Open-Source AI Matches Top Proprietary LLM in Solving Tough Medical Cases
Greater competition between AI diagnostic tools should benefit patients and clinicians
Greater competition between AI diagnostic tools should benefit patients and clinicians
At a glance:
Artificial intelligence can transform medicine in myriad ways, including its promise to act as a trusted diagnostic aide to busy clinicians.
Over the past two years, proprietary AI models, also known as closed-source models, have excelled at solving hard-to-crack medical cases that require complex clinical reasoning. Notably, these closed-source AI models have outperformed open-source ones, so-called because their source code is publicly available and can be tweaked and modified by anyone.
Has open-source AI caught up?
The answer appears to be yes, at least when it comes to one such open-source AI model, according to the findings of a new NIH-funded study led by researchers at Harvard Medical School and done in collaboration with clinicians at Harvard-affiliated Beth Israel Deaconess Medical Center and Brigham and Women’s Hospital.
The results, published March 14 in JAMA Health Forum, show that a challenger open-source AI tool called Llama 3.1 405B performed on par with GPT-4, a leading proprietary closed-source model. In their analysis, the researchers compared the performance of the two models on 92 mystifying cases featured in The New England Journal of Medicine weekly rubric of diagnostically challenging clinical scenarios.
The findings suggest that open-source AI tools are becoming increasingly competitive and could offer a valuable alternative to proprietary models.
“To our knowledge, this is the first time an open-source AI model has matched the performance of GPT-4 on such challenging cases as assessed by physicians,” said senior author Arjun Manrai, assistant professor of biomedical informatics in the Blavatnik Institute at HMS. “It really is stunning that the Llama models caught up so quickly with the leading proprietary model. Patients, care providers, and hospitals stand to gain from this competition.”
Open-source AI and closed-source AI differ in several important ways. First, open-source models can be downloaded and run on a hospital’s private computers, keeping patient data in-house. In contrast, closed-source models operate on external servers, requiring users to transmit private data externally.
“The open-source model is likely to be more appealing to many chief information officers, hospital administrators, and physicians since there’s something fundamentally different about data leaving the hospital for another entity, even a trusted one,” said the study’s lead author, Thomas Buckley, a doctoral student in the new AI in Medicine track in the HMS Department of Biomedical Informatics.
© 2025 by the President and Fellows of Harvard College