Yifan Cui, Sikhulile Moyo, Molly Pretorius Holme, Kathleen E Hurwitz, Wonderful Choga, Kara Bennett, Unoda Chakalisa, James Emmanuel San, Kutlo Manyake, Coulson Kgathi, Ame Diphoko, Simani Gaseitsiwe, Tendani Gaolathe, M Essex, Eric Tchetgen Tchetgen, Joseph M Makhema, Shahin Lockman
{"title":"博茨瓦纳艾滋病毒血清转换的预测因素:对具有代表性、基于人群的艾滋病毒发病队列进行机器学习分析。","authors":"Yifan Cui, Sikhulile Moyo, Molly Pretorius Holme, Kathleen E Hurwitz, Wonderful Choga, Kara Bennett, Unoda Chakalisa, James Emmanuel San, Kutlo Manyake, Coulson Kgathi, Ame Diphoko, Simani Gaseitsiwe, Tendani Gaolathe, M Essex, Eric Tchetgen Tchetgen, Joseph M Makhema, Shahin Lockman","doi":"10.1097/QAD.0000000000004055","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To identify predictors of HIV acquisition in Botswana.</p><p><strong>Design: </strong>We applied machine learning approaches to identify HIV risk predictors using existing data from a large, well-characterized HIV incidence cohort.</p><p><strong>Methods: </strong>We applied machine learning (randomForestSRC) to analyze data from a large population-based HIV incidence cohort enrolled in a cluster-randomized HIV prevention trial in 30 communities across Botswana. We sought to identify the most important risk factors for HIV acquisition, starting with 110 potential predictors.</p><p><strong>Results: </strong>During a median 29-month follow-up of 8,551 HIV-negative adults, 147 (1.7%) acquired HIV. Our machine learning analysis found that for females, the most important variables for predicting HIV acquisition were the use of injectable hormonal contraception, frequency of sex in the prior 3 months with the most recent partner and residing in a community with HIV prevalence of 29% or higher. For the small proportion (0.3%) of females who had all three risk factors, their estimated probability of acquiring HIV during 29 months of follow-up was 34% (approximate annual incidence of 14%). For males, non-long-term relationships with the most recent partner and community HIV prevalence of 34% or higher were the most important HIV risk predictors. The 6% of males who had both risk factors had a 5.1% probability of acquiring HIV during the follow-up period (approximate annual incidence of 2.1%).</p><p><strong>Conclusions: </strong>Machine learning approaches allowed us to analyze a large number of variables to efficiently identify key factors strongly predictive of HIV risk. These factors could help target HIV prevention interventions in Botswana.</p><p><strong>Clinical trials registration: </strong>NCT01965470.</p>","PeriodicalId":7502,"journal":{"name":"AIDS","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predictors of HIV seroconversion in Botswana: machine learning analysis in a representative, population-based HIV incidence cohort.\",\"authors\":\"Yifan Cui, Sikhulile Moyo, Molly Pretorius Holme, Kathleen E Hurwitz, Wonderful Choga, Kara Bennett, Unoda Chakalisa, James Emmanuel San, Kutlo Manyake, Coulson Kgathi, Ame Diphoko, Simani Gaseitsiwe, Tendani Gaolathe, M Essex, Eric Tchetgen Tchetgen, Joseph M Makhema, Shahin Lockman\",\"doi\":\"10.1097/QAD.0000000000004055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>To identify predictors of HIV acquisition in Botswana.</p><p><strong>Design: </strong>We applied machine learning approaches to identify HIV risk predictors using existing data from a large, well-characterized HIV incidence cohort.</p><p><strong>Methods: </strong>We applied machine learning (randomForestSRC) to analyze data from a large population-based HIV incidence cohort enrolled in a cluster-randomized HIV prevention trial in 30 communities across Botswana. We sought to identify the most important risk factors for HIV acquisition, starting with 110 potential predictors.</p><p><strong>Results: </strong>During a median 29-month follow-up of 8,551 HIV-negative adults, 147 (1.7%) acquired HIV. Our machine learning analysis found that for females, the most important variables for predicting HIV acquisition were the use of injectable hormonal contraception, frequency of sex in the prior 3 months with the most recent partner and residing in a community with HIV prevalence of 29% or higher. For the small proportion (0.3%) of females who had all three risk factors, their estimated probability of acquiring HIV during 29 months of follow-up was 34% (approximate annual incidence of 14%). For males, non-long-term relationships with the most recent partner and community HIV prevalence of 34% or higher were the most important HIV risk predictors. The 6% of males who had both risk factors had a 5.1% probability of acquiring HIV during the follow-up period (approximate annual incidence of 2.1%).