Foundation models for generalist medical artificial intelligence

Moor, Michael; Banerjee, Oishi; Abad, Zahra Shakeri Hossein; Krumholz, Harlan M.; Leskovec, Jure; Topol, Eric J.; Rajpurkar, Pranav

doi:10.1038/s41586-023-05881-4

reviewNatureApr 12, 2023HYBRID OA

Foundation models for generalist medical artificial intelligence

MMMichael MoorOBOishi Banerjee ZSZahra Shakeri Hossein Abad HMHarlan M. Krumholz JLJure Leskovec

Stanford University · Harvard University · +6 more institutions

PubMed

Indexed incrossrefpubmed

Abstract

The exceptionally rapid development of highly flexible, reusable artificial intelligence (AI) models is likely to usher in newfound capabilities in medicine. We propose a new paradigm for medical AI, which we refer to as generalist medical AI (GMAI). GMAI models will be capable of carrying out a diverse set of tasks using very little or no task-specific labelled data. Built through self-supervision on large, diverse datasets, GMAI will flexibly interpret different combinations of medical modalities, including data from imaging, electronic health records, laboratory results, genomics, graphs or medical text. Models will in turn produce expressive outputs such as free-text explanations, spoken recommendations or…

Citation impact

1,501

total citations

FWCI: 247.32
Percentile: 100%
References: 50

Citations per year

Authors

7

MM
Michael Moor
Stanford University
OB
Oishi Banerjee
Harvard University
ZS
Zahra Shakeri Hossein Abad
University of Toronto, Public Health Ontario
HM
Harlan M. Krumholz
Yale New Haven Hospital, Yale University
JL
Jure Leskovec
Stanford University

Topics & keywords

Topics

Keywords

Computer science
Set (abstract data type)
Artificial intelligence
Modalities
Task (project management)
Data science
Machine learning

No related works found for this paper.