With help from artificial intelligence, doctors across medical disciplines will soon be able to consult patients’ entire medical files against a breadth of medical healthcare data and published medical literature.
“We see a paradigm shift coming in the field of medical AI. Previously, medical AI models could only address very small, narrow pieces of the healthcare puzzle. Now we are entering a new era, where it’s much more about larger pieces of the puzzle in this high-stakes field,” explained Jure Leskovec, a computer science professor at Stanford Engineering.
In a new study published in Nature, researchers from Stanford described how generalist medical artificial intelligence (GMAI) is a new category of AI models that is flexible, knowledgeable, and reusable across numerous data types and medical applications.
GMAI can interpret various data combinations drawn from electronic health records, imaging, lab results, medical text, and genomics– an ability that far surpasses other AI models such as ChatGPT.
GMAI will even draw sketches, annotate images, provide explanations, and offer care recommendations.
“A lot of inefficiencies and errors that happen in medicine today occur because of the hyper-specialization of human doctors and the slow and spotty flow of information,” said Michael Moor, the study’s co-first author.
“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.”
There are currently over 500 AI models– designed for clinical medicine– that are approved by the U.S. Food and Drug Administration (FDA). But, most of these models are only able to perform one or two specific tasks. For instance, looking for signs of pneumonia by scanning a patient’s chest X-ray.
However, new advances in the research of foundational models are promising and could solve a much more challenging and diverse range of tasks.