About us

Healthcare is far from equitable; many individuals around the world do not receive the standard of care they require. One major reason is the lack of medical professional resources. Artificial intelligence (AI) based on machine learning (ML) offers potential solutions to bridge this gap and transform healthcare into equitable learning health systems (LHS). Notably, the recently emerged generative pre-trained transformers (GPT) that leverage large language models (LLM) of neural networks can effectively engage in natural language interactions with humans. This breakthrough opens up a new world of opportunities to actualize equitable healthcare.

 

Our team has been engaged in healthcare AI/ML research, working collaboratively with clinical teams in many areas such as:

  1. GenAI copilot for medical education, clinical case studies, and benchmarking.

  2. EHR machine learning for predictive care.

  3. Development of LHS units for equitable health care tasks.  

  4. Synthetic patient data to expedite healthcare AI and LHS research.  

 

Some Representative Research Results

Chatgpt in Medical Education

We have incorporated ChatGPT into LHS training and evaluated its precision in furnishing scientific references (refer to JAMA paper below). A comprehensive benchmarking study of ChatGPT for a wide array of diseases is currently under peer review.

ML-LHS Simulation with synthetic data

We pioneered the simulation of ML-empowered LHS units using synthetic patient data (refer to Nature paper below). With insights gleaned from these simulations, our clinical collaborators are building ML-LHS units aimed at disease screening and early detection. Related papers are under review.

Practical and Inclusive ML Models

We have developed cancer risk prediction ML models that are both practical and inclusive for implementation in LHS units by hospitals and community/rural clinics (see the cancer prevention paper below). This data-driven hybrid approach is versatile and can be applied across various diseases.

Recent Publications
 

Chen A, Chen DO. Accuracy of Chatbots in Citing Journal Articles. JAMA Netw Open. 2023;6(8):e2327647. doi:10.1001/jamanetworkopen.2023.27647

 

Chen A. et al. Development of Inclusive and Practical Disease Risk Prediction Machine Learning Models for Implementation of Learning Health Systems. Poster presentation, AcademyHealth ARM 2023, 6/26/2023.

 

Chen A, Lu R, Han R, et al. Building practical risk prediction models for nasopharyngeal carcinoma screening with patient graph analysis and machine learning. Cancer Epidemiol Biomarkers Prev. 2022:EPI-22-0792. doi:10.1158/1055-9965.EPI-22-0792.

 

Chen A, Huang R, Wu E, et al. The Generation of a Lung Cancer Health Factor Distribution Using Patient Graphs Constructed From Electronic Medical Records: Retrospective Study. J Med Internet Res. 2022;24(11):e40361. doi:10.2196/40361.

 

Chen A, Chen DO. Simulation of a machine learning enabled learning health system for risk prediction using synthetic patient data. Nature Sci. Rep. 2022;12(1):17917. doi:10.1038/s41598-022-23011-4.

 

Haendel MA, Chute CG, Bennett TD, et al; N3C Consortium. The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment. J Am Med Inform Assoc. 2021;28(3):427–443. doi:10.1093/jamia/ocaa196. 

 

Chen A, Shen B, Zhang R, et al. Developing new event-driven CBK network for global real-time clinical collaborations. Learning Health Systems. 2021;5(2):e10256. doi:10.1002/lrh2.10256.

 

Chen A, et al. Feasibility study for implementation of the AI-powered Internet+ Primary Care Model (AiPCM) across hospitals and clinics in Gongcheng county, Guangxi, China. The Lancet. 2019;394(Supplement 1):S44. doi:10.1016/S0140-6736(19)32380-3.

 

Additionally, we have initiated the LHS Tech Forum Initiative at the Learning Health Community, a nonprofit dedicated to advancing NAM’s LHS vision. Furthermore, we launched the Open LHS Initiative on GitHub to foster community engagement and data sharing, including Open Synthetic Patient Data repository on GitHub, Synthetic Patient Data ML Dataverse in the Harvard Dataverse.

 

To support clinical teams in getting started with AI/ML-enabled LHS, we created the first open “Learning Health System Practical Guide” on GitHub, focused on the new “ML-LHS unit” practical approach to building AI/ML and LHS.

 

With our effective tools and expertise in AI/ML/LHS research, we are committed to support medical students and professionals around the world in their medical education and clinical research endeavors.