Abstract:
Successful implementation of antiretroviral treatment programs insub-Saharan Africa has transformed HlV and AlDS from an emerging global health catastrophe to a manageable chronic condition.The HlVcare cascade is a conceptual model describing key milestones insuccessful delivery of care and treatment for people living with HlVThese include diagnosis of HlV, linkage and retention in careinitiation of antiretroviral therapy, and suppression of viral load.Manycare programs, such as AMPATH in western Kenya, have implemented electronic health records with point-of-care interface for visualizing patient records and entering data in real time. This has improved the ability of care providers to track outcomes and, wherenecessary,intervene to improve them.In this talk we describe development and implementation of a Bayesian decision support module geared toward maximizing retention in care - a critically important component of the cascade.The goal of the project is to identify in advance those patients at highrisk for missed visit, interruption in treatment, and loss to follow upThe project involves building and validating predictive models derived from an electronic health record system, embedding the models in the EHR back end to generate real-time predictions of missing ascheduled visit, and using the predictions to activate pre-visit outreach by clinic staff. Our model addresses several idiosyncrasiesin the data, such as competing risks, discontinuous hazard functionsand missing predictors. We describe how to use the posterior predictive distribution to generate various types of insights, such as flagging patient-level features that explain risk classification and identifying optimal timing for the next appointment. We also show the implementation of the model at the point of care and describe ourplans for evaluating the impact of the decision support process.
About the Speaker:
Joseph Hogan, ScD is Professor and Chair of Biostatistics, andCarole and Lawrence Sirovich Professor of Public Health, at Brown University. His research concerns development and application ofstatistical methods for causal inference, missing data, and Bayesian inference for large-scale observational data and randomized trialswith focus in HlV/AlDS and global infectious disease. Prof Hoganserves as Co-Director of Biostatistics for AMPATH, an international consortium of universities in the US, Canada and Kenya focused on treatment and prevention of HlV in Kenya, Program co-Director for NAMBARl, an NlH-funded biostatistics training partnership between Brown and Moi University in Kenya, and co-Director of the Biostatistics Core for the Providence-Boston Center for AIDS Research. He collaborates with the Rhode Island Department of Health on infectious disease surveillance (COVlD and HlV) and has served as advisor and consultant for the FDA, NIH, NSF and National Academies of Science. Prof Hogan is an elected Fellow ofthe American Statistical. Association and currently serves asStatistical Editor for the New England Journal of Medicine and forNEJM-AI.
Your participation is warmly welcomed!
欢迎扫码关注北大统计科学中心公众号，了解更多讲座信息!
