JAIDS Journal of Acquired Immune Deficiency Syndromes最新文献

{"title":"DEVELOPING A PRACTICE-DRIVEN TAXONOMY OF IMPLEMENTATION STRATEGIES FOR HIV PREVENTION.","authors":"Sarit A Golub, Carly Wolfer, Alexa Beacham, Benjamin V Lane, Cody A Chastain, Kathrine A Meyers","doi":"10.1097/QAI.0000000000003581","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003581","url":null,"abstract":"<p><strong>Background: </strong>Effective implementation of evidence-based HIV prevention interventions continues to be a challenge in the United States, and the field is increasingly turning to implementation science for solutions. As such, it is critical to expand the current implementation science vocabulary - and its taxonomy of implementation strategies - to increase its relevance and utility for front-line implementers.</p><p><strong>Setting: </strong>Community-based health centers providing HIV prevention services in the Southeastern US.</p><p><strong>Method: </strong>We conducted a collective case-study analysis, combining document review and qualitative interviews with program directors, clinicians, and other providers (N = 30) at five sites. We employed an inductive and iterative analytic approach to specify and categorize strategies, and then conducted in-depth cross-case analysis to derive a practice-driven taxonomy of HIV prevention implementation strategies.</p><p><strong>Results: </strong>From an initial matrix of 264 activities, we identified 50 strategies common across sites. In contrast to existing implementation science frameworks, the majority (68%, n = 34) of strategies were designed to impact implementation outcomes (e.g., acceptability, adoption, feasibility) for patients. We present a practice-driven taxonomy of these strategies, operationalized according to implementation science literature, but with terminology that more directly relates to implementers.</p><p><strong>Conclusions: </strong>Findings demonstrate the feasibility and utility of this method for developing a practice-driven implementation science vocabulary for HIV prevention. Our evidence-based taxonomy provides a framework for implementers seeking data about the universe of strategies they might consider for their own programs, and increases researchers' ability to measure and evaluate the effectiveness of implementation strategies being enacted in practice settings.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review of network models for HIV spread.","authors":"Heather Mattie, Ravi Goyal, Victor De Gruttola, Jukka-Pekka Onnela","doi":"10.1097/QAI.0000000000003578","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003578","url":null,"abstract":"<p><strong>Background: </strong>HIV/AIDS has been a global health crisis for over four decades. Network models, which simulate human behavior and intervention impacts, have become an essential tool in guiding HIV prevention strategies and policies. However, no comprehensive survey of network models in HIV research has been conducted. This paper fills that gap, offering a summary of past work and future directions to engage more researchers and inform policy related to eliminating HIV.</p><p><strong>Setting: </strong>Network models explicitly represent interactions between individuals, making them well-suited to study HIV transmission dynamics. Two primary modeling paradigms exist: a mechanistic approach from applied mathematics and a statistical approach from the social sciences. Each has distinct strengths and weaknesses, which should be understood for effective application to HIV research.</p><p><strong>Methods: </strong>We conducted a systematic review of network models used in HIV research, detailing the model types, populations, interventions, behaviors, datasets, and software employed, while identifying potential future research directions.</p><p><strong>Results: </strong>Network models are particularly valuable for studying behaviors central to HIV transmission, such as partner selection and treatment adherence. Unlike traditional models, they focus on indi- vidual behaviors, aligning them with clinical practice. However, more accurate network data are needed for better model calibration and actionable insights.</p><p><strong>Conclusion: </strong>This paper serves as a point of reference for HIV researchers interested in applying network models and understanding their limitations. To our knowledge, this is the most comprehensive review of HIV network models to date.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"INCREASING THE ACCESSIBILITY AND RELEVANCE OF IMPLEMENTATION SCIENCE FOR FRONT-LINE IMPLEMENTERS.","authors":"Sarit A Golub, Carly Wolfer, Cody A Chastain","doi":"10.1097/QAI.0000000000003580","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003580","url":null,"abstract":"<p><strong>Background: </strong>Implementation science has been heralded as a critical strategy for ending the HIV epidemic (EHE), and the United States (US) has made a tremendous financial investment in implementation research. However, several dynamics in its development and organization may alienate front-line implementers and recapitulate some of the same missteps that have stymied past translational work.