{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T11:56:27Z","timestamp":1792410987905,"version":"4.4.0"},"reference-count":37,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Hepatic encephalopathy (HE) contributes significantly to mortality among patients with liver cirrhosis. Early prediction of HE is essential for clinical decision-making, yet remains challenging\u2014particularly in noncancer-related cirrhosis due to the unpredictable disease course.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop a novel machine learning (ML) model to improve early prediction of HE in patients with noncancer-related cirrhosis.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A multicenter, retrospective cohort study was conducted from January 2010 to December 2017 across all Chang Gung Memorial Hospital branches in northern, middle, and southern Taiwan. We applied several ML models to evaluate HE predictability and compared their performance in the training dataset and testing dataset. Optimal sensitivity and specificity were determined using the Youden index. The best ML model was interpreted by the Shapley Additive Explanations plot.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 5878 patients with cirrhosis were included in the analysis, of whom 1187 (20.2%) subsequently developed HE. Compared to the non-HE group, patients with HE were older (median age 55, IQR 46\u201065 vs median age 54, IQR 44\u201066 years;\n P<\/jats:italic>\n =.04) and had higher rates of hepatitis B virus infection (351\/1187, 30% vs 961\/4691, 20.5%;\n P<\/jats:italic>\n <.001), alcohol use (540\/1187, 45.5% vs 1512\/4691, 32.2%;\n P<\/jats:italic>\n <.001), sepsis (393\/1187, 33.1% vs 792\/4691, 16.9%;\n P<\/jats:italic>\n <.001), and mortality (425\/1187, 35.8% vs 502\/4691, 10.7%;\n P<\/jats:italic>\n <.001), along with distinct laboratory abnormalities reflecting liver dysfunction. Among the ML algorithms evaluated, the extreme gradient boosting algorithm demonstrated the highest predictive accuracy, achieving an area under the curve (AUC) of 0.86 (95% CI 0.83\u20100.88) in the testing dataset. This performance was significantly superior to that of the neural network (AUC 0.79, 95% CI 0.76\u20100.81;\n P<\/jats:italic>\n <.001), support vector machine (AUC 0.77, 95% CI 0.73\u20100.80;\n P<\/jats:italic>\n <.001), and the model for end-stage liver disease score (AUC 0.74, 95% CI 0.71\u20100.77;\n P<\/jats:italic>\n <.001). Using a probability threshold of 0.25, the extreme gradient boosting model demonstrated a sensitivity of 72% (95% CI 0.67\u20100.77), specificity of 80% (95% CI 0.78\u20100.82), a positive predictive value of 48% (95% CI 43-53), and a negative predictive value of 92% (95% CI 90-94) in the testing set. Comparable performance was observed in the training dataset, with a sensitivity of 80% (95% CI 0.77\u20100.83), specificity of 81% (95% CI 0.80\u20100.82), and a negative predictive value of 94% at the same threshold. The most influential predictive variables identified by the model included serum ammonia, aspartate transaminase, alanine transaminase, prothrombin time, and serum potassium.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n We developed a novel ML model for predicting HE in patients with noncancer-related cirrhosis. This model provides a practical guide to help physicians and these patients in shared decision-making regarding treatment strategy, with the ultimate goal of improving clinical care and reducing the burden of HE-related morbid complications.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/71229","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T08:30:08Z","timestamp":1750062608000},"page":"e71229-e71229","source":"Crossref","is-referenced-by-count":6,"title":["A Machine Learning\u2013Based Prognostication Model Enhances Prediction of Early Hepatic Encephalopathy in Patients With Noncancer-Related Cirrhosis: Multicenter Longitudinal Cohort Study in Taiwan"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2544-2946","authenticated-orcid":false,"given":"Hsin-Yu","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8740-4682","authenticated-orcid":false,"given":"Yiu-Hua","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9345-4121","authenticated-orcid":false,"given":"Wei-Chung","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7471-6667","authenticated-orcid":false,"given":"Yi-Chuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8191-4036","authenticated-orcid":false,"given":"Yi-Wen","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1016\/S2468-1253(19)30349-8","article-title":"The global, regional, and national burden of cirrhosis by cause in 195 countries and territories, 1990-2017: a systematic analysis for the global burden of disease study 2017","volume":"5","author":"GBD 2017 