NIH Reporter #1R21HL184915-01A1

Unlocking Hidden Concurrent Symptom Burdens and Estimating Their Associations with Health Outcomes in People Living with HIV and Co-Morbid Diabetes and Hypertension Through Topic Modeling

The award funds a research project at the University of Texas Health Science Center Houston to study hidden symptom clusters in people living with HIV and co-morbid diabetes and hypertension using topic modeling, aiming to improve understanding of symptom patterns and health outcomes.

Description

This study aims to identify and analyze hidden symptom clusters among people living with HIV (PWH), especially those with co-morbid diabetes and hypertension, using advanced topic modeling techniques such as Latent Dirichlet Allocation (LDA). The research will explore the associations of these symptom clusters with health outcomes like viral failure, mortality, and quality of life measures (VACS index and EQ-5D). The project will stratify patients based on symptom clusters, evaluate differences in clinical and demographic covariates, and develop a new topic model incorporating known diagnoses to derive mixed symptom-covariate clusters.

View original record