{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:14:49Z","timestamp":1773260089055,"version":"3.50.1"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T00:00:00Z","timestamp":1560470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>HIV infection risk can be estimated based on not only individual features but also social network information. However, there have been insufficient studies using n machine learning methods that can maximize the utility of such information. Leveraging a state-of-the-art network topology modeling method, graph convolutional networks (GCN), our main objective was to include network information for the task of detecting previously unknown HIV infections.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We used multiple social network data (peer referral, social, sex partners, and affiliation with social and health venues) that include 378 young men who had sex with men in Houston, TX, collected between 2014 and 2016. Due to the limited sample size, an ensemble approach was engaged by integrating GCN for modeling information flow and statistical machine learning methods, including random forest and logistic regression, to efficiently model sparse features in individual nodes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Modeling network information using GCN effectively increased the prediction of HIV status in the social network. The ensemble approach achieved 96.6% on accuracy and 94.6% on F1 measure, which outperformed the baseline methods (GCN, logistic regression, and random forest: 79.0%, 90.5%, 94.4% on accuracy, respectively; and 57.7%, 80.2%, 90.4% on F1). In the networks with missing HIV status, the ensemble also produced promising results.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Network context is a necessary component in modeling infectious disease transmissions such as HIV. GCN, when combined with traditional machine learning approaches, achieved promising performance in detecting previously unknown HIV infections, which may provide a useful tool for combatting the HIV epidemic.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocz070","type":"journal-article","created":{"date-parts":[[2019,4,28]],"date-time":"2019-04-28T11:07:45Z","timestamp":1556449665000},"page":"1263-1271","source":"Crossref","is-referenced-by-count":17,"title":["Network context matters: graph convolutional network model over social networks improves the detection of unknown HIV infections among young men who have sex with men"],"prefix":"10.1093","volume":"26","author":[{"given":"Yang","family":"Xiang","sequence":"first","affiliation":[{"name":"School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA"}]},{"given":"Kayo","family":"Fujimoto","sequence":"additional","affiliation":[{"name":"Department of Health Promotion & Behavioral Sciences, School of Public Health, University of Texas Health Science Center at Houston, Houston, Texas, USA"}]},{"given":"John","family":"Schneider","sequence":"additional","affiliation":[{"name":"Departments of Medicine and Public Health Sciences, University of Chicago, Chicago, Illinois, USA"},{"name":"Chicago Center for HIV Elimination, University of Chicago, Chicago, Illinois, USA"}]},{"given":"Yuxi","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA"},{"name":"Department of Medical Informatics, School of Public Health, Jilin University, Jilin, China"}]},{"given":"Degui","family":"Zhi","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA"}]},{"given":"Cui","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA"}]}],"member":"286","published-online":{"date-parts":[[2019,6,14]]},"reference":[{"key":"2020110613075524400_ocz070-B1","author":"Centers for Disease Control and Prevention (CDC)"},{"key":"2020110613075524400_ocz070-B2","author":"CDC"},{"key":"2020110613075524400_ocz070-B3","author":"Jones"},{"key":"2020110613075524400_ocz070-B4","author":"CDC"},{"key":"2020110613075524400_ocz070-B5","author":"Leke-Betechuoh"},{"key":"2020110613075524400_ocz070-B6","first-page":"211","article-title":"Prediction of HIV sexual risk behaviors among disadvantaged African American adults using a syndemic conceptual framework","volume":"79","author":"Abrutyn","year":"2015","journal-title":"AIDS Behav"},{"key":"2020110613075524400_ocz070-B7","first-page":"1","article-title":"Identifying risk factors for recent HIV infection in Kenya using a recent infection testing algorithm: results from a nationally representative population-based survey","volume":"11","author":"Kim","year":"2016","journal-title":"PLoS One"},{"issue":"8","key":"2020110613075524400_ocz070-B8","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.2105\/AJPH.87.8.1289","article-title":"Sociometric risk networks and risk for HIV infection","volume":"87","author":"Friedman","year":"1997","journal-title":"Am J Public Health"},{"key":"2020110613075524400_ocz070-B9","doi-asserted-by":"crossref","first-page":"28","DOI":"10.2105\/AJPH.2012.301003","article-title":"Network mixing and network influences most linked to HIV infection and risk behavior in the HIV epidemic among black men who have sex with men","volume":"103","author":"Schneider","year":"2013","journal-title":"Am J Public Health"},{"key":"2020110613075524400_ocz070-B10","author":"Friedman"},{"issue":"6","key":"2020110613075524400_ocz070-B11","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.2105\/AJPH.2014.302474","article-title":"Venue-mediated weak ties in multiplex HIV transmission risk networks among drug-using male sex workers and associates","volume":"105","author":"Fujimoto","year":"2015","journal-title":"Am