Cirrhosis Collaborators","journal-title":"Lancet Gastroenterol Hepatol"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-17948-6","article-title":"Global burden of liver cirrhosis and other chronic liver diseases caused by specific etiologies from 1990 to 2019","volume":"24","author":"Wu","journal-title":"BMC Public Health"},{"issue":"12","key":"R3","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1111\/apt.15749","article-title":"Outcomes after hepatic encephalopathy in population-based cohorts of patients with cirrhosis","volume":"51","author":"Tapper","journal-title":"Aliment Pharmacol Ther"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.cld.2020.01.006","article-title":"The health care burden of hepatic encephalopathy","volume":"24","author":"Elsaid","journal-title":"Clin Liver Dis"},{"issue":"10","key":"R5","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1184860","article-title":"Hepatic encephalopathy increases the risk for mortality and hospital readmission in decompensated cirrhotic patients: a prospective multicenter study","volume":"10","author":"Riggio","journal-title":"Front Med (Lausanne)"},{"issue":"8S","key":"R6","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/j.cgh.2022.04.036","article-title":"Changing epidemiology of cirrhosis and hepatic encephalopathy","volume":"20","author":"Louissaint","journal-title":"Clin Gastroenterol Hepatol"},{"issue":"11","key":"R7","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1016\/j.cgh.2018.03.010","article-title":"Factors that affect results of psychometric tests to identify patients with minimal hepatic encephalopathy","volume":"16","author":"P\u00e9rez-Matos","journal-title":"Clin Gastroenterol Hepatol"},{"key":"R8","unstructured":"White paper on palliative and hospice care policy in Taiwan. National Health Research Institutes; 2019. URL: https:\/\/www.nhri.edu.tw\/Files\/2020-02-25-001.pdf [Accessed 19-07-2025]"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1001\/jama.278.2.89","article-title":"The effect of universal health insurance on health care utilization in Taiwan. Results from a natural experiment","volume":"278","author":"Cheng","journal-title":"JAMA"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1377\/hlthaff.22.3.61","article-title":"Taiwan\u2019s new national health insurance program: genesis and experience so far","volume":"22","author":"Cheng","journal-title":"Health Aff (Millwood)"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.4178\/epih.e2018062","article-title":"Data resource profile: the National Health Insurance Research Database (NHIRD)","volume":"40","author":"Lin","journal-title":"Epidemiol Health"},{"issue":"11","key":"R12","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1111\/liv.15684","article-title":"Inequity in end-of-life care for patients with chronic liver disease in England","volume":"43","author":"Woodland","journal-title":"Liver Int"},{"issue":"5","key":"R13","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1111\/liv.13620","article-title":"Palliative care in decompensated cirrhosis: a review","volume":"38","author":"Langberg","journal-title":"Liver Int"},{"issue":"S1","key":"R14","first-page":"S122","volume":"48","author":"Roth","journal-title":"J Am Geriatr Soc"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1053\/he.2000.5852","article-title":"A model to predict poor survival in patients undergoing transjugular intrahepatic portosystemic shunts","volume":"31","author":"Malinchoc","journal-title":"Hepatology"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","journal-title":"J Stat Softw"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","journal-title":"J Stat Softw"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-12-8","article-title":"Predicting sample size required for classification performance","volume":"12","author":"Figueroa","journal-title":"BMC Med Inform Decis Mak"},{"issue":"302","key":"R19","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1080\/14786440009463897","article-title":"On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling","volume":"50","author":"Pearson","journal-title":"Philos Mag (Abingdon)"},{"issue":"6","key":"R20","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","journal-title":"Biometrics Bull"},{"issue":"6","key":"R21","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1016\/s0168-8278(00)80110-5","article-title":"Hepatic encephalopathy in chronic liver disease: a clinical manifestation of astrocyte swelling and low-grade cerebral edema?","volume":"32","author":"H\u00e4ussinger","journal-title":"J Hepatol"},{"issue":"6","key":"R22","doi-asserted-by":"publisher","first-page":"2427","DOI":"10.1097\/MS9.0000000000000470","article-title":"Hypokalemia as a responsible factor related with the severity of hepatic encephalopathy: a