{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:05:02Z","timestamp":1782846302689,"version":"3.54.5"},"reference-count":29,"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 Predicting mortality among people living with HIV enables clinicians to implement timely, targeted, and preventive interventions at the start of antiretroviral therapy (ART). However, prognostic models must rely strictly on baseline predictors to avoid look-ahead bias and ensure scientific validity. This study evaluates machine-learning (ML) algorithms for baseline mortality prediction using routine electronic medical record data.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to predict mortality among people living with HIV receiving ART using baseline clinical and sociodemographic characteristics through ML models in public health facilities of Gondar City Administration, Northwest Ethiopia.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The retrospective cohort study was conducted using electronic medical record data from 12,871 people living with HIV on ART (2005\u20102024). Seven base classifiers were evaluated using stratified 10-fold cross-validation. Synthetic minority oversampling technique (SMOTE)\u2013balanced variants were used only for sensitivity analysis. SMOTE oversampling was applied only to training folds; the final evaluation used the original imbalanced test data. Shapley Additive Explanations (SHAP) analysis identified key baseline predictors.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Gradient boosting on the original data achieved superior performance (accuracy 87.0%,\n F<\/jats:italic>\n 1<\/jats:sub>\n -score 0.619, area under the receiver operating characteristic curve 0.859), outperforming extreme gradient boosting (\n F<\/jats:italic>\n 1<\/jats:sub>\n -score 0.609, area under the receiver operating characteristic curve 0.835) and SMOTE variants. The SHAP analysis identified education level, lack of formal education (+0.84), and a low baseline cluster of differentiation 4 (CD4; a type of immune cell count) count of 140 cells\/mm\u00b3 (+0.54) as substantially increasing predicted mortality risk. Urban residence (\u22120.35) and working functional status (\u22120.12) showed protective effects, whereas age (45 y; \u22120.02) had minimal influence in the illustrated case. Globally, lower CD4 counts and the absence of formal education were consistently associated with increased mortality risk.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Ensemble ML models demonstrated moderate-to-strong discrimination for predicting mortality among people living with HIV using strictly baseline routine electronic medical record data. SHAP-based interpretability confirmed that educational attainment and baseline CD4 count were the dominant determinants of predicted mortality risk, underscoring the combined influence of socioeconomic vulnerability and immunological status at ART initiation. These findings support the potential utility of interpretable ML models for early risk stratification and targeted clinical decision-making in resource-limited settings; however, external validation is required before routine clinical implementation.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/78770","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T18:08:23Z","timestamp":1776708503000},"page":"e78770-e78770","source":"Crossref","is-referenced-by-count":0,"title":["Mortality Prediction Among People Living With HIV on Antiretroviral Therapy in Public Health Facilities in Gondar City Administration, Northwest Ethiopia: Machine Learning\u2013Based Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7195-1278","authenticated-orcid":false,"given":"Andualem Enyew","family":"Gedefaw","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2315-7495","authenticated-orcid":false,"given":"Getaye Tizazu","family":"Biwota","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7176-9447","authenticated-orcid":false,"given":"Abraraw Gebre","family":"Mesele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0014-2242","authenticated-orcid":false,"given":"Abraham Keffale","family":"Mengistu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8187-2366","authenticated-orcid":false,"given":"Gizaw Hailiye","family":"Teferi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.2196\/68225","article-title":"Machine learning models to predict risk of maternal morbidity and mortality from electronic medical record data: scoping review","volume":"27","author":"Vasudevan","journal-title":"J Med Internet Res"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.2196\/65708","article-title":"Federated learning-based model for predicting mortality: systematic review and meta-analysis","volume":"27","author":"Tahir","journal-title":"J Med Internet Res"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","DOI":"10.2196\/33182","article-title":"Machine learning-based short-term mortality prediction models for patients with cancer using electronic health record data: systematic review and critical appraisal","volume":"10","author":"Lu","journal-title":"JMIR Med Inform"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","DOI":"10.2196\/23458","article-title":"Using automated machine learning to predict the mortality of patients with COVID-19: prediction model development study","volume":"23","author":"Ikemura","journal-title":"J Med Internet Res"},{"issue":"11","key":"R5","doi-asserted-by":"publisher","DOI":"10.2196\/24018","article-title":"Machine learning to predict mortality and critical events in a cohort of patients with COVID-19 in New York City: model development and validation","volume":"22","author":"Vaid","journal-title":"J Med Internet Res"},{"issue":"4","key":"R6","doi-asserted-by":"publisher","DOI":"10.2196\/24996","article-title":"Machine learning-driven models to predict prognostic outcomes in patients hospitalized with heart failure using electronic health records: retrospective