Strategies of Managing Repeated Measures: Using Synthetic Random Forest to Predict HIV Viral Suppression Status Among Hospitalized Persons with HIV.

The HIV/AIDS epidemic remains a major public health concern since the 1980s; untreated HIV infection has numerous consequences on quality of life. To optimize patients' health outcomes and to reduce HIV transmission, this study focused on vulnerable populations of people living with HIV (PLWH) and compared different predictive strategies for viral suppression using longitudinal or repeated measures. The four methods of predicting viral suppression are (1) including the repeated measures of each feature as predictors, (2) utilizing only the initial (baseline) value of the feature as predictor, (3) using the last observed value as the predictors and (4) using a growth curve estimated from the features to create individual-specific prediction of growth curves as features. This study suggested the individual-specific prediction of the growth curve performed the best in terms of lowest error rate on an independent set of test data.

A study protocol for Project I-Test: a cluster randomized controlled trial of a practice coaching intervention to increase HIV testing in substance use treatment programs.

BACKGROUND: People with substance use disorders are vulnerable to acquiring HIV. Testing is fundamental to diagnosis, treatment, and prevention; however, in the past decade, there has been a decline in the number of substance use disorder (SUD) treatment programs offering on-site HIV testing. Fewer than half of SUDs in the USA offer on-site HIV testing. In addition, nearly a quarter of newly diagnosed cases have AIDS at the time of diagnosis. Lack of testing is one of the main reasons that annual HIV incidences have remained constant over time. Integration of HIV testing with testing for HCV, an infection prevalent among persons vulnerable to HIV infection, and in settings where they receive health services, including opioid treatment programs (OTPs), is of great public health importance. METHODS/DESIGN: In this 3-arm cluster-RCT of opioid use disorders treatment programs, we test the effect of two evidence-based "practice coaching" (PC) interventions on the provision and sustained implementation of on-site HIV testing, on-site HIV/HCV testing, and linkage to care. Using the National Survey of Substance Abuse Treatment Services data available from SAMHSA, 51 sites are randomly assigned to one of the three conditions: practice coach facilitated structured conversations around implementing change, with provision of resources and documents to support the implementation of (1) HIV testing only, or (2) HIV/HCV testing, and (3) a control condition that provides a package with information only. We collect quantitative (e.g., HIV and HCV testing at 6-month-long intervals) and qualitative site data near the time of randomization, and again approximately 7-12 months after randomization. DISCUSSION: Innovative and comprehensive approaches that facilitate and promote the adoption and sustainability of HIV and HCV testing in opioid treatment programs are important for addressing and reducing HIV and HCV infection rates. This study is one of the first to test organizational approaches (practice coaching) to increase HIV and HIV/HCV testing and linkage to care among individuals receiving treatment for opioid use disorder. The study may provide valuable insight and knowledge on the multiple levels of intervention that, if integrated, may better position OTPs to improve and sustain testing practices and improve population health. TRIAL REGISTRATION: ClinicalTrials.gov NCT03135886. Registered on 2 May 2017.