streamlining clinical workflows. Leveraging various technologies , AI enables dynamic interpretation of complex clinical, imaging, and procedural data. In endoscopy, AI facilitates real - time polyp detection, dysplasia lo calization in Barrett ’ s esophagus, and automated analysis of capsule endoscopy, thereby improving lesion detection rates and procedural quality. In hepatology, AI supports real - time fibrosis assessment via ultrasound elastography and predicts acute - on - chro nic liver failure (ACLF) progression at admission. Integrated into electronic health records (EHRs), AI models anticipate complications like bleeding or decompensation, enabling proactive management. Additionally, NLP systems automate structured reporting, and radiomics and radiogenomics inform tumor behavior and therapy response in hepatocellular carcinoma. Collectively, AI - driven DSS empower clinicians with actionable insights at the point of care, reducing variability, improving outcomes, and enhancing o perational efficiency. Algorithmic Approach to Gastrointestinal Diseases Machine Learning Models for Disease Diagnosis Machine learning (ML) has significantly advanced diagnostic capabilities in gastroenterology by analyzing structured and unstructured data to uncover patterns, stratify risk, and support clinical decisions. (1) For example, in pancreatic disorders, ML models such as gradient boosting machines (GBM) and support vector machines (SVM) effectively distinguish benign from malignant cystic lesions, aiding in surgical decision - making and reducing overtrea tment. (2,3) In the management of inflammatory bowel disease (IBD), ML algorithms incorporate endoscopic, imaging, and serological data to predict disease severity and flare risk, facilitating personalized care. (4) Ensemble models like XGBoost have demonstrated up to 9 0 % accuracy in identifying high - risk patients for upper GI lesions, including early gastric cancer, based on clinical and pathological inputs. (5) C onvolutional neural networks (CNNs) play a vital role in diagnostic tasks, particularly for image - based classification (6) Additionally, explainable AI (XAI) frameworks enhance s transparency and strengthen clinical trust in diagnostic process aiding in an informed decision making. (7) . These technologies collectively imp rove diagnostic accuracy, reduce interobserver variability, standardize diagnostic criteria, and streamline complex data analysis — laying the foundation for precision medicine in gastroenterology. AI for Personalized Medicine AI is rapidly transforming personalized care by enhancing therapeutic precision, treatment responsiveness, and long - term disease management in gastroenterology. (8) In inflammatory bowel disease (IBD), AI algorithms forecast patient response s to biologics and small molecules using clinical, genetic, and imaging - derived features, reducing empirical treatment selection and minimizing adverse effects. (4) Advances in AI are transforming microbiome - targeted interventions by identifying dysbiosis patterns that predict therapeutic outcomes. (9) This technology plays an important role in enhancing the success of interventions such as fecal microbiota transplantation (FMT) , and probiotics in IBD for irritable bowel syndrome (IBS). (10,11) Real - time integration of data from wearable devices and electronic health records (EHRs) allows for dynamic treatment adjustments based on patient - reported outcomes and biom etric trends, particularly valuable in chronic conditions like IBD and acute pancreatitis. (12) Furthermore, AI leverages multi - omics datasets — including genomics, proteomics, and metabolomics — to develop precision therapy frameworks, such as tailoring hepatocellular carcinoma treatment based on radiogenomic signatures. (13) Remote Monitoring & Telemedicine The integration of artificial intelligence (AI) into telemedicine is set to revoluti onized remote monitoring in gastroenterology, particularly for chronic conditions requiring continuous follow - up. (14) AI - powered virtual assistants facilitate symptom tracking, medication adherence, and personalized lifestyle recommendations, enhancing disease control in inflammatory bowel disease (IBD) and reducing