{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T19:35:50Z","timestamp":1787945750905,"version":"build-2784847793"},"reference-count":26,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,4,20]],"date-time":"2025-04-20T00:00:00Z","timestamp":1745107200000},"content-version":"vor","delay-in-days":19,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009054","name":"U.S. President\u2019s Emergency Plan for AIDS Relief","doi-asserted-by":"publisher","award":["1U2GGH001226"],"award-info":[{"award-number":["1U2GGH001226"]}],"id":[{"id":"10.13039\/100009054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Int AIDS Soc."],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Optimal use of HIV testing resources accelerates progress towards ending HIV as a global threat. In Kenya, current testing practices yield a 2.8% positivity rate for new diagnoses reported through the national HIV electronic medical record (EMR) system. Increasingly, researchers have explored the potential for machine learning to improve the identification of people with undiagnosed HIV for referral for HIV testing. However, few studies have used routinely collected programme data as the basis for implementing a real\u2010time clinical decision support system to improve HIV screening. In this study, we applied machine learning to routine programme data from Kenya's EMR to predict the probability that an individual seeking care is undiagnosed HIV positive and should be prioritized for testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We combined de\u2010identified individual\u2010level EMR data from 167,509 individuals without a previous HIV diagnosis who were tested between June and November 2022. We included demographics, clinical histories and HIV\u2010relevant behavioural practices with open\u2010source data that describes population\u2010level behavioural practices as other variables in the model. We used multiple imputations to address high rates of missing data, selecting the optimal technique based on out\u2010of\u2010sample error. We generated a stratified 60\u201020\u201020 train\u2010validate\u2010test split to assess model generalizability. We trained four machine learning algorithms including logistic regression, Random Forest, AdaBoost and XGBoost. Models were evaluated using Area Under the Precision\u2010Recall Curve (AUCPR), a metric that is well\u2010suited to cases of class imbalance such as this, in which there are far more negative test results than positive.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>All model types demonstrated predictive performance on the test set with AUCPR that exceeded the current positivity rate. XGBoost generated the greatest AUCPR, 10.5 times greater than the rate of positive test results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our study demonstrated that machine learning applied to routine HIV testing data may be used as a clinical decision support tool to refer persons for HIV testing. The resulting model could be integrated in the screening form of an EMR and used as a real\u2010time decision support tool to inform testing decisions. Although issues of data quality and missing data remained, these challenges could be addressed using sound data preparation techniques.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jia2.26436","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T01:59:06Z","timestamp":1745200746000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Machine learning to improve HIV screening using routine data in Kenya"],"prefix":"10.1002","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0264-0338","authenticated-orcid":false,"given":"Jonathan D.","family":"Friedman","sequence":"first","affiliation":[{"name":"Data Science Palladium Group Washington DC USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan M.","family":"Mwangi","sequence":"additional","affiliation":[{"name":"Division of Global, HIV &amp; TB US Centers for Disease Control and Prevention Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kennedy J.","family":"Muthoka","sequence":"additional","affiliation":[{"name":"Kenya Health Information Management Systems (KeHMIS) III Project, Palladium Kenya Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benedette A.","family":"Otieno","sequence":"additional","affiliation":[{"name":"Kenya Health Information Management Systems (KeHMIS) III Project, Palladium Kenya Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob O.","family":"Odhiambo","sequence":"additional","affiliation":[{"name":"Kenya Health Information Management Systems (KeHMIS) III Project, Palladium Kenya Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederick O.","family":"Miruka","sequence":"additional","affiliation":[{"name":"Division of Global, HIV &amp; TB US Centers for Disease Control and Prevention Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lilly M.","family":"Nyagah","sequence":"additional","affiliation":[{"name":"National AIDS and STIs Control Programme, Ministry of Health Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal M.","family":"Mwele","sequence":"additional","affiliation":[{"name":"Kenya Health Information Management Systems (KeHMIS) III Project, Palladium Kenya Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edmon