A Knowledge Database of Physical Activity Interventions for Hypertension using Large Language Models

Physical exercise lowers blood pressure, but guidelines address broad populations and rarely consider age, comorbidities, medications or baseline severity. No structured, queryable database of exercise interventions for hypertension exists, and manual curation is not scalable. We present PAHD (Physical Activity for Hypertension Database), built with large language models (LLMs). An LLM screened 2,548 PubMed records by title and abstract, then full text, selecting 255 studies. LLMs extracted each study's groups, exercise protocols, patient characteristics and results; two LLMs cross-checked the study structure, and every value carries a verbatim quote. Code standardized and joined the extractions into 17,312 records from 254 studies, one per reported comparison. Against adjudicated benchmarks, screening reached 86.3% recall and 80.6% precision, and extraction recovered 90.1% of blood pressure values with 90.5% precision. A web portal matches patients' hypertension stage and comorbidities to studies. PAHD provides a structured evidence base for personalized exercise interventions on hypertension management.