Eugene, Ore.-based Ksana Health is undertaking a multi-institutional research effort aimed at creating a new class of artificial intelligence to advance mental health and substance use disorder treatment and prevention.
The software company was awarded a $17.9 million contract by the U.S. Department of Health and Human Services (HHS) to create a Large Health Behavior Model (LHBM). Its goal is to train AI models on smartphones and other wearables data, including sleep, mobility and language use linked to large scale electronic health records (EHRs).
“This initiative augments Ksana’s current efforts to shift behavioral healthcare from episodic, subjective assessment toward continuous, data-driven health promotion, reducing healthcare spending, improving quality of life, and reaching populations that currently lack access to effective behavioral health support,” said Tony Scripa, Ksana Health COO and project co-investigator, in a statement.
Related
In April, HHS announced the first set of research teams as part of its Advanced Research Projects Agency for Health’s (ARPA-H) Evidence-Based Validation & Innovation for Rapid Therapeutics in Behavioral Health (EVIDENT) initiative. Other participants include Duke University, the Johns Hopkins University School of Medicine and the Yale Stress Center.
Ksana’s project is set to be completed in phases, beginning with a “proof-of-concept” study and pilot data collection, according to the announcement. It will then scale to tens of thousands of participants across multiple health systems.
Participating health systems include Providence, MedStar Health and the University of Washington. Providence and Medstar will lead participant recruitment, while the University of Washington will lead computational modeling work.
Recruitment will begin across Providence this summer, with all patients 18 years and older eligible for participation, the Reno, Wash.-based health system said in a May 14 press release.
Related
Staci Wendt, Ph.D., director of research for the Providence Health Research Accelerator, said participants will download Ksana’s app and participate in activities for three months—and consent to have EHRs included.
“Behavioral factors are a leading cause in a large majority of patient conditions that the health care industry treats,” said Bill Wright, Ph.D., Providence's chief research officer, in a statement. “Given the proliferation of smartphones and watches, if we can harness the sensing capabilities of those devices and link behavioral signals to patient health records, we can build a new model of personalized, proactive behavioral health care. This innovation [will] be a major component of the delivery model of the future.”