Will Generalist Medical AI Solve Current Limitations in Clinical AI Tools?
The integration of clinical AI tools into health care faces both skepticism and potential promise. Many physicians, although aware of these tools, remain cautious due to doubts about their quality and safety. Concerns regarding whether AI truly enhances patient care persist, necessitating more robust analysis. However, the rise of generalist medical AI, powered by extensive data and adaptable for various tasks, offers some hope.
Surveys show that although many physicians are aware of clinical AI tools, only a small proportion — between 10% and 30% — has actually used them. Attitudes range from cautious optimism to an outright lack of trust…
参考記事を見る
But excitement does seem to be growing about an approach sometimes called generalist medical AI. These are models trained on massive data sets, much like the models that power ChatGPT and other AI chatbots. After ingesting large quantities of medical images and text, the models can be adapted for many tasks. Whereas currently approved tools serve specific functions, such as detecting lung nodules in a computed tomography (CT) chest scan, these generalist models would act more like a physician, assessing every anomaly in the scan and assimilating it into something like a diagnosis.