hospital visits (15) In hepatology, AI - enhanced devices ( w earable biosensors, paired with real - time AI analytics ) monitor vital signs and liver - specific biomarkers in patients with acute - on - chronic liver failure (ACLF), enabling timely intervention and avoiding late ICU admissions. (12) Similarly, continuous analysis of physiological trends supports titration of diuretics and beta - blockers in cirrhosis and portal hypertension. AI also enables remote assessment of n utritional status and sarcopenia through analysis of muscle mass and metabolic indicators, particularly relevant in liver disease management. (16 ,17) Beyond clinical applications, AI - integrated telemedicine improves patient satisfaction, reduces healthcare costs, enhances accessibility to specialized care, and streamlines workflows by automating routine tasks. (18) AI - Based Tumor Boards: Streamlining Complex Cancer Care Complex gastrointestinal cancers often require input from multidisciplinary tumor boards comprising surgeons, oncologists, radiologists, pathologists, and gastroenterologists to formulate optimal treatment strategies. While indispensable, these meetings can be tim e - consuming and resource - intensive. AI - powered platforms offer a scalable solution by integrating patient demographics, clinical history, imaging, pathology, and genomic data to generate evidence - based, personalized treatment recommendations. (1 9) These systems align therapeutic decisions with established guidelines and emerging research, thereby expediting clinical workflows and improving access to expert - level care, especially in resource - limited or remote settings. Although not a substitute for human expertise, AI - assisted tumor boards can augment multidisciplinary discussions, ensure consistency in care delivery, and continuously adapt as new evidence emerges. (20) This approach repres ents a paradigm shift in gastrointestinal oncology, enhancing precision, efficiency, and equity in cancer care. AI in Gastroenterology Education and Research GastroAGI: AI - Powered Learning in Gastroenterology GastroAGI, developed by YRaM Biosolutions , an India - based AI startup ( https://gastroagi.com ) , is a valuable tool designed to aid students and researchers in gastroenterology. This AI - powered platform offers in - depth educational resources, interactive learnin g modules, and real - time access to updated medical literature. By leveraging machine learning algorithms, GastroAGI customizes learning pathways based on user engagement, providing tailored recommendations on research articles, case studies, and clinical g uidelines. It enables postgraduate students and trainees to streamline their academic pursuits, making it an essential resource for evidence - based learning in gastroenterology. AI Integration in Drug Discovery AI is revolutionizing drug discovery in gastroenterology by accelerating the identification of novel chemical entities (NCEs) and enabling the repurposing of existing drugs for complex diseases such as idiopathic pancreatitis and inflammatory bowel disease (I BD). In de novo drug design, deep learning tools such as AlphaFold2 predict protein structures with remarkable accuracy, supporting the development of targeted therapies for gastrointestinal malignancies. Generative models are also utilized to assess effic acy and toxicity profiles in early - stage compounds, significantly reducing late - stage attrition in clinical pipelines. Furthermore, AI enhances safety by predicting drug - drug interactions in polypharmacy scenarios, particularly relevant for cirrhosis and p ortal hypertension management. Beyond discovery, AI contributes substantially to formulation science by identifying optimal excipients through computational chemistry. ML algorithms evaluate the compatibility and molecular interactions between active pharm aceutical ingredients (APIs) and excipients, optimizing solubility, stability, and bioavailability — especially critical for poorly soluble drugs. In parallel, AI is increasingly applied to predict ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties with high precision. By integrating physicochemical, structural, and biological datasets, these models provide early