
ELHS Institute founder Dr. AJ Chen was invited to deliver a keynote at the Tsinghua Heath AI Summit. Given the unprecedented predictive capabilities of generative AI (GenAI) based on large language models (LLMs), a critical question arises: how can GenAI be applied to improve clinical diagnosis across all diseases and populations, thereby reducing global health disparities at scale? The answer may lie in the convergence of GenAI and Learning Health Systems (LHS).
Dr. Chen presented the vision of LHS as articulated by the U.S. National Academy of Medicine. To enable more efficient implementation of LHS, the ELHS Institute pioneered a novel machine learning-enabled LHS (ML-LHS) unit concept, demonstrated by the first simulation of an ML-LHS unit for cancer prediction (published by Nature). Following benchmarking studies of ChatGPT for accurate disease prediction (published in JAMIA) and the fine-tuning of open-source LLMs to achieve higher accuracy at lower cost, we proposed the convergence of GenAI and LHS as a practical pathway to democratize high-standard health care for all populations.
This convergence positions GenAI as an engine for scalable clinical evidence generation and dissemination within LHS units, while LHS provides GenAI with an embedded research framework for continuous learning and improvement—ensuring the responsible use of GenAI in health care. Drawing on our pilot clinical studies and award-winning solutions, we support clinical teams in applying the GenAI–LHS convergence to both research and routine care through three stages:
Conference: Beijing-Tsinghua Health AI Summit (BEIHAI 2025)
Data Time: 11:10 AM on October 23-25, 2025
Organizer: Tsinghua Medicine, Tsinghua University
Location: Tsinghua University, Beijing, China
Democratizing GenAI and LHS to Advance Global Health Equity
info@elhsi.org
Palo Alto, California, USA
