Leidos’ Srini Iyer on Using Domain-Specific Generative AI in Health Care Application Development

Srini Iyer, senior vice president and chief technology officer for the health and civil sector at Leidos, said that instead of using a foundational artificial intelligence model, the company has built a health care application around a domain-specific generative AI model to further speed up the approval processing time for disability benefits.

Leidos said Wednesday Iyer’s team collaborated with a group led by Ken Su, senior outbound product manager in the CloudAI for health care group at Google, to develop the new application around a health care-specific domain model called Medical Pathways Language Model 2, or MedPaLM2, from Google.

“In a span of about six weeks, we were able to go from a concept to a demo version of a full-stack genAI application,” Iyer said.

The Leidos executive cited the importance of using a domain-specific model in health care settings.

“Understanding the different meanings of words and other data in healthcare is one reason it’s critical to use a domain-specific model,” Iyer stated.

He noted that the company worked on the application based on Leidos’ Framework for AI Resilience and Security, adding that “security and reliability are baked in.”

Iyer said he is looking at other areas in health care that could benefit from a domain-specific generative AI model.

“The entire process of claims management is an opportunity to use AI to reduce waste and abuse,” he said. “I’d also like to see if genAI can address the issue of data interoperability and eventually provide clinical decision support. There are just so many use cases for AI in healthcare; we can leverage the technology in numerous ways.”