A new study, recently published in the journal Nature, claims that artificial intelligence systems could change the technological landscape and potential in medicine.
The Stanford team and their collaborators view generalist medical artificial intelligence (GMAI) as a new class of medical AI models that are informed, flexible, and reusable across many medical applications.
GMAI will outperform the abilities of concurrent models like ChatGPT. GMAI will have the ability to interpret varying combinations of data from imaging, electronic health records, lab results, genomics, and medical text, and offer feedback and treatment pathways.
Michael Moor, an MD and Postdoctoral Scholar at Stanford Engineering, said, “The potential impact of generalist medical AI models could be profound because they wouldn’t be just an expert in their own narrow area, but would have more abilities across specialties”.
Researchers outlined how GMAI will be able to offer unprecedented potential to perform a variety of tasks simultaneously. GMAI may be able to note-take, converse with patients directly, and even suggest treatment plans or make the recommended referrals.
In their research paper, the co-authors stated that verification is the largest problem for generalist models in medicine. Therefore, the appropriate safeguards must also be developed in regards to overseeing patient health to ensure inaccuracies are avoided.
Additionally, it is the responsibility of the owners and developers of such models to ensure that biases are identified and addressed.
Overall, GMAI could shift the paradigm and provide medical professionals the extra support they need to deliver high-quality, accessible healthcare.
Source: Stanford News
Image Credit: iStock