Abstract Advancing precision medicine requires integrating clinical, genomic, and social determinants of health (SDoH) data to uncover disease mechanisms, personalize care, and address disparities. However, current tools often lack the capacity to handle SDoH variables and present technical barriers that limit accessibility—particularly for underserved populations. To overcome these challenges, we developed AI-HOPE-PM, a conversational Artificial Intelligence (AI) system enabling real-time, natural language-driven cancer analysis. The platform unifies large-scale clinical, genomic, and SDoH data in a user-friendly interface to support inclusive, multi-dimensional research. Methods: AI-HOPE-PM combines large language models, structured natural language processing, and a Python-based workflow engine to automate cohort selection, analysis, and visualization. It operates on harmonized datasets (TCGA, cBioPortal, AACR GENIE) enhanced with simulated SDoH variables (e.g., financial strain, food insecurity). Free-text queries are translated into executable scripts aligned with biomedical ontologies, supporting survival analysis, odds ratio testing, and case-control comparisons. Results: The platform executed real-time analyses on colorectal cancer (CRC) datasets from Hispanic/Latino populations. It identified survival differences linked to TP53 mutations and financial strain (p = 0.04), APC status and healthcare access (p = 0.02), and additional outcomes associated with food insecurity, social support, and health literacy. Odds ratio analyses highlighted disparities in chemotherapy exposure and KRAS mutation prevalence by sex and literacy. All analyses were completed in under one minute. Conclusions: AI-HOPE-PM offers a scalable, accessible solution for integrative precision oncology. By contextualizing molecular data within social frameworks through natural language interaction, it enhances hypothesis generation, supports biomarker discovery, and advances population-aware treatment strategies. Citation Format: Enrique Velazquez-Villarreal, Brigette Waldrup, Ei-Wen Yang. Artificial intelligence for precision medicine: A conversational system integrating clinical, genomic, and social determinants of health data abstract. In: Proceedings of the 18th AACR Conference on the Science of Cancer Health Disparities; 2025 Sep 18-21; Baltimore, MD. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2025;34(9 Suppl):Abstract nr C010.
Velazquez‐Villarreal et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: