Adolescent HIV-related behavioural prediction using machine learning: a foundation for precision HIV prevention
dc.contributor.author | Wang, Bo | |
dc.contributor.author | Liu, Feifan | |
dc.contributor.author | Deveaux, Lynette | |
dc.contributor.author | Ash, Arlene S. | |
dc.contributor.author | Gosh, Samiran | |
dc.contributor.author | Li, Xiaoming | |
dc.contributor.author | Rundensteiner, Elke | |
dc.contributor.author | Cottrell, Lesley | |
dc.contributor.author | Adderley, Richard | |
dc.contributor.author | Stanton, Bonita | |
dc.date | 2022-08-11T08:10:36.000 | |
dc.date.accessioned | 2022-08-23T17:14:18Z | |
dc.date.available | 2022-08-23T17:14:18Z | |
dc.date.issued | 2021-05-01 | |
dc.date.submitted | 2021-09-23 | |
dc.identifier.citation | <p>Wang B, Liu F, Deveaux L, Ash A, Gosh S, Li X, Rundensteiner E, Cottrell L, Adderley R, Stanton B. Adolescent HIV-related behavioural prediction using machine learning: a foundation for precision HIV prevention. AIDS. 2021 May 1;35(Suppl 1):S75-S84. doi: 10.1097/QAD.0000000000002867. PMID: 33867490; PMCID: PMC8133351. <a href="https://doi.org/10.1097/QAD.0000000000002867">Link to article on publisher's site</a></p> | |
dc.identifier.issn | 0269-9370 (Linking) | |
dc.identifier.doi | 10.1097/QAD.0000000000002867 | |
dc.identifier.pmid | 33867490 | |
dc.identifier.uri | http://hdl.handle.net/20.500.14038/46927 | |
dc.description.abstract | BACKGROUND: Precision prevention is increasingly important in HIV prevention research to move beyond universal interventions to those tailored for high-risk individuals. The current study was designed to develop machine learning algorithms for predicting adolescent HIV risk behaviours. METHODS: Comprehensive longitudinal data on adolescent risk behaviours, perceptions, peer and family influence, and neighbourhood risk factors were collected from 2564 grade-10 students at baseline followed for 24 months over 2008-2012. Machine learning techniques [support vector machine (SVM) and random forests] were applied to innovatively leverage longitudinal data for robust HIV risk behaviour prediction. In this study, we focused on two adolescent risk behaviours: had ever had sex and had multiple sex partners. Twenty percent of the data were withheld for model testing. RESULTS: The SVM model with cost-sensitive learning achieved the highest sensitivity, at 79.1%, specificity of 75.4% with AUC of 0.86 in predicting multiple sex partners on the training data (10-fold cross-validation), and sensitivity of 79.7%, specificity of 76.5% with AUC of 0.86 on the testing data. The random forest model obtained the best performance in predicting had ever had sex, yielding the sensitivity of 78.5%, specificity of 73.1% with AUC of 0.84 on the training data and sensitivity of 82.7%, specificity of 75.3% with AUC of 0.87 on the testing data. CONCLUSION: Machine learning methods can be used to build effective prediction model(s) to identify adolescents who are likely to engage in HIV risk behaviours. This study builds a foundation for targeted intervention strategies and informs precision prevention efforts in school-setting. | |
dc.language.iso | en_US | |
dc.relation | <p><a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&list_uids=33867490&dopt=Abstract">Link to Article in PubMed</a></p> | |
dc.relation.url | https://doi.org/10.1097/qad.0000000000002867 | |
dc.subject | adolescent HIV risk behaviour | |
dc.subject | machine learning | |
dc.subject | multiple sex partners | |
dc.subject | prediction | |
dc.subject | Artificial Intelligence and Robotics | |
dc.subject | Behavior and Behavior Mechanisms | |
dc.subject | Epidemiology | |
dc.subject | Virus Diseases | |
dc.title | Adolescent HIV-related behavioural prediction using machine learning: a foundation for precision HIV prevention | |
dc.type | Journal Article | |
dc.source.journaltitle | AIDS (London, England) | |
dc.source.volume | 35 | |
dc.source.issue | Suppl 1 | |
dc.identifier.legacycoverpage | https://escholarship.umassmed.edu/qhs_pp/1406 | |
dc.identifier.contextkey | 25084002 | |
html.description.abstract | <p>BACKGROUND: Precision prevention is increasingly important in HIV prevention research to move beyond universal interventions to those tailored for high-risk individuals. The current study was designed to develop machine learning algorithms for predicting adolescent HIV risk behaviours.</p> <p>METHODS: Comprehensive longitudinal data on adolescent risk behaviours, perceptions, peer and family influence, and neighbourhood risk factors were collected from 2564 grade-10 students at baseline followed for 24 months over 2008-2012. Machine learning techniques [support vector machine (SVM) and random forests] were applied to innovatively leverage longitudinal data for robust HIV risk behaviour prediction. In this study, we focused on two adolescent risk behaviours: had ever had sex and had multiple sex partners. Twenty percent of the data were withheld for model testing.</p> <p>RESULTS: The SVM model with cost-sensitive learning achieved the highest sensitivity, at 79.1%, specificity of 75.4% with AUC of 0.86 in predicting multiple sex partners on the training data (10-fold cross-validation), and sensitivity of 79.7%, specificity of 76.5% with AUC of 0.86 on the testing data. The random forest model obtained the best performance in predicting had ever had sex, yielding the sensitivity of 78.5%, specificity of 73.1% with AUC of 0.84 on the training data and sensitivity of 82.7%, specificity of 75.3% with AUC of 0.87 on the testing data.</p> <p>CONCLUSION: Machine learning methods can be used to build effective prediction model(s) to identify adolescents who are likely to engage in HIV risk behaviours. This study builds a foundation for targeted intervention strategies and informs precision prevention efforts in school-setting.</p> | |
dc.identifier.submissionpath | qhs_pp/1406 | |
dc.contributor.department | Population and Quantitative Health Sciences | |
dc.contributor.department | UMass Chan Analytics | |
dc.contributor.department | Biostatistics and Health Services Research | |
dc.source.pages | S75-S84 |