J Public Health"},{"key":"2020110613075524400_ocz070-B12","first-page":"37","article-title":"Using sexual affiliation networks to describe the sexual structure of a population","author":"Street","year":"2007","journal-title":"Sex Transm Infect"},{"key":"2020110613075524400_ocz070-B13","author":"Fujimoto"},{"issue":"2","key":"2020110613075524400_ocz070-B14","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1007\/s10461-010-9858-x","article-title":"Concurrent partnerships, acute infection, and HIV epidemic dynamics among young adults in Zimbabwe","volume":"16","author":"Goodreau","year":"2012","journal-title":"AIDS Behav"},{"issue":"1","key":"2020110613075524400_ocz070-B15","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1214\/16-AOAS1010","article-title":"Inference for social network models from egocentrically sampled data, with application to understanding persistant racial disparities in HIV prevalence in the US","volume":"11","author":"Krivitsky","year":"2017","journal-title":"Ann Appl Stat"},{"key":"2020110613075524400_ocz070-B16","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017","journal-title":"ICLR"},{"issue":"2","key":"2020110613075524400_ocz070-B17","doi-asserted-by":"crossref","first-page":"174","DOI":"10.2307\/3096941","article-title":"Respondent-driven sampling: a new approach to the study of hidden populations","volume":"44","author":"Heckathorn","year":"1997","journal-title":"Soc Probl"},{"issue":"1","key":"2020110613075524400_ocz070-B18","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1525\/sp.2002.49.1.11","article-title":"Respondent-driven sampling II: deriving valid population estimates from chain-referral samples of hidden populations","volume":"49","author":"Heckathorn","year":"2002","journal-title":"Soc Probl"},{"key":"2020110613075524400_ocz070-B19","first-page":"335","article-title":"Structural bridging network position is associated with HIV status in a younger Black men who have sex with men epidemic","volume":"18","author":"Laumann","year":"2015","journal-title":"AIDS Behav"},{"key":"2020110613075524400_ocz070-B20","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.socnet.2018.01.003","article-title":"Statistical adjustment of network degree in respondent-driven sampling estimators\u202f: venue attendance as a proxy for network size among young MSM","volume":"54","author":"Fujimoto","year":"2018","journal-title":"Soc Networks"},{"key":"2020110613075524400_ocz070-B21","author":"Cheng"},{"issue":"4","key":"2020110613075524400_ocz070-B22","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/j.socnet.2007.04.002","article-title":"Some unique properties of eigenvector centrality","volume":"29","author":"Bonacich","year":"2007","journal-title":"Soc Networks"},{"issue":"2","key":"2020110613075524400_ocz070-B23","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1097\/MLR.0000000000000595","article-title":"Multiplex competition, collaboration, and funding networks among social and health organizations: towards organization-based HIV interventions for young men who have sex with men","volume":"55","author":"Fujimoto","year":"2017","journal-title":"Med Care"},{"key":"2020110613075524400_ocz070-B24","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"2020110613075524400_ocz070-B25","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"Sak","year":"2014","journal-title":"Interspeech"},{"key":"2020110613075524400_ocz070-B26","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"2020110613075524400_ocz070-B27","first-page":"729","article-title":"A new model for learning in graph domains","volume":"2","author":"Gori","year":"2005","journal-title":"Proc Int Jt Conf Neural Networks"},{"key":"2020110613075524400_ocz070-B28","first-page":"1","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"Duvenaud","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"2020110613075524400_ocz070-B29","author":"Defferrard"},{"key":"2020110613075524400_ocz070-B30","author":"Zhang"},{"key":"2020110613075524400_ocz070-B31","first-page":"807","author":"Nair","year":"2010"},{"key":"2020110613075524400_ocz070-B32","author":"Hosmer"},{"key":"2020110613075524400_ocz070-B33","author":"Choi"},{"key":"2020110613075524400_ocz070-B34","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"2020110613075524400_ocz070-B35","first-page":"2339","article-title":"Prediction of HIV status from demographic data using neural networks","volume":"3","author":"Leke-Betechuoh","year":"2006","journal-title":"Syst Man Cybern"},{"key":"2020110613075524400_ocz070-B36","first-page":"1467","article-title":"Autoencoder networks for HIV classification","volume":"91","author":"Betechuoh","year":"2006","journal-title":"Curr Sci"},{"key":"2020110613075524400_ocz070-B37","first-page":"48","author":"Dom","year":"2016"},{"key":"2020110613075524400_ocz070-B38","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2020110613075524400_ocz070-B39","author":"Kingma","year":"2015"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/11\/1263\/34152005\/ocz070.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/11\/1263\/34152005\/ocz070.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:17:38Z","timestamp":1604690258000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/26\/11\/1263\/5518586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,14]]},"references-count":39,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2019,6,14]]},"published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocz070","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,11]]},"published":{"date-parts":[[2019,6,14]]}}}