O.","family":"Obat","sequence":"additional","affiliation":[{"name":"USAID United States Agency for International Development, Health Population and Nutrition Office Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gonza O.","family":"Omoro","sequence":"additional","affiliation":[{"name":"U.S. Department of Defense Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Margaret M.","family":"Ndisha","sequence":"additional","affiliation":[{"name":"Division of Global, HIV &amp; TB US Centers for Disease Control and Prevention Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9326-0407","authenticated-orcid":false,"given":"Davies O.","family":"Kimanga","sequence":"additional","affiliation":[{"name":"Division of Global, HIV &amp; TB US Centers for Disease Control and Prevention Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,4,20]]},"reference":[{"key":"e_1_2_13_2_1","unstructured":"Centers for Disease Control and Prevention.Status neutral HIV prevention and care. Accessed June 1 2023. Available athttps:\/\/www.cdc.gov\/hiv\/effective\u2010interventions\/prevent\/status\u2010neutral\u2010hiv\u2010prevention\u2010and\u2010care\/index.html#:~:text=The%20status%20neutral%20approach%20to test%20is%20positive%20or%20negative"},{"key":"e_1_2_13_3_1","unstructured":"Kenya HIV prevention and treatment guidelines 2022. Ministry of Health National AIDS and STI Control Program. Accessed August 15 2023. Available athttps:\/\/nphl.go.ke\/wp\u2010content\/uploads\/2022\/11\/Kenya\u2010ARV\u2010Guidelines\u20102022\u20102.pdf"},{"key":"e_1_2_13_4_1","unstructured":"UNAIDS Reference.Understanding fast track: accelerating action to end the AIDS epidemic by 2030. Accessed July 1 2023. Available athttps:\/\/www.unaids.org\/sites\/default\/files\/media_asset\/201506_JC2743_Understanding_FastTrack_en.pdf"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0272405"},{"key":"e_1_2_13_6_1","unstructured":"UNAIDS.Country Factsheets Kenya 2022. Accessed August 15 2023. Available athttps:\/\/www.unaids.org\/en\/regionscountries\/countries\/kenya"},{"key":"e_1_2_13_7_1","unstructured":"Kenya Population\u2010Based HIV Impact Assessment 2018.2022. Ministry of Health National AIDS and STI Control Program. Accessed August 18 2023. Available athttps:\/\/phia.icap.columbia.edu\/kenya\u2010final\u2010report\u20102018\/"},{"key":"e_1_2_13_8_1","unstructured":"US President's Emergency Plan for AIDS Relief.Kenya Country Operational Plan 2022 Strategic Direction Summary. Accessed August 18 2023. Available athttps:\/\/www.state.gov\/wp\u2010content\/uploads\/2022\/09\/Kenya\u2010COP22\u2010SDS\u2010.pdf"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11904\u2010022\u201000601\u20105"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10461\u2010021\u201003404\u20108"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0264429"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciz1096"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874\u2010021\u201001346\u20102"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12879\u2010022\u201007460\u2010w"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgph.0000720"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2352\u20103018(19)30137\u20107"},{"key":"e_1_2_13_17_1","unstructured":"Institute for Health Metrics and Evaluation.Africa HIV prevalence geospatial elements 2000\u20132017. Accessed November 30 2022. Available athttps:\/\/ghdx.healthdata.org\/record\/ihme\u2010data\/africa\u2010hiv\u2010prevalence\u2010geospatial\u2010estimates\u20102000\u20102017"},{"key":"e_1_2_13_18_1","unstructured":"WorldPop Hub.Open spatial demographic data and research. Accessed November 30 2022. Available athttps:\/\/hub.worldpop.org\/"},{"key":"e_1_2_13_19_1","unstructured":"Kenya: High Resolution Population Density Maps.Data for Good at Meta. Accessed November 30 2022. Available athttps:\/\/data.humdata.org\/dataset\/highresolutionpopulationdensitymaps\u2010ken"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911\u2010023\u201002265\u20106"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i03"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3968"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.3233\/FI\u20102010\u2010288"},{"key":"e_1_2_13_24_1","doi-asserted-by":"crossref","unstructured":"ChenT GuestrinC.XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016.https:\/\/doi.org\/10.48550\/arXiv.1603.02754","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.13140"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0212762"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1086\/651492"}],"container-title":["Journal of the International AIDS Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jia2.26436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T06:24:27Z","timestamp":1747722267000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jia2.26436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1002\/jia2.26436"],"URL":"https:\/\/doi.org\/10.1002\/jia2.26436","archive":["Portico"],"relation":{},"ISSN":["1758-2652","1758-2652"],"issn-type":[{"value":"1758-2652","type":"print"},{"value":"1758-2652","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"2024-08-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e26436"}}