Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220906911> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4220906911 endingPage "160" @default.
- W4220906911 startingPage "154" @default.
- W4220906911 abstract "Background: A core objective of HIV/AIDS programming is keeping clients on treatment to improve their health outcomes and to limit spread. Machine learning and artificial intelligence can combine client, temporal, and locational attributes to identify which clients are at greatest risk of loss to follow-up (LTFU) and enable health providers to direct support interventions accordingly. Setting: The analysis was part of a project funded by U.S. President's Emergency Plan for AIDS Relief and United States Agency for International Development, Data for Implementation, and applied to data from publicly available sources (health facility data, geospatial data, and satellite imagery) and de-identified electronic medical record data on antiretroviral therapy clients in Nigeria and Mozambique. Methods: The project applied binary classification techniques using temporal cross-validation to predict the risk that patients would be LTFU. Classifiers included logistic regression, neural networks, and tree-based models. Results: Models showed strong predictive power in both settings. In Mozambique, the best-performing model, a Random Forest, achieved an area under the precision–recall curve of 0.65 compared against an underlying LTFU rate of 23%. In Nigeria, the best-performing model, a boosted tree, achieved an area under the precision–recall curve of 0.52 compared against an underlying LTFU rate of 27%. Conclusions: Machine-learned models outperformed current classification techniques and showed potential to better direct health worker resources toward patients at greatest risk of LTFU. Moreover, models performed equally across sex and age groups, supporting the model's generalizability and wider application." @default.
- W4220906911 created "2022-04-03" @default.
- W4220906911 creator A5004335153 @default.
- W4220906911 creator A5030213878 @default.
- W4220906911 creator A5070235870 @default.
- W4220906911 creator A5077549860 @default.
- W4220906911 date "2022-06-01" @default.
- W4220906911 modified "2023-10-12" @default.
- W4220906911 title "Predictive Analytics Using Machine Learning to Identify ART Clients at Health System Level at Greatest Risk of Treatment Interruption in Mozambique and Nigeria" @default.
- W4220906911 cites W1512346648 @default.
- W4220906911 cites W2083484297 @default.
- W4220906911 cites W2901036517 @default.
- W4220906911 cites W3044048793 @default.
- W4220906911 cites W3095596475 @default.
- W4220906911 doi "https://doi.org/10.1097/qai.0000000000002947" @default.
- W4220906911 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35262514" @default.
- W4220906911 hasPublicationYear "2022" @default.
- W4220906911 type Work @default.
- W4220906911 citedByCount "6" @default.
- W4220906911 countsByYear W42209069112022 @default.
- W4220906911 countsByYear W42209069112023 @default.
- W4220906911 crossrefType "journal-article" @default.
- W4220906911 hasAuthorship W4220906911A5004335153 @default.
- W4220906911 hasAuthorship W4220906911A5030213878 @default.
- W4220906911 hasAuthorship W4220906911A5070235870 @default.
- W4220906911 hasAuthorship W4220906911A5077549860 @default.
- W4220906911 hasBestOaLocation W42209069111 @default.
- W4220906911 hasConcept C105795698 @default.
- W4220906911 hasConcept C111472728 @default.
- W4220906911 hasConcept C119857082 @default.
- W4220906911 hasConcept C138885662 @default.
- W4220906911 hasConcept C151956035 @default.
- W4220906911 hasConcept C154945302 @default.
- W4220906911 hasConcept C159110408 @default.
- W4220906911 hasConcept C160735492 @default.
- W4220906911 hasConcept C162324750 @default.
- W4220906911 hasConcept C169258074 @default.
- W4220906911 hasConcept C27158222 @default.
- W4220906911 hasConcept C27415008 @default.
- W4220906911 hasConcept C2778136018 @default.
- W4220906911 hasConcept C33923547 @default.
- W4220906911 hasConcept C41008148 @default.
- W4220906911 hasConcept C50522688 @default.
- W4220906911 hasConcept C71924100 @default.
- W4220906911 hasConceptScore W4220906911C105795698 @default.
- W4220906911 hasConceptScore W4220906911C111472728 @default.
- W4220906911 hasConceptScore W4220906911C119857082 @default.
- W4220906911 hasConceptScore W4220906911C138885662 @default.
- W4220906911 hasConceptScore W4220906911C151956035 @default.
- W4220906911 hasConceptScore W4220906911C154945302 @default.
- W4220906911 hasConceptScore W4220906911C159110408 @default.
- W4220906911 hasConceptScore W4220906911C160735492 @default.
- W4220906911 hasConceptScore W4220906911C162324750 @default.
- W4220906911 hasConceptScore W4220906911C169258074 @default.
- W4220906911 hasConceptScore W4220906911C27158222 @default.
- W4220906911 hasConceptScore W4220906911C27415008 @default.
- W4220906911 hasConceptScore W4220906911C2778136018 @default.
- W4220906911 hasConceptScore W4220906911C33923547 @default.
- W4220906911 hasConceptScore W4220906911C41008148 @default.
- W4220906911 hasConceptScore W4220906911C50522688 @default.
- W4220906911 hasConceptScore W4220906911C71924100 @default.
- W4220906911 hasIssue "2" @default.
- W4220906911 hasLocation W42209069111 @default.
- W4220906911 hasLocation W42209069112 @default.
- W4220906911 hasLocation W42209069113 @default.
- W4220906911 hasOpenAccess W4220906911 @default.
- W4220906911 hasPrimaryLocation W42209069111 @default.
- W4220906911 hasRelatedWork W2911455822 @default.
- W4220906911 hasRelatedWork W3174196512 @default.
- W4220906911 hasRelatedWork W3198710639 @default.
- W4220906911 hasRelatedWork W4212963941 @default.
- W4220906911 hasRelatedWork W4239706975 @default.
- W4220906911 hasRelatedWork W4283313480 @default.
- W4220906911 hasRelatedWork W4285237370 @default.
- W4220906911 hasRelatedWork W4308191010 @default.
- W4220906911 hasRelatedWork W4321636153 @default.
- W4220906911 hasRelatedWork W4323021782 @default.
- W4220906911 hasVolume "90" @default.
- W4220906911 isParatext "false" @default.
- W4220906911 isRetracted "false" @default.
- W4220906911 workType "article" @default.