{"doi":"10.1371/journal.pgph.0000720","title":"Machine learning with routine electronic medical record data to identify people at high risk of disengagement from HIV care in Tanzania","abstract":"Machine learning methods for health care delivery optimization have the potential to improve retention in HIV care, a critical target of global efforts to end the epidemic. However, these methods have not been widely applied to medical record data in low- and middle-income countries. We used an ensemble decision tree approach to predict risk of disengagement from HIV care (missing an appointment by ≥28 days) in Tanzania. Our approach used routine electronic medical records (EMR) from the time of antiretroviral therapy (ART) initiation through 24 months of follow-up for 178 adults (63% female). We compared prediction accuracy when using EMR-based predictors alone and in combination with sociodemographic survey data collected by a research study. Models that included only EMR-based indicators and incorporated changes across past clinical visits achieved a mean accuracy of 75.2% for predicting risk of disengagement in the next 6 months, with a mean sensitivity of 54.7% for targeting the 30% highest-risk individuals. Additionally including survey-based predictors only modestly improved model performance. The most important variables for prediction were time-varying EMR indicators including changes in treatment status, body weight, and WHO clinical stage. Machine learning methods applied to existing EMR data in resource-constrained settings can predict individuals' future risk of disengagement from HIV care, potentially enabling better targeting and efficiency of interventions to promote retention in care.","journal":"PLOS Global Public Health","year":2022,"id":244440,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":29,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9533,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":706718,"name":"Linqing Wei","orcid":"0000-0003-3504-4436","position":1,"is_corresponding":false},{"id":294521,"name":"Prosper Njau","orcid":"0000-0002-6351-9489","position":2,"is_corresponding":false},{"id":877773,"name":"Siraji Shabani","orcid":"0000-0003-4357-4971","position":3,"is_corresponding":false},{"id":878166,"name":"Sylvester Kwilasa","orcid":null,"position":4,"is_corresponding":false},{"id":877774,"name":"Werner Maokola","orcid":"0000-0003-0782-0784","position":5,"is_corresponding":false},{"id":440141,"name":"Laura Packel","orcid":"0000-0002-8186-5246","position":6,"is_corresponding":false},{"id":877775,"name":"Zeyu Zheng","orcid":"0000-0001-5653-152X","position":7,"is_corresponding":false},{"id":779147,"name":"Jingshen Wang","orcid":"0000-0002-1432-3834","position":8,"is_corresponding":false},{"id":294525,"name":"Sandra I. McCoy","orcid":"0000-0002-4764-9195","position":9,"is_corresponding":false},{"id":294520,"name":"Carolyn A. Fahey","orcid":"0000-0001-9865-2397","position":0,"is_corresponding":true}],"reference_count":25,"raw_metadata":null,"created_at":"2026-07-19T00:23:25.718788Z","pmid":"36962586","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}