</p><p><strong>Setting: </strong>Increasing the accessibility and relevance of HIV implementation science for front-line implementers (e.g., health department and health systems directors, clinic administrators, program managers, clinicians, and other providers) is critical.</p><p><strong>Methods: </strong>We review current challenges to the meaningful inclusion of front-line implementers in implementation science research, and consider specific changes to language, frameworks, and methods that would maximize the accessibility and relevance of the field.</p><p><strong>Results: </strong>Our analysis suggests the need for greater attention to implementation strategies most relevant to front-line implementers, i.e., those focused on intervention recipients. We propose a novel, multi-layer framework for conceptualizing the strategies necessary to achieve HIV implementation outcomes by organizations, providers, and recipients. There is a compelling rationale to adopt incentive structures that prioritize research questions most important for practice.</p><p><strong>Conclusions: </strong>Maximizing the impact of implementation science on EHE goals requires: (a) expanding the focus of implementation science to include more recipient-focused implementation strategies; (b) developing and applying frameworks that better reflect the experience and needs of front-line implementers; (c) using language most relevant and applicable to practice, and (d) prioritizing actionable research questions that directly address the needs and concerns of those doing implementation work.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142785544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Age of Sexual Debut on HIV Care Engagement among Sexual and Gender Minorities in Nigeria.","authors":"Connor Volpi, Ruxton Adebiyi, John Chama, Uche Ononaku, Abayomi Aka, Andrew Mitchell, Ashley Shutt, Afoke Kokogho, Abdulwasiu B Tiamiyu, Stefan D Baral, Man Charurat, Sylvia Adebajo, Trevor A Crowell, Rebecca G Nowak","doi":"10.1097/QAI.0000000000003574","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003574","url":null,"abstract":"<p><strong>Background: </strong>Sexual and gender minorities (SGM) bear a high burden of HIV. The age of anal sexual debut may influence HIV care engagement. Our objective was to evaluate this relationship to help healthcare providers promote and anticipate future HIV care engagement among at-risk SGM.</p><p><strong>Methods: </strong>The TRUST/RV368 study provided HIV testing and treatment at SGM-friendly clinics in Abuja and Lagos, Nigeria. Self-reported age of sexual debut was dichotomized as <16 or ≥16 years. Multivariable logistic models estimated adjusted odds ratios (aOR) and 95% confidence intervals (CI) for the association of sexual debut with 1) prior HIV testing history, 2) HIV testing at the clinics, 3) initiation of antiretroviral therapy (ART) within 6 months of a clinic diagnosis, 4) viral suppression within 12 months of ART initiation.</p><p><strong>Results: </strong>Of the 2,680 participants, 30% (n=805) reported a sexual debut <16 years. Those with an <16-year debut had significantly more receptive sex partners, condomless sex, and transactional sex (all p<0.01) and were 24% less likely to have tested for HIV before enrollment (aOR: 0.76; CI: 0.62-0.93). However, <16-year debut was not associated with HIV testing, receiving ART or achieving viral suppression once engaged with TRUST/RV368 (all p>0.05).</p><p><strong>Conclusions: </strong>SGM with <16-year debut engaged in behaviors that could increase HIV risk and were less likely to have a history of HIV testing. However, once enrolled in SGM-friendly clinics, uptake of HIV care was not associated with <16-year debut, suggesting that SGM-friendly care models may promote HIV care engagement.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimated Impact of HIV Testing on Length of Stay at Visits to United States Emergency Departments, 2018-2021.","authors":"Brian Kuglen, Carson Clay, Derek Boothroyd, Christopher L Bennett","doi":"10.1097/QAI.0000000000003575","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003575","url":null,"abstract":"","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ALIGNMENT OF PREP USE WITH POTENTIAL HIV EXPOSURE IN YOUNG WOMEN AND MEN IN UGANDA.","authors":"Linxuan Wu, Timothy Ssebuliba, Timothy R Muwonge, Felix Bambia, Gabrielle Stein, Olivia Nampewo, Oliver Sapiri, B Jay Goetz, Kerri J Penrose, Urvi M Parikh, Andrew Mujugira, Renee Heffron","doi":"10.1097/QAI.0000000000003573","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003573","url":null,"abstract":"<p><strong>Background: </strong>Despite high oral pre-exposure prophylaxis (PrEP) uptake among young heterosexual cisgender women, early discontinuation is frequent. It is unclear whether this aligns with potential HIV exposure.</p><p><strong>Methods: </strong>Young women 16-25 years and ≥1 of their male partners were enrolled in separate but linked longitudinal HIV PrEP studies in Kampala, Uganda from 2018-2021. Data on sexual behavior, PrEP use, STI positivity, and Y chromosome DNA (Yc DNA; a marker for condomless sex) were collected at enrollment and quarterly visits. Potential HIV exposure was defined as one of the following in the past 3 months: any STI, detection of Yc DNA, condomless vaginal sex, or multiple sex partners. Alignment between potential HIV exposure and PrEP use by participants was examined using GEE regression.