pharmacokinetic and safety profiles, enabling more informed candidate selection. Collectively, these AI - driven innovat ions are streamlining drug development and formulation, paving the way for personalized and precision - based therapeutics in gastroenterology. Role of AI in Endoscopy Diagno stic Endoscopy Recent breakthroughs in computer vision, powered by deep learning, are driving the evolution of ambient intelligence (AmI) in healthcare environments. In gastrointestinal endoscopy, these advances enable more sophisticated and accurate interpretation of endoscopic images. AI - powered systems, especially computer - aided de tection (CADe) and diagnosis (CADx), utilize convolutional neural networks (CNNs) to identify lesions such as colorectal polyps, early gastric cancer, and Barrett ’ s esophagus with high sensitivity. Tools like EndoAngel have demonstrated diagnostic accuracy exceeding 90% for early gastric cancers and have notably reduced missed anatomical sites. In inflammatory bowel disease (IBD), AI supports automated scoring of mucosal inflammation in ulcerative colitis and enables accurate interpretation of capsule endos copy in Crohn ’ s disease, thus facilitating timely diagnosis and disease monitoring. Therapeutic Endoscopy In therapeutic endoscopy, AI aids in real - time procedural decision - making. Post - endoscopic mucosal resection (EMR) or endoscopic submucosal dissecti on (ESD), AI can assess residual neoplastic tissue, helping confirm procedural completeness and reduce recurrence. In complex procedures such as ERCP or EUS, AI enhances anatomical navigation, especially in mediastinal regions, improving outcomes in challe nging scenarios like biliary strictures or pancreatic lesions. Moreover, AI - based risk stratification tools assist in determining malignancy potential in indeterminate lesions, guiding biopsy decisions and treatment strategies. Advanced Features AI contri butes to procedural standardization and quality control by monitoring withdrawal speed, bowel preparation, and completeness of mucosal inspection. It provides real - time alerts for blind spots or missed areas, ensuring thorough examinations. In endoscopy tr aining, AI simulators offer interactive guidance, improving novice skill acquisition. Furthermore, AI automates structured reporting and image documentation, optimizing workflow. As validation continues, AI is set to become integral to endoscopy, bridging precision with efficiency in clinical practice. Challenges of AI Adoption in Healthcare Despite its transformative potential, the adoption AI in healthcare — including gastroenterology and hepatology — faces several significant challenges. Data heterogeneity, poor interoperability, and lack of high - quality, standardized datasets hinder model training and generalizability. Privacy concerns governe d by regulations such as HIPAA and GDPR complicate data sharing, while high computational costs and limited infrastructure pose barriers, particularly in resource - constrained settings. Bringing AI into regular clinical use takes time because it must first be carefully tested through studies and clinical trials to prove it is safe and effective. There are also ethical concerns, such as the risk of bias in algorithms, lack of transparency in how AI makes decisions (often referred to as the “ black box ” problem ), and unequal access to these technologies (democratizing AI) In addition, keeping AI systems updated and supported over the long term can be challenging, especially in settings with limited budgets. Resistance from clinicians, often due to workflow dis ruption and scepticism toward AI - driven decisions, necessitates cultural change and targeted training. Additionally, regulatory uncertainty around liability and approval pathways slows commercialization. Overcoming these barriers requires collaborative eff orts to standardize data, invest in secure and scalable infrastructure, streamline validation, and embed ethical, regulatory, and educational frameworks into AI deployment strategies. Addressing these issues is essential to unlock AI ’ s full potential in de livering equitable, efficient, and evidence - based care in gastroenterology and beyond. Conclusion The integration of AI , in