ARiSE Healthcare Network
Advancing AI applications in healthcare through rigorous evaluation
Our Mission
The ARiSE (AI Research and Science Evaluation) Healthcare Network was established in 2024 as a collaboration between clinicians and researchers across academic medical centers to advance the field of healthcare AI by designing and executing rigorous, multi-center research studies. Our network of physicians evaluate AI outputs and AI solutions against use cases, which enables us to run Randomized Controlled Trials using arms like AI alone, AI + doctor, and doctor alone.
Our mission is to empower the healthcare community to effectively integrate emerging AI technologies to advance patient care through rigorous scientific evaluation.
Our Publications
NPJ Digital Medicine
Artificial intelligence tools in supporting healthcare professionals for tailored patient care
Red teaming ChatGPT in medicine to yield real-world insights on model behavior
Clinical entity augmented retrieval for clinical information extraction
NEJM AI
Developing ICU Clinical Behavioral Atlas Using Ambient Intelligence and Computer Vision
JAMA Network Open:
Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial
JAMA Internal Medicine:
Chatbot vs Medical Student Performance on Free-Response Clinical Reasoning Examinations
Clinical Reasoning of a Generative Artificial Intelligence Model Compared With Physicians
JAMA Network:
Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge
The Oxford Handbook of AI Governance:
Artificial Intelligence in Healthcare
Chest Pulmonary:
Acquisition of Cardiac Point of Care Ultrasound Images with Deep Learning
Journal of the American Medical Informatics Association:
OrderRex clinical user testing: a randomized trial of recommender system decision support on simulated cases
Nature Medicine:
Adapted large language models can outperform medical experts in clinical text summarization
Journal of General Internal Medicine:
Comparing IM Residency Application Personal Statements Generated by GPT-4 and Authentic Applicants
Related Press Release and Coverage
- – AAMC
Medical schools move from worrying about AI to teaching it
Faculty used to fret over how artificial intelligence might affect education. Now they’re training medical students how to use it for patient care and research.
- – Artificial Intelligence in Medicine
Artificial Intelligence in Medicine - Real Magic or Technological
Even with respect to empathy, a seemingly human-specific trait, chatbots tend to outperform their human doctor counterparts. But there's more to the story
- – Here are best practices for implementing AI in healthcare
Here are best practices for implementing AI in healthcare
Healthcare’s interest in artificial intelligence shows no obvious signs of slowing down. Major industry events have produced a steady stream of AI products and partnerships, particularly for popular use cases such as clinical documentation, process automation and data aggregation. A vast majority of healthcare systems use AI, according to the “AI Adoption and Healthcare Report […]
- – Bloomberg.com
Why AI Is Better than Doctors at the Most Human Part of Medicine
The hope is that artificial intelligence will eventually do much of the work that makes it difficult for doctors to spend enough time with patients.
- – Newsweek
It's Time To Bring Health Care Systems Into the Digital Age | Opinion
Bringing health care systems into the digital age could reduce administration costs by over 60 percent.
- – ABC7 San Francisco
Can artificial intelligence chatbots outperform human doctors? Here's what new Stanford study found
There's been a lot of conversation and consternation about artificial intelligence and its role in our society. Can a chatbot diagnose what's ailing you or considering medical ethics? Can it be trusted to help make life-or-death decisions? ABC7's Kristen Sze finds out in a new interview with a Stanford doctor.
- – Study suggests physicians make better decisions with help of AI chatbots
Study suggests physicians make better decisions with help of AI chatbots
According to new research, doctors may benefit from an LLM assist when faced with a clinical crossroads.
- – News Center
Study suggests physician’s medical decisions benefit from chatbot
A study showed that chatbots alone outperformed doctors when making nuanced clinical decisions, but when supported by artificial intelligence, doctors performed as well as the chatbots.
- – The Washington Post
ChatGPT is little help for doctors in diagnosing diseases, study finds
The research, conducted with 50 physicians last year, found that using ChatGPT did not significantly improve doctors’ diagnostic reasoning.
- – New York Times
ChatGPT Defeated Doctors at Diagnosing Illness
A small study found ChatGPT outdid human physicians when assessing medical case histories, even when those doctors were using a chatbot.
Leadership
Stanford University
Ethan Goh, MD
Executive Director
Stanford University
Jonathan Chen, MD, PhD
Beth Israel Deaconess Medical Center
Adam Rodman, MD, MPH
Site Leads
Stanford University
Jonathan Chen, MD, PhD
Beth Israel Deaconess Medical Center
Adam Rodman, MD, MPH
University of Virginia
Andrew Parsons, MD, MPH, FACP
University of Minnesota
Andrew Olson, MD, FACP, FAAP
ARiSE Founding Members
Founding Institutions
Jonathan H. Chen MD, PhD leads a clinical informatics research group to empower individuals with the collective experience of the many, combining human and artificial intelligence to deliver better care than either. Dr. Chen founded a company to translate his Computer Science graduate work into an AI system used by students around the world. His expertise is featured in the popular press with over 100 research publications and awards. Dr. Chen continues to practice medicine for the reward of caring for real people and to inspire his research to discover and distribute the latent knowledge embedded in clinical data.
TBD
Joséphine Cool is an adult hospitalist at Beth Israel Deaconess Medical Center. She is the director of the medical procedure service for the hospital medicine group at BIDMC, as well as the director of Point-of-Care Ultrasound Education and Simulation Education for the internal medicine residency program at BIDMC. She is a graduate of the Rabkin Fellowship in Medical Education at the Shapiro Institute, and she holds an SHM/CHEST certificate in Point-of-Care Ultrasound. She further co-founded the Procedural Research and Innovation for Medical Educators (PRIME) consortium. In addition to her work researching AI, Dr. Cool does research in technological innovations including in procedural innovation and competency and use of point-of-care ultrasound.
Jason A. Freed MD is the deputy section chief of Benign Hematology at Beth Israel Deaconess Medical Center and an assistant professor at Harvard Medical School. He completed his residency, chief residency, and fellowship at BIDMC before joining the faculty. He has a number of educational leadership roles at BIDMC and HMS including serving as the associate program director for the internal medicine residency, the director of fellowship education for the department of medicine, and course director for hematology in the Harvard-MIT combined MD program. He does research in medical education and clinical hematology and his work has been published in Academic Medicine, the Journal of General Internal Medicine, and JAMA.
Robert Gallo is a medical informatics research fellow in the Department of Health Policy and the VA Palo Alto Health Care System’s Center for Innovation to Implementation. He obtained his medical degree at Washington University School of Medicine, and subsequently completed his residency training in Internal Medicine at Stanford. Dr. Gallo’s research focuses on inpatient health services delivery, particularly for diabetes and cardiovascular disease. He also has interest in the evaluation and implementation of prediction models.
Dr. Ethan Goh is an experienced healthcare executive with a background in informatics, digital health transformation, and strategic innovation. Through his role as a Stanford healthcare AI researcher, he has successfully led multi-site, grant-funded evaluation studies on Large Language Models applications within healthcare. Prior to Stanford, he was an Internal Medicine clinician, startup founder and technology consultant, working with partners like Google, OpenAI, Roche, Samsung, IDEO, and the NHS in the development, validation and commercialization of digital health products and AI technology. He holds an MD from Imperial College, London, and a Masters in Clinical Informatics and Management from Stanford University.
Laura Holdsworth PhD is a health services researcher and implementation scientist in the Evaluation Sciences Unit at Stanford. She uses a range of qualitative methods in her work, and is experienced in mixed methods research and evaluation. Her specific research interest is in the intersection of health care service processes and patient experiences, with the goal of improving the implementation and delivery of health services.