</p><p><strong>Results: </strong>88 young women (median age=20.6, IQR 19.5-22.0) and 124 male partners (median age=23.5, IQR 21.0-26.0) were included. Women and men were dispensed PrEP in 66.9% and 60.5% of their first linked visits, respectively. PrEP dispensation was more common when women or men self-reported condomless vaginal sex and multiple sex partners, or when women had Yc DNA detected in vaginal swabs. Men's self-report of multiple partners (aPR=1.56, p=0.012) and the detection of Yc DNA (aPR=1.52, p=0.040) were significantly associated with women's PrEP dispensation.</p><p><strong>Conclusions: </strong>Women and their male partners may align their PrEP use with their HIV risk behaviors, providing some reassurance that PrEP discontinuation in young people often aligns with sexual behavior. Greater attention to measurement of and mismatches in PrEP discontinuation and potential HIV exposure is needed.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The implications of removing race from interpretation of pulmonary function among persons with or without HIV.","authors":"Richard J Wang, Ken M Kunisaki, Alison Morris, M Bradley Drummond, Mehdi Nouraie, Laurence Huang, Phyllis C Tien, Aaron D Baugh, Igor Barjaktarevic, Neha Bhandari, Surya P Bhatt, Gypsamber D'Souza, Margaret A Fischl, Robert F Foronjy, Robert L Jensen, Deepa G Lazarous, Ighovwerha Ofotokun, Divya Reddy, Valentina Stosor, Meredith C McCormack, Sarath Raju","doi":"10.1097/QAI.0000000000003579","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003579","url":null,"abstract":"<p><strong>Background: </strong>Studies suggest that the use of race-specific pulmonary function reference equations may obscure racial inequities in respiratory health. Whether removing race from the interpretation of pulmonary function would influence analyses of HIV and pulmonary function is unknown.</p><p><strong>Setting: </strong>Pulmonary function measurements from 1,067 men (591 with HIV) in the Multicenter AIDS Cohort Study (MACS) and 1,661 women (1,175 with HIV) in the Women's Interagency HIV Study (WIHS) were analyzed.</p><p><strong>Methods: </strong>Percent-of-predicted values for spirometry and single-breath diffusing capacity of carbon monoxide (DLCO) measurements were generated with race-specific reference equations derived from the National Health and Nutrition Examination Survey and with the race-neutral application of reference equations derived from the Global Lung Function Initiative database. Regression models were used to evaluate the association between HIV and percent-of-predicted measures of pulmonary function. Alpaydin's F test was used to compare how well these values predicted self-reported respiratory health-related quality of life.</p><p><strong>Results: </strong>Persons with HIV were observed to have significantly lower percent-of-predicted DLCO than those without HIV but no significant differences in spirometric measures of pulmonary function, regardless of whether a race-specific or race-neutral approach was used. Among men, but not women, the race-neutral application of reference equations to generate percent-of-predicted DLCO values performed better for predicting respiratory-related quality of life.</p><p><strong>Conclusion: </strong>The race-neutral application of pulmonary function reference equations continues to identify lung function impairment in persons with or at risk for HIV and, for DLCO, may be superior to the use of race-specific reference equations in identifying clinically relevant impairments.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Economic Evaluation of delivering an evidence-based online HIV prevention program to MSM via direct-to-consumer marketing versus community-based organization recruitment.","authors":"Sarah Munroe, Bruce R Schackman, Krystal Madkins, Rana Saber, Kathryn Macapagal, Jocelyn Vititow, Nicholas Sweeney, Noah M Feder, Nanette Benbow, Brian Mustanski, Benjamin P Linas","doi":"10.1097/QAI.0000000000003572","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003572","url":null,"abstract":"<p><strong>Purpose: </strong>This study, conducted as part of the Keep It Up! (KIU!) 3.0 trial, compares the implementation costs of two strategies - centralized direct-to-consumer (DTC) marketing and decentralized distribution via community-based organizations (CBO) - in delivering an evidence-based online HIV prevention program.</p><p><strong>Methods: </strong>We conducted interviews and collected data to identify and quantify all costs for both delivery strategies. Costs were then categorized into start-up and ongoing (time-dependent and variable) costs and assigned dollar values based on established micro-costing protocols.</p><p><strong>Results: </strong>In the DTC arm (1,468 enrollees), the program was implemented from October 2019 through August 2022. Total ongoing costs including overhead and excluding start-up costs were $735,953, averaging $501 per participant. Start-up costs were $398,384 ($376,393 for content design and development and $21,991 for other costs), time-dependent costs were $219,177 ($149 per participant), and variable costs were $491,658 ($335 per participant). In the CBO arm (656 enrollees across 22 sites), KIU! was implemented for a two-year period between October 2019 and December 2022. Total ongoing costs including overhead and excluding start-up costs were $2,780,682 ($4,239 per participant). Start-up costs were $511,528 ($401,141 for content design and development and $110,386 for other costs), time-dependent costs were $1,926,958 ($2,937 per participant), and variable costs were $256,543 ($391 per participant).