study","volume":"23","author":"Lv","journal-title":"J Med Internet Res"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1186\/s40635-025-00765-5","article-title":"Explainable machine learning models for mortality prediction in patients with sepsis in tertiary care hospital ICU in low- to middle-income countries","volume":"13","author":"Diwan","journal-title":"Intensive Care Med Exp"},{"key":"R8","unstructured":"Global HIV & AIDS statistics \u2014 Fact sheet. UNAIDS. URL: https:\/\/www.unaids.org\/en\/resources\/fact-sheet [Accessed 14-04-2026]"},{"issue":"4","key":"R9","volume":"32","author":"Kloos","journal-title":"Ethiop J Health Dev"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Vitalis D . Adherence to Antiretroviral Therapy among Perinatal Women in Guyana: Challenges and Lessons for Developing Nations. Springer; 2021:183-199. [doi: 10.1007\/978-981-15-3974-9]","DOI":"10.1007\/978-981-15-3974-9_7"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-024-10225-2","article-title":"Survival and predictors of mortality among HIV-infected adults after initiation of antiretroviral therapy in Eastern Ethiopia Governmental hospitals, from January 2015 to December 2021 (multi-center retrospective follow-up study)","volume":"24","author":"Argaw","journal-title":"BMC Infect Dis"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02167-7","article-title":"Machine learning to predict virological failure among HIV patients on antiretroviral therapy in the University of Gondar Comprehensive and Specialized Hospital, in Amhara Region, Ethiopia, 2022","volume":"23","author":"Mamo","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cell.2020.03.022","article-title":"How machine learning will transform biomedicine","volume":"181","author":"Goecks","journal-title":"Cell"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1","article-title":"DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network","volume":"18","author":"Katzman","journal-title":"BMC Med Res Methodol"},{"issue":"5","key":"R16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pntd.0010388","article-title":"Machine learning-based in-hospital mortality prediction of HIV\/AIDS patients with Talaromyces marneffei infection in Guangxi, China","volume":"16","author":"Shi","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-13-1047","article-title":"Predictors of mortality among HIV infected children on anti-retroviral therapy in Mekelle Hospital, Northern Ethiopia: a retrospective cohort study","volume":"13","author":"Gebremedhin","journal-title":"BMC Public Health"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-024-09368-z","article-title":"The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis","volume":"24","author":"Li","journal-title":"BMC Infect Dis"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-024-10013-y","article-title":"Machine learning-based prognostic prediction for hospitalized HIV\/AIDS patients with cryptococcus infection in Guangxi, China","volume":"24","author":"Zhan","journal-title":"BMC Infect Dis"},{"issue":"4","key":"R20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgph.0004497","article-title":"Use of machine learning in predicting continuity of HIV treatment in selected Nigerian states","volume":"5","author":"Ijaiya","journal-title":"PLOS Glob Public Health"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","first-page":"58","DOI":"10.4258\/hir.2022.28.1.58","article-title":"Development and comparison of three data models for predicting diabetes mellitus using risk factors in a Nigerian population","volume":"28","author":"Odukoya","journal-title":"Healthc Inform Res"},{"key":"R22","unstructured":"Tamiru AT Rade BK Taye EB et al. Community Level of COVID-19 Information Exposure and Influencing Factors in Northwest Ethiopia."},{"key":"R23","unstructured":"Ethiopia\u2019s national research ethics guidelines. URL: https:\/\/www.scribd.com\/document\/450446123\/national-research-ethics-review-guidline [Accessed 15-04-2026]"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Sarkar D Bali R Sharma T . Practical Machine Learning with Python: A Problem-Solver\u2019s Guide to Building Real-World Intelligent Systems. Apress; 2018:25-30. URL: https:\/\/link.springer.com\/book\/10.1007\/978-1-4842-3207-1 [Accessed 27-03-2026]","DOI":"10.1007\/978-1-4842-3207-1"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Kuhn M Johnson K . Applied Predictive Modeling. Springer; 2013. ISBN: 978-1-4614-6848-6","DOI":"10.1007\/978-1-4614-6849-3_1"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2024-101189","article-title":"Evaluating machine learning algorithms for predicting HIV status among young Thai men who have sex with men","volume":"32","author":"Soha","journal-title":"BMJ Health Care Inform"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-021-06977-w","article-title":"Modelling trends of CD4 counts for patients on antiretroviral therapy (ART): a comprehensive health care clinic in Nairobi, Kenya","volume":"22","author":"Mugo","journal-title":"BMC Infect Dis"},{"issue":"3","key":"R28","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1111\/j.1360-0443.2006.01709.x","article-title":"Predictors of mortality among injecting and non-injecting HIV-negative drug users in northern Thailand","volume":"102","author":"Quan","journal-title":"Addiction"},{"issue":"4","key":"R29","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1093\/cid\/ciab995","article-title":"Predictors of all-cause mortality among people with human immunodeficiency virus (HIV) in a prospective cohort study in East Africa and Nigeria","volume":"75","author":"Kibuuka","journal-title":"Clin Infect Dis"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:11:30Z","timestamp":1782843090000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78770"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":29,"URL":"https:\/\/doi.org\/10.2196\/78770","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]},"article-number":"v14i3e78770"}}