Use of machine learning approaches to predict transition of retention in care among people living with HIV in South Carolina: a real-world data study.

IF 1.2 4区 医学 Q4 HEALTH POLICY & SERVICES
Ruilie Cai, Xueying Yang, Yunqing Ma, Hao H Zhang, Bankole Olatosi, Sharon Weissman, Xiaoming Li, Jiajia Zhang
{"title":"Use of machine learning approaches to predict transition of retention in care among people living with HIV in South Carolina: a real-world data study.","authors":"Ruilie Cai, Xueying Yang, Yunqing Ma, Hao H Zhang, Bankole Olatosi, Sharon Weissman, Xiaoming Li, Jiajia Zhang","doi":"10.1080/09540121.2024.2361245","DOIUrl":null,"url":null,"abstract":"<p><p>Maintaining retention in care (RIC) for people living with HIV (PLWH) helps achieve viral suppression and reduce onward transmission. This study aims to identify the best machine learning model that predicts the RIC transition over time. Extracting from the enhanced HIV/AIDS reporting system, this study included 9765 PLWH from 2005 to 2020 in South Carolina. Transition of RIC was defined as the change of RIC status in each two-year time window. We applied seven classifiers, such as Random Forest, Support Vector Machine, eXtreme Gradient Boosting and Long-short-term memory, for each lagged response to predict the subsequent year's RIC transition. Classification performance was assessed using balanced prediction accuracy, the area under the curve (AUC), recall, precision and F1 scores. The proportion of the four categories of RIC transition was 13.59%, 29.78%, 9.06% and 47.57%, respectively. Support Vector Machine was the best approach for every lag model based on both the F1 score (0.713, 0.717 and 0.719) and AUC (0.920, 0.925 and 0.928). The findings could facilitate the risk augment of PLWH who are prone to follow-up so that clinicians and policymakers could come up with more specific strategies and relocate resources for intervention to keep them sustained in HIV care.</p>","PeriodicalId":48370,"journal":{"name":"Aids Care-Psychological and Socio-Medical Aspects of Aids/hiv","volume":" ","pages":"1745-1753"},"PeriodicalIF":1.2000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11560699/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aids Care-Psychological and Socio-Medical Aspects of Aids/hiv","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1080/09540121.2024.2361245","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/4 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"HEALTH POLICY & SERVICES","Score":null,"Total":0}
引用次数: 0

Abstract

Maintaining retention in care (RIC) for people living with HIV (PLWH) helps achieve viral suppression and reduce onward transmission. This study aims to identify the best machine learning model that predicts the RIC transition over time. Extracting from the enhanced HIV/AIDS reporting system, this study included 9765 PLWH from 2005 to 2020 in South Carolina. Transition of RIC was defined as the change of RIC status in each two-year time window. We applied seven classifiers, such as Random Forest, Support Vector Machine, eXtreme Gradient Boosting and Long-short-term memory, for each lagged response to predict the subsequent year's RIC transition. Classification performance was assessed using balanced prediction accuracy, the area under the curve (AUC), recall, precision and F1 scores. The proportion of the four categories of RIC transition was 13.59%, 29.78%, 9.06% and 47.57%, respectively. Support Vector Machine was the best approach for every lag model based on both the F1 score (0.713, 0.717 and 0.719) and AUC (0.920, 0.925 and 0.928). The findings could facilitate the risk augment of PLWH who are prone to follow-up so that clinicians and policymakers could come up with more specific strategies and relocate resources for intervention to keep them sustained in HIV care.

使用机器学习方法预测南卡罗来纳州艾滋病毒感染者继续接受护理的过渡情况:一项真实世界数据研究。
保持对艾滋病病毒感染者(PLWH)的持续关怀(RIC)有助于实现病毒抑制和减少继续传播。本研究旨在找出能预测 RIC 随时间变化的最佳机器学习模型。本研究从增强型艾滋病报告系统中提取数据,纳入了 2005 年至 2020 年南卡罗来纳州的 9765 名艾滋病毒感染者。RIC 过渡定义为每两年时间窗口中 RIC 状态的变化。我们针对每个滞后响应应用了随机森林、支持向量机、极梯度提升和长短期记忆等七种分类器来预测下一年的 RIC 过渡。使用平衡预测准确率、曲线下面积(AUC)、召回率、精确率和 F1 分数评估分类性能。四类 RIC 过渡的比例分别为 13.59%、29.78%、9.06% 和 47.57%。根据 F1 分数(0.713、0.717 和 0.719)和 AUC(0.920、0.925 和 0.928),支持向量机是每个滞后模型的最佳方法。这些研究结果有助于对容易出现随访问题的 PLWH 进行风险评估,从而使临床医生和政策制定者能够制定出更具体的策略,并调配资源进行干预,使他们能够持续接受 HIV 护理。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
3.50
自引率
0.00%
发文量
172
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信