</p><p><strong>Conclusion: </strong>The DTC arm demonstrated a lower overall cost and a lower cost per participant compared to distribution via the CBO arm. Understanding these cost dynamics is pivotal for guiding decisions on program sustainability and determining funding requirements for future large-scale implementation.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tenofovir Disoproxil Fumarate/Emtricitabine Prophylaxis Has No Effect on Bone Mineral Density and Bone Mineral Content in African Breastfeeding Women Receiving Pre-Exposure Prophylaxis for HIV.","authors":"Gaysheen Kistan, Motshedisi Sebitloane, Carl Lombard, Zukiswa Godlwana, Alicia C Desmond, Richard Clark, James F Rooney, Glenda Gray, Dhayendre Moodley","doi":"10.1097/QAI.0000000000003563","DOIUrl":"https://doi.org/10.1097/QAI.0000000000003563","url":null,"abstract":"<p><strong>Background: </strong>Tenofovir disoproxil fumarate (TDF) when used as preexposure prophylaxis (PrEP) in pregnancy is considered safe overall however there is insufficient evidence of its effect on maternal bone. We compared bone mineral density (BMD) and content (BMC) at the lumbar spine (LS) and hip of African breastfeeding women exposed and not exposed to TDF-containing PrEP in a randomized control trial (RCT).</p><p><strong>Methods: </strong>This is a secondary data analysis of an RCT where pregnant women were randomized to initiating PrEP in pregnancy or delayed initiation of PrEP until breastfeeding cessation. BMD and BMC at the LS and hip were measured using dual-energy x-ray absorptiometry (DXA) at 6, 26, 50, and 74 weeks postpartum. In an exploratory analysis, BMD at the hip and LS were evaluated against varying Tenofovir (TFV) levels during pregnancy.</p><p><strong>Results: </strong>Of 300 women in the RCT who had a DXA at 6 weeks postpartum, 102 (66%) women in the Immediate PrEP arm and 105 (72%) in the Delayed PrEP arm had a 74-week DXA scan. Adjusting for breastfeeding duration and body mass index (BMI), there were no significant differences in BMD or BMC at the hip and LS between treatment arms. There was no consistent dose-effect of TFV-DP detected during pregnancy on BMD at the hip (p=0.231) or the LS (p=0.277).</p><p><strong>Conclusion: </strong>After adjusting for breastfeeding and BMI, TDF when given as oral preexposure prophylaxis during pregnancy had no deleterious effect on BMD and BMC at the hip and LS of African breastfeeding women.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142728685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using machine learning techniques to predict viral suppression among people with HIV.","authors":"Xueying Yang, Ruilie Cai, Yunqing Ma, Hao H Zhang, XiaoWen Sun, Bankole Olatosi, Sharon Weissman, Xiaoming Li, Jiajia Zhang","doi":"10.1097/QAI.0000000000003561","DOIUrl":"10.1097/QAI.0000000000003561","url":null,"abstract":"<p><strong>Background: </strong>This study aims to develop and examine the performance of machine learning (ML) algorithms in predicting viral suppression among statewide people living with HIV (PWH) in South Carolina (SC).</p><p><strong>Methods: </strong>Extracted through the electronic reporting system in SC, the study population was adult PWH who were diagnosed between 2005-2021. Viral suppression was defined as viral load <200 copies/ml. The predictors, includingsocio-demographics, a historical information of viral load indicators (e.g., viral rebound), comorbidities, healthcare utilization, and annual county-level factors (e.g., social vulnerability) were measured in each 4-month windows. Using historic information in different lag time windows (1-, 3- or 5-lagged time windows with each 4-month as a unit), both traditional and ML approaches (e.g., Long Short-Term Memory network [LSTM]) were applied to predict viral suppression. Comparisons of prediction performance between different models were assessed by area under curve (AUC), recall, precision, F1 score, and Youden index.</p><p><strong>Results: </strong>Machine learning approaches outperformed the generalized linear mixed model. In all the three lagged analysis of a total of 15,580 PWH, the LSTM (lag 1: AUC=0.858; lag 3: AUC=0.877; lag 5: AUC=0.881) algorithm outperformed all the other methods in terms of AUC performance for predicting viral suppression. The top-ranking predictors that were common in different models included historical information of viral suppression, viral rebound, and viral blips in the Lag-1 time window. Inclusion of county level variables did not improve the model prediction accuracy.</p><p><strong>Conclusion: </strong>Supervised machine learning algorithms may offer better performance for risk prediction of viral suppression than traditional statistical methods.</p>","PeriodicalId":14588,"journal":{"name":"JAIDS Journal of Acquired Immune Deficiency Syndromes","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142668071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}