wide multination cross-sectional study","volume":"85","author":"Ullah","journal-title":"Ann Med Surg (Lond)"},{"issue":"2","key":"R23","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/s0168-8278(03)00267-8","article-title":"Pathogenesis of hepatic encephalopathy: new insights from neuroimaging and molecular studies","volume":"39","author":"Butterworth","journal-title":"J Hepatol"},{"issue":"41","key":"R24","doi-asserted-by":"publisher","first-page":"11815","DOI":"10.3748\/wjg.v21.i41.11815","article-title":"Inflammation: a novel target of current therapies for hepatic encephalopathy in liver cirrhosis","volume":"21","author":"Luo","journal-title":"World J Gastroenterol"},{"issue":"5","key":"R25","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1007\/s11011-016-9862-6","article-title":"Factors contributing to the development of overt encephalopathy in liver cirrhosis patients","volume":"31","author":"Iwasa","journal-title":"Metab Brain Dis"},{"issue":"5","key":"R26","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1111\/liv.14785","article-title":"Clinical, neuropsychological and neurophysiological indices and predictors of hepatic encephalopathy (HE)","volume":"41","author":"Formentin","journal-title":"Liver Int"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jceh.2023.07.011","article-title":"Integrated unsupervised and supervised machine learning unveils and predicts the Clusters with Distinct Profiles and Survival in Acute-on-Chronic Liver Failure (CLUSTER-ACLF)","volume":"13","author":"Verma","journal-title":"J Clin Exp Hepatol"},{"issue":"10","key":"R28","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1111\/jgh.16645","article-title":"Systematic review of machine learning models in predicting the risk of bleed\/grade of esophageal varices in patients with liver cirrhosis: a comprehensive methodological analysis","volume":"39","author":"Malik","journal-title":"J Gastroenterol Hepatol"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","first-page":"71","DOI":"10.15403\/jgld-5876","article-title":"Machine learning models predicting decompensation in cirrhosis","volume":"34","author":"M\u00fcller","journal-title":"J Gastrointestin Liver Dis"},{"issue":"6","key":"R30","doi-asserted-by":"publisher","first-page":"S","DOI":"10.1016\/S0016-5085(23)04120-3","article-title":"Su1581 prospective validation of a neural network model for the prediction of 1-year mortality in cirrhotic patients with acute esophageal variceal bleeding","volume":"164","author":"Rech","journal-title":"Gastroenterology"},{"issue":"6","key":"R31","doi-asserted-by":"publisher","first-page":"S","DOI":"10.1016\/S0016-5085(21)02602-0","article-title":"590 predicting 30 and 365-day mortality after liver transplantation using a machine learning algorithm","volume":"160","author":"Soldera","journal-title":"Gastroenterology"},{"issue":"211","key":"R32","doi-asserted-by":"publisher","first-page":"106420","DOI":"10.1016\/j.cmpb.2021.106420","article-title":"Using machine learning methods to predict hepatic encephalopathy in cirrhotic patients with unbalanced data","volume":"211","author":"Yang","journal-title":"Comput Methods Programs Biomed"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C . XGBoost: a scalable tree boosting system. Presented at: KDD \u201916: The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Aug 13-17, 2016; San Francisco, CA, United States. [doi: 10.1145\/2939672.2939785]","DOI":"10.1145\/2939672.2939785"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: deep learning is not all you need","volume":"81","author":"Shwartz-Ziv","journal-title":"Inform Fusion"},{"key":"R35","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: Proceedings of the 31st International Conference on Neural Information Processing Systems; Dec 4-9, 2017:4768-4777; Long Beach, CA, United States."},{"issue":"4","key":"R36","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1002\/hep.29628","article-title":"A risk score to predict the development of hepatic encephalopathy in a population-based cohort of patients with cirrhosis","volume":"68","author":"Tapper","journal-title":"Hepatology"},{"issue":"12","key":"R37","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.14309\/ajg.0000000000000762","article-title":"Incidence and bedside predictors of the first episode of overt hepatic encephalopathy in patients with cirrhosis","volume":"115","author":"Tapper","journal-title":"Am J Gastroenterol"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e71229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:00:26Z","timestamp":1782842426000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e71229"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.2196\/71229","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,6]]},"article-number":"v13i1e71229"}}