MetroHealth, the Cleveland-based academic medical center, has partnered with Dallas-based Pieces Technologies Inc. to study a conversational artificial intelligence agent designed to allow cancer patients to ask questions in real time about any aspect of their attention, while obtaining information about the social determinants of health. (SDOH).
Under a $2 million Small Business Innovation Research (SBIR) contract from the National Cancer Institute (NCI) within the National Institutes of Health (NIH), Pieces and MetroHealth will implement and study how PiecesChat converses with patients.
“One barrier to advancing cancer care is the material challenge of obtaining real, actionable data from patients. Having an AI tool that is able to converse directly with patients, spend the necessary time with them, and demonstrate empathy will not only help doctors achieve SDOH
information, but also helps categorize findings into actionable data,” R. Douglas Bruce, MD, senior vice president and chief clinical integration officer at MetroHealth System, said in a statement. “MetroHealth has food-for-drug programs, transportation, and a number of other resources that we can offer if we really understand what patients need in a nuanced way. “We look forward to collaborating with Pieces to leverage the unique capabilities of AI to help clinicians take one step closer to resolving the SDOH disparities our patients face.”
A key innovation of the project is extending the patent-pending Pieces SafeRead platform to support conversational AI. The company said its SafeRead system employs highly optimized adversarial AI along with human-in-the-loop (HITL) monitoring to minimize communication errors.
This project will be one of the first rigorous research demonstrations of HITL-based conversational AI in the healthcare space, the organizations said.
“The technology being studied has potentially far-reaching implications across multiple domains, including cancer care, SDOH management, and patient empowerment. For the first time, patients will have broad ability to ask any question or detail about their care to a highly supervised AI,” Ruben Amarasingham, MD, CEO of Pieces, said in a statement.
Pieces said it is leveraging passive and active detection to capture SDOH information during this clinical trial. Working with Amazon Web Services (AWS), Pieces Technologies will leverage Amazon Bedrock, a fully managed service that offers a variety of high-performance foundation models (FMs) to responsibly integrate generative AI capabilities.
The study will measure utilization, effectiveness, reliability, accuracy, empathy, and patient perceptions of the artificial intelligence tool. The study will also help expand Pieces’ hallucination risk classification framework for use in conversational AI, which NIH evaluation panels identified as an opportunity to advance AI safety protocols in the delivery of care. clinic.