gastroenterology has marked the beginning of a transformative era in precision medicine, delivering significant advances in diagnostics, therapeutic planning, medical education, and multidisciplinary cancer care. AI - powered tools — ranging from predictiv e models and endoscopic image analysis to computational drug discovery and personalized treatment algorithms including remote monitoring — are redefining the clinical approach to complex gastrointestinal and hepatic disorders. Real - world applications, such a s predicting the severity of acute pancreatitis and forecasting treatment response in inflammatory bowel disease (IBD), underscore the tangible impact of AI on patient outcomes. However, to fully realize these benefits, several challenges must be addressed , including data privacy, ethical considerations, the interpretability of AI models, and the need for robust clinical validation. Ensuring transparency in AI decision - making is essential to build clinician trust, while rigorous trials are needed to verify safety, reliability, and generalizability. Protecting patient data and ensuring equitable access to AI technologies remain critical priorities. Moving forward, successful and responsible adoption of AI will require sustained interdisciplinary collaboration among clinicians, data scientists, regulatory authorities, and ethicists. With thoughtful implementation, continuous evaluation, and adherence to ethical standards, AI holds the potential to enhance clinical care, improve patient outcomes, and bring scala ble innovation to every level of gastroenterology practice. The future is promising — but must be navigated with diligence, equity, and scientific rigor. References for introduction 1. Sharma S, et al. Role of artificial intelligence in gastrointestinal surge ry. World J Gastrointest Surg. 2024;5(2):97317. 2. Karger Publishers. Article Collection: Artificial Intelligence in Gastroenterology. 2024. 3. Bal T. A New Tool for the Diagnosis and Management of Viral Hepatitis: Artificial Intelligence. Viral Hepat Derg. 2024 ;30(1):1 - 10. 4. Emerging Applications of NLP and Large Language Models in Gastroenterology and Hepatology. medRxiv. 2024. 5. Dahiya DS, et al. Artificial Intelligence and the Future of Gastroenterology and Hepatology. J Clin Gastroenterol. 2022;56(5):377 - 386. 6. Di agnostic Accuracy of Artificial Intelligence for Detecting Gastroenterological Pathologies: A Systematic Review and Meta - Analysis. SSRN. 2022. 7. Xiao Y, et al. Artificial intelligence in gastroenterology: Ethical and diagnostic implications. World J Gastroen terol. 2025;31(10):102725. 8. Chen Y, Shen Z. Artificial Intelligence Enhances Studies on Inflammatory Bowel Disease. World J Gastroenterol. 2021;27(26):4233 - 4245. 9. AI - designed drug candidate shows promise for gastric acid inhibition. News - Medical. 20 Referen ces for AI data and clinical applications 1. Cheung KS, Leung WK, Seto WK. Application of Big Data analysis in gastrointestinal research. World J Gastroenterol. 2019;25(24):2990 - 3008. Discusses how big data enables phenomapping, precision medicine, drug safety, and post - marketing surveillance in GI, while also addressing challenges like data validity, privacy, and analytic complexity. 2. ‘ Big data ’ can revolutionize gastroenterology. MDLinx, 2024. Reviews how big data and AI/ML are revolutionizing GI by integrating multi - omics, imaging, and EHRs to improve diagnostics, precision medicine, and personalized care, while noting the need for data quality and privacy protections. 3. Artificial intelligence in gastroenterology: Ethical and diagnostic implication s. World J Gastroenterol. 2025;31(10):102725. Illustrates how AI leverages large, heterogeneous datasets (including omics and imaging) for precision diagnostics, predictive modeling, and real - time clinical decision support, while highlighting ethical and o perational challenges. 