Tag
HealthClaw is an open-source agent architecture for longitudinal personal health management that uses self-evolving memory to improve support over repeated encounters, achieving higher accuracy and privacy compared to baselines across biomedical tasks.
RubricsTree proposes a scalable, expert-aligned evaluation framework for personal health agents using over 100 atomic Boolean rubrics, achieving up to 66% relative gains on HealthBench across Gemini, GPT, and Qwen model families.
This study evaluates the use of large language models (Gemini 3.0 Flash) with personal health records to answer patient health queries, finding significant improvements in helpfulness, safety, and personalization when PHR context is provided.
This article critiques Mark Kaplan's approach to fine-tuning medical LLMs via his platform healtthruth.ai, highlighting pitfalls in overriding foundational training for healthcare AI.
Perplexity has launched Perplexity Health, a feature that allows users to ask health questions across their medical records, lab results, and wearable device data.
OpenAI introduces ChatGPT Health, a dedicated experience with enhanced privacy and security features that allows users to securely connect medical records and wellness apps to receive more personalized health guidance. The feature addresses the common use case of health queries on ChatGPT (230+ million weekly users) while maintaining strict data isolation and declining to use health conversations for model training.