Advanced RAG-LLM Prototype AI on PubMed for Cardiac Health
conference paper
Healthy lifestyle behaviours are effective in preventing and treating cardiovascular disease. However, the growing body of scientific literature and the prevalence of conflicting studies make it challenging for healthcare practitioners and patients to stay informed. Large Language Models (LLMs), combined with Retrieval-Augmented Generation (RAG), enable automated claim verification and summarization. We enhanced RAG-LLM with extra modules and evaluated performance. Inclusion-Criteria-based filtering of PubMed papers improved verdict performance. Next, for health claims, PICO-based (Population, Intervention, Comparison, Outcome) paper mapping and summarization improves transparency of evidence used for verdict generation (like ‘Berries reduce blood pressure’). Still, the RAG-LLM models we tested have biases towards positivity (too many foods deemed heart healthy) and neutrality (no clear direction). We discuss mechanisms at play and challenges on the route forward. © The authors
Topics
TNO Identifier
1015049
ISBN
9789612869984
Publisher
University of Maribor Press
Source title
38th Bled eConference: Empowering Transformation: Shaping Digital Futures for All, June 8-11, Bled, Slovenia 2025
Editor(s)
Pucihar, A.
Kljajić Borštnar, M.
Blatnik, S.
Marolt, M.
Bons, R.
Smit, K.
Glowatz, M.
Kljajić Borštnar, M.
Blatnik, S.
Marolt, M.
Bons, R.
Smit, K.
Glowatz, M.
Place of publication
Maribor, Slovenia
Pages
265-279