AWS' technologies "are truly multimodal, and healthcare is multimodal," Bhatia said. "The foundation models can allow us to build (AI) with less data, faster."
The collaboration will put generative AI models to work across the imaging solutions GE HealthCare manufactures: CT, MRI, ultrasound and X-ray, he said.
"Thirty percent of all data is healthcare data, and some 97% of that data is not used" because it is unstructured, Bhatia said. AI can put that data to work, he said.
Recently, GE HealthCare's foundation model work included an advanced ultrasound image segmentation tool that isolated and identified anatomical structures with over 90% accuracy, requiring little human input, the company said in a press release.
Not a Modern Healthcare subscriber? Sign up today.
Bhatia said the AI segmentation tool worked with "anatomies it has never even seen before," analyzing anatomical structures like fetal heads and breast lesions despite those not being part of the foundation model’s initial training set.
In accelerating the use of AI, the clinician "stays in the loop" and is in charge of, for example, taking sonographs, he said, but the device is better able to guide the clinician toward good imaging. The result is a faster, better path to diagnostic-quality images with potentially fewer images taken, he said.
GE HealthCare already leads the way in use of AI, as for the third year in a row it has been first in the U.S. Food & Drug Administration's list of AI-enabled device authorizations.
GE HealthCare said in the press release it will use Amazon Bedrock, a managed service that provides secure access to the industry's leading foundation models. And internal developers at GE HealthCare will work with Amazon Q Developer, a generative AI–powered assistant to accelerate software development by generating real-time code suggestions and securely completing tasks.
"The company also expects to use Amazon Q Business to explore the intersection of multimodal clinical and operational data with an aim of reducing the cognitive burden on physicians, enabling personalized care and increasing efficiency," the press release said.
Download Modern Healthcare’s app to stay informed when industry news breaks.
AWS' capacity is complementary to GE HealthCare's needs, Bhatia said, providing selection, scale and security to its efforts to customize and accelerate AI use.
He said the deep solutions and easy-to-navigate choices available from AWS are "enterprise-grade," allowing GE HealthCare to scale up AI tools throughout the company and across numerous clinical applications.
“Our work with AWS is a big step towards helping clinicians make medical care simpler, more efficient and deeply personalized. It's about advancing the way we care for people everywhere, one innovative solution at a time," Global Chief Science and Technology Officer Dr. Taha Kass-Hout said in the release.
This story first appeared in Crain's Chicago Business.