</p><p><strong>Conclusions: </strong>Machine learning approaches allowed us to analyze a large number of variables to efficiently identify key factors strongly predictive of HIV risk. These factors could help target HIV prevention interventions in Botswana.</p><p><strong>Clinical trials registration: </strong>NCT01965470.</p>\",\"PeriodicalId\":7502,\"journal\":{\"name\":\"AIDS\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-11-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"AIDS\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/QAD.0000000000004055\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"IMMUNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"AIDS","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/QAD.0000000000004055","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"IMMUNOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
目的确定博茨瓦纳艾滋病感染的预测因素:我们采用机器学习方法,利用一个大型、特征明确的 HIV 发病率队列中的现有数据来识别 HIV 风险预测因子:我们应用机器学习(randomForestSRC)分析了博茨瓦纳 30 个社区中参加集群随机艾滋病预防试验的大型人群艾滋病发病队列的数据。我们试图从 110 个潜在的预测因素入手,找出艾滋病感染最重要的风险因素:在对 8551 名 HIV 阴性成人进行的为期 29 个月的中位随访中,有 147 人(1.7%)感染了 HIV。我们的机器学习分析发现,对于女性而言,预测感染 HIV 的最重要变量是使用注射式激素避孕药、在过去 3 个月中与最近的性伴侣发生性关系的频率以及居住在 HIV 感染率为 29% 或更高的社区。对于一小部分(0.3%)同时具备这三个风险因素的女性来说,她们在 29 个月的随访期间感染艾滋病毒的概率估计为 34%(年发病率约为 14%)。对于男性来说,与最近的性伴侣之间的非长期关系以及 34% 或更高的社区 HIV 感染率是最重要的 HIV 风险预测因素。同时具备这两个风险因素的 6% 男性在随访期间感染 HIV 的概率为 5.1%(年发病率约为 2.1%):机器学习方法使我们能够对大量变量进行分析,从而有效识别出强烈预测艾滋病风险的关键因素。这些因素有助于博茨瓦纳有针对性地采取艾滋病预防干预措施:临床试验注册:NCT01965470。
Predictors of HIV seroconversion in Botswana: machine learning analysis in a representative, population-based HIV incidence cohort.
Objective: To identify predictors of HIV acquisition in Botswana.
Design: We applied machine learning approaches to identify HIV risk predictors using existing data from a large, well-characterized HIV incidence cohort.
Methods: We applied machine learning (randomForestSRC) to analyze data from a large population-based HIV incidence cohort enrolled in a cluster-randomized HIV prevention trial in 30 communities across Botswana. We sought to identify the most important risk factors for HIV acquisition, starting with 110 potential predictors.
Results: During a median 29-month follow-up of 8,551 HIV-negative adults, 147 (1.7%) acquired HIV. Our machine learning analysis found that for females, the most important variables for predicting HIV acquisition were the use of injectable hormonal contraception, frequency of sex in the prior 3 months with the most recent partner and residing in a community with HIV prevalence of 29% or higher. For the small proportion (0.3%) of females who had all three risk factors, their estimated probability of acquiring HIV during 29 months of follow-up was 34% (approximate annual incidence of 14%). For males, non-long-term relationships with the most recent partner and community HIV prevalence of 34% or higher were the most important HIV risk predictors. The 6% of males who had both risk factors had a 5.1% probability of acquiring HIV during the follow-up period (approximate annual incidence of 2.1%).
Conclusions: Machine learning approaches allowed us to analyze a large number of variables to efficiently identify key factors strongly predictive of HIV risk. These factors could help target HIV prevention interventions in Botswana.
期刊介绍:
Publishing the very latest ground breaking research on HIV and AIDS. Read by all the top clinicians and researchers, AIDS has the highest impact of all AIDS-related journals. With 18 issues per year, AIDS guarantees the authoritative presentation of significant advances. The Editors, themselves noted international experts who know the demands of your work, are committed to making AIDS the most distinguished and innovative journal in the field. Submitted articles undergo a preliminary review by the editor. Some articles may be returned to authors without further consideration. Those being considered for publication will undergo further assessment and peer-review by the editors and those invited to do so from a reviewer pool.