4. Application of artificial intelligence in gastroenterology. PMC, 2019. Reviews AI/ML applications for diagnosis, prognosis, and outcome prediction in GI, including ANN models for disease classification and risk prediction using cl inical, demographic, and laboratory data. 5. Siemens Healthineers. Prediction and Early Identification of Disease Through AI, 2021. Describes the development of AI - based predictive models for early identification and management of liver disease, integrated into EHRs for real - time risk stratification and proactive care. 6. Combining explainable machine learning, demographic and multi - modal data to predict drug response in IBD. PLOS ONE, 2022. Presents an explainable ML approach integrating multi - omic, demogr aphic, and pharmacological data to predict individualized drug response in IBD, supporting precision therapy and biomarker discovery. 7. Artificial intelligence in gastroenterology: Ethical and diagnostic implications. World J Gastroenterol. 2025;31(10):10 2725. Discusses the integration of AI into real - time DSS for endoscopy, fibrosis assessment, and structured reporting, emphasizing improved workflow efficiency and diagnostic accuracy. Reference Algorithmic Approach to Gastrointestinal Diseases 1. Kim HJ, Gong EJ, Bang CS. Application of Machine Learning Based on Structured Medical Data in Gastroenterology. Biomimetics. 2023 Nov;8(7):512. 2. Vasudevan B, SenthilKumaran R , Immanuel K, Karthikeyan MV. Non Invasive Early Pancreatic Cancer Prediction with Gradient Boosting Algorithms Machine Learning Models with Clinical dataset collected from Urinary Biomarkers. In: 2024 International Conference on Advances in Computing, Com munication and Applied Informatics (ACCAI) [Internet]. 2024 [cited 2025 Apr 13]. p. 1 – 6. Available from: https://ieeexplore.ieee.org/abstract/document/10602237 3. Jiang J, Chao WL, Culp S, Krishna SG. Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma. Cancers. 2023 Jan;15(9):2410. 4. Javaid A, Shahab O, Adorno W, Fernandes P, May E, Syed S. Machine Learning Predictive Outcomes Modeling in Inflammatory Bowel Diseases. Inflamm Bowel Dis. 2022 Jun 1;28(6):8 19 – 29. 5. Ke X, Cai X, Bian B, Shen Y, Zhou Y, Liu W, et al. Predicting early gastric cancer risk using machine learning: A population - based retrospective study. Digit Health. 2024 Sep 1;10:20552076241240905. 6. Yadav SS, Jadhav SM. Deep convolutional ne ural network based medical image classification for disease diagnosis. J Big Data. 2019 Dec 17;6(1):113. 7. Adeniran AA, Onebunne AP, William P. Explainable AI (XAI) in healthcare: Enhancing trust and transparency in critical decision - making. World J Adv Res Rev. 2024;23:2647 – 58. 8. Faiz A, Aisyah N, Hafiz M, Zulaikha S, Yusof ZB, Hakimi I. Evaluating the Role of Artificial Intelligence in Enhancing Diagnostic Accuracy and Personalized Treatment of Gastrointestinal and Hepatobiliary Diseases. 9. Shukla V , Singh S, Verma S, Verma S, Rizvi AA, Abbas M. Targeting the microbiome to improve human health with the approach of personalized medicine: Latest aspects and current updates. Clin Nutr ESPEN. 2024 Oct 1;63:813 – 20. 10. Khan R, Roy N, Ali H, Naeem M. Feca l Microbiota Transplants for Inflammatory Bowel Disease Treatment: Synthetic - and Engineered Communities - Based Microbiota Transplants Are the Future. Gastroenterol Res Pract. 2022;2022(1):9999925. 11. Das A, Behera RN, Kapoor A, Ambatipudi K. The Potentia l of Meta - Proteomics and Artificial Intelligence to Establish the Next Generation of Probiotics for Personalized Healthcare. J Agric Food Chem. 2023 Nov 22;71(46):17528 – 42. 12. Chong KP, Woo BK. Emerging wearable technology applications in gastroenterolog y: A review of the literature. World J Gastroenterol. 2021 Mar 28;27(12):1149 – 60. 13. Ao L, Song X, Li X, Tong M, Guo Y, Li J, et al. An individualized prognostic signature and multi - omics distinction for early stage hepatocellular carcinoma patients with surgical resection. Oncotarget. 2016 Mar 19;7(17):24097 – 110. 14. Aldzhyan V, Tamamian C, Tabibian JH. Leveraging telemedicine in gastroenterology and hepatology: a narrative review. mHealth. 2023 Oct 16;9:36. 15. Majidova K, Handfield J, Kafi K, Martin RD, Kubinski R. Role of Digital Health and Artificial Intelligence in Inflammatory Bowel Disease: A Scoping Review. Genes. 2021 Sep 22;12(10):1465. 16. Kumar R, Prakash SS, Priyadarshi RN, Anand U. Sarcopenia in Chronic Liver Disease: A Metabolic Perspect ive. J Clin Transl Hepatol. 2022 Dec 28;10(6):1213 – 22. 