A research team led by Dr. Qi Long and Dr. Robert Gross has received a six-million, five-year R01 grant from NIH/NIMH to develop accurate, efficient and unbiased multimodal AI models for HIV prevention and care, harnessing rich information from multimodal data in electronic health records. In this project, the team will also develop and maintain an interpretable multimodal HIV knowledge graph with continuous updates using multimodal medical LLMs, and then integrate the multimodal AI models with HIV knowledge graphs to enhance biomedical reasoning capabilities for clinical decision support.
The AI models will be used and validated in three important use cases in HIV prevention and care, namely, 1) identification of HIV patients at risk of medication non-adherence and/or loss to care; 2) prediction of complications of HIV patients; and 3) identification of patients at high risk of HIV infection. The project will also develop collaborative, equitable partnerships and meaningful engagement between researchers and community members throughout the research process, which will be led by Dr. Florence Momplaisir.
The research team also includes Dr. Jessie Torgersen from Penn Medicine as well as collaborators from UNC, Emory, Yale and VA.