Evaluating the Utility of Personal Health Records in Personalized Health AI
The study evaluates the effectiveness of Personal Health Records (PHRs) in enhancing responses from large language models (LLMs) for patient health inquiries. Results indicate that incorporating PHR data significantly improves the helpfulness, safety, accuracy, and personalization of answers. The research highlights the potential of PHRs to assist users in understanding their health while identifying areas for further improvement in LLM comprehension.
- ▪The study assessed 2,257 user queries to evaluate LLM responses with and without PHR context.
- ▪Significant improvements in answer helpfulness were observed when PHR data was included.
- ▪The research developed a new framework to identify gaps in LLM understanding of complex PHRs.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.18937 (cs) [Submitted on 18 May 2026] Title:Evaluating the Utility of Personal Health Records in Personalized Health AI Authors:Rory Sayres, Kejia Chen, Ayush Jain, Matthew Thompson, Jonathan Richina, Xiang Yin, Jimmy Hu, Fan Zhang, Bob Lou, Mike Sanchez, Ines Mezerreg, Meredith Schreier, Hamsa Subramaniam, I-Ching Lee, Yugang Jia, Daniel Mcduff, Yossi Matias, Avinatan Hassidim, Dale Webster, Yun Liu, Jackie Barr, Quang Duong View a PDF of the paper titled Evaluating the Utility of Personal Health Records in Personalized Health AI, by Rory Sayres and 21 other authors View PDF Abstract:Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex,…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