17. Turimov Mustapoevich D, Kim W. Machine Learning Applications in Sarcopenia Detection and Management: A Comprehensive Survey. Healthcare. 2023 Sep 7;11(18):2483. 18. Mbanugo OJ. AI - Enhanced Teleme dicine: A Common - Sense Approach to Chronic Disease Management and a Tool to Bridging the Gap in Healthcare Disparities. Dep Healthc Manag Inform Coles Coll Bus Kennesaw State Univ Ga USA [Internet]. [cited 2025 Apr 14]; Available from: https://www.research gate.net/profile/Olu - Mbanugo/publication/389262394_AI - Enhanced_Telemedicine_A_Common - Sense_Approach_to_Chronic_Disease_Management_and_a_Tool_to_Bridg ing_the_Gap_in_Healthcare_Disparities/links/67bb29caf5cb8f70d5bd5c07 /AI - Enhanced - Telemedicine - A - Common - Sens e - Approach - to - Chronic - Disease - Management - and - a - Tool - to - Bridging - the - Gap - in - Healthcare - Disparities.pdf 19. Parekh ADE, Shaikh OA, Simran, Manan S, Hasibuzzaman MdA. Artificial intelligence (AI) in personalized medicine: AI - generated personalized therapy reg imens based on genetic and medical history: short communication. Ann Med Surg. 2023 Sep 13;85(11):5831 – 3. 20 Nardone V, Marmorino F, Germani MM, Cichowska - Cwalińska N, Menditti VS, Gallo P, et al. The Role of Artificial Intelligence on Tumor Boards: Pers pectives from Surgeons, Medical Oncologists and Radiation Oncologists. Curr Oncol. 2024 Sep;31(9):4984 – 5007. References for Role of AI in education and Research 1. Ahmad OF, et al. Artificial intelligence in gastroenterology: A state - of - the - art review. World J Gastroenterol . 2021;27(40):6738 - 6753 2. Vo,A.H.,VanVleet,T.R.,Gupta,R.R.,Liguori,M.J.&Rao,M.S.Anovervi ewofmachinelearningandbigdatafordrugtoxicity evaluation. Chem. Res. Toxicol. 33, 20 – 37 (2020). 3. Lee,C.Y.&Chen,Y.P.P.Predictionofdrugadverseeventsusingdeeple arninginpharmaceuticaldiscovery. Brief.Bioinform. 22, 1884 – 1901 (2021) 4. Julia Yuen Hang Liu John A. Rudd. Predicting drug adverse effects using a new Gastro - Intestinal Pacemaker Activity Drug Datab ase (GIPADD). Scientific Reports. (2023) 13:6935 References for role of AI in Endoscopy 1. Hassam Ali , Muhammad Ali Muzammil , Dushyant Singh Dahiya , Farishta Ali , Shafay Yasin , Waqar Hanif , Manesh Kumar Gangwani Muhammad Aziz , Muhammad Khalaf , Debargha Basuli , Mohammad Al - Haddad Artificial intelligence in gastrointestinal endoscopy: a comprehensive review. Ann Gastroenterol. 2024 Feb 14;37(2):133 – 141 2. Okagawa Y, Abe S, Yamada M, Oda I, Saito Y. Artificial intelligence in endoscopy. Dig Dis Sci. 2022;67:1553 – 1572. 3. El Hajjar A, Rey J F. Artificial intelligence in gastrointestinal endoscopy: general overview. Chin Med J (Engl) 2020;133:326 – 334. 4. Luo H, Xu G, Li C, et al. Real - time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case - con trol, diagnostic study. Lancet Oncol. 2019;20:1645 – 1654. 5. Byrne MF, Chapados N, Soudan F, et al. Real - time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut. 2019;68:94 – 100. 6. Hassan C, Spadaccini M, Iannone A, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta - analysis. Gastrointest Endosc. 2021;93:77 – 85. Challenges of AI adoption in Health Care 1. Molla Imaduddin Ahmed , Brendan Spooner , John Isherwood , Mark Lane , Emma Orrock , Ashley Dennison . A Systematic Review of the Barriers to the Implementation of Artificial Intelligence in Healthcare. Cureus . 2023 Oct 4 ;15(10):e46454 2. Jaremko JL, Azar M, Bromwich R, et al : Canadian Association of Radiologists White Paper on Ethical and Legal Issues Related to Artificial Intelligence in Radiology. Can Assoc Radiol J 70(2):107 - 118, 2019 3. He J, Baxter SL, Xu J, Xu J, Zhou X, Zhang K : The practical implementation of artificial intelligence technologies in medicine. Nat Med 25(1):30 - 36, 2019 World J of Gastroenterology Bureau C, Garcia - Pagan JC, Otal P, Pomier - Layrargues G, Chabbert V, Cortez C, Perreault P, Péron JM, Abraldes JG, Bouchard L, Bilbao JI, Bosch J, Rousseau H, Vinel JP. Improved clinical outcome using polytetrafluoroethylene - coated stents for TIPS: results of a randomized study. Gastroenterology. 2004;126:469 - 475. [ RCA] [ PubMed] [DOI] [Full Text] [Cited in This Article: 1] [Cited by in Crossref: 370] [Cited by in RCA: 315] [Article Influence: 15.0] [Reference Citation Analysis (0)]