AUTHOR=Wu Jiaqin , Shaw Bryan , Oni Babatunji , Jean-Charles Kurt , Dorestan Darwin , Bien-Aime Marie , Compere-Louis Daphne , Dorce Venise , Jean-Pierre Vladimy , Joseph Marc Elie , Labbe Nancy Rachel 
  
TITLE=Applying Machine Learning to Predict Loss to Follow-Up Among People Living With HIV in Haiti Using a National Electronic Medical Record Cohort
  
JOURNAL=International Journal of Public Health
  
VOLUME=Volume 71 - 2026
  
YEAR=2026
  
URL=https://www.ssph-journal.org/journals/international-journal-of-public-health/articles/10.3389/ijph.2026.1609496
  
DOI=10.3389/ijph.2026.1609496
  
ISSN=1661-8564
  
ABSTRACT=ObjectivesLoss to follow-up (LTFU) among people living with HIV (PLHIV) remains a major barrier to epidemic control. This study developed machine learning (ML) models to forecast individual risk of LTFU using routine electronic medical record (EMR) data.MethodsWe analyzed data from Haiti’s national EMR database, with 115,822 PLHIV receiving antiretroviral therapy (ART) across 167 health facilities from 2018 to 2024. We trained four ML models, including demographic, clinical, and institutional predictors for LTFU. Model performance was assessed across four quarters using F2-score, recall, precision, ROC-AUC, PR-AUC, and calibration. SHAP values were used to interpret key predictors of LTFU risk.ResultsThe CatBoost model trained with weight adjustment performed best across all quarters. The highest F2-score and recall were observed in the first quarter, with modest declines over time. Predictive features with the strongest influence included prior visit and viral load test frequency, ART dispensation patterns, and facility location.ConclusionML models using national EMR data can effectively forecast LTFU risk among PLHIV in Haiti. Incorporating these models into routine care systems can support proactive, tiered interventions to improve retention outcomes.