2023
DOI: 10.1038/s41586-023-05881-4
|View full text |Cite
|
Sign up to set email alerts
|

Foundation models for generalist medical artificial intelligence

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 … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

1
125
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 541 publications
(187 citation statements)
references
References 31 publications
1
125
0
Order By: Relevance
“…Newer foundational AI models will be able to ingest, analyze, and generate diverse data types. As intuitive user interfaces are layered on top of these models, the geneticist of the future will operate in ways that are very different from today (Lee et al, 2023;Moor et al, 2023). In this piece, we briefly outline our predictions pertaining to the field of medical genetics.…”
Section: Introductionmentioning
confidence: 99%
“…Newer foundational AI models will be able to ingest, analyze, and generate diverse data types. As intuitive user interfaces are layered on top of these models, the geneticist of the future will operate in ways that are very different from today (Lee et al, 2023;Moor et al, 2023). In this piece, we briefly outline our predictions pertaining to the field of medical genetics.…”
Section: Introductionmentioning
confidence: 99%
“…What has changed is the public availability and interest in large language models (LLMs), most notably OpenAI’s ChatGPT and Google’s Bard, with potential applications in medicine. These LLMs are large (1 trillion parameters for GPT-4 and growing), general rather than trained for a specific task (though fine-tuning is possible), autoregressive (using only past data to predict future data), and foundational (likely to be the seed for many further devices and applications) . There has also been interest in creating LLMs with more curated medical training data, such as Google’s Med-PaLM 2.…”
mentioning
confidence: 99%
“…Recent work has discussed applications of ChatGPT for medical education and clinical decision support. [2][3][4] However, health care professionals should be aware of the drawbacks and limitations-and potential capabilities -of using ChatGPT and similar LLMs to interact with medical knowledge.…”
mentioning
confidence: 99%