The health system is launching a project with IBM Research to identify clinical signatures using audio-visual interviews and digital health data from patients 15-30 years old.
As healthcare organizations explore how to use AI to influence patient care, they’re training their sights on ambient and generative AI technology that can sift through data and point providers in the right direction.
The latest to embrace this strategy is Mount Sinai Health Care, whose care teams want to identify young people in need of mental health services and give providers the information to improve care.
The New York-based health system is partnering with IBM Research on what it’s calling the Phenotypes Reimagined to Define Clinical Treatment and Outcome Research (PREDiCTOR) study. The research will use AI tools to comb through not only audio and video interviews but a wide range of digital health data to identify predictive markers that would allow care providers to identify and arrange treatment more quickly and effectively.
“Every clinical visit provides a wealth of untapped behavioral data that includes spoken language, eye contact, and facial expressions from both the patient and clinician,” Cheryl Corcoran, MD, an associate professor of psychiatry at Mount Sinai’s Icahn School of Medicine and co-leader of the research project, said in a press release.
“With advancements in computational approaches, these behaviors can be operationalized and quantified through analysis of audiovisual data obtained from the recording of clinical interviews,” she said. “Coupled with valid behavioral data derived from smartphones that track physical activity metrics like step count and distance traveled, geolocation, social interactions like text messages and phone calls, sleep patterns, and audio data from diaries, we can develop clinical signatures that are indicative of key outcomes.”
The $20 million project, funded by a grant from the National Institute of Mental Health (NIMH), will include researchers from Harvard, Johns Hopkins, Columbia and Carnegie Mellon Universities and use ambient tools developed by Deliberate AI.
The project aims to focus AI on one of the more pressing healthcare issues in the U.S.: the soaring rate of mental and behavioral health concerns. Often the onus of diagnosing these concerns falls on providers who don’t have the background to detect subtle clues.
The research team is focusing on patients between the ages of 15 and 30 who are seeking treatment at one of six Mount Sinai Health outpatient mental health clinics. Researchers say that age range “represents a developmental window during which many disturbances of thought, emotion, and behavior emerge and when diagnoses and prognoses are often still unclear.”
The researchers will combine digital health data with audio and visual recordings of the patients’ visits over a year. They’ll then develop clinical signatures that characterize what those patients present when seeking help, which providers can then use to fine-tune care management.
“Our goal is to gain a better understanding of what predicts whether young people stay in mental health treatment or drop out, and what predicts whether their symptoms worsen such that they need acute care in an emergency crisis center or hospital,” Guillermo Cecchi, PhD, director of the computational psychiatry and neuroimaging groups at IBM Research, said in the press release. “We have shown in our research that artificial intelligence can be used to predict some outcomes in controlled experimental settings, but we believe that current advancements are powerful enough to be applied in the context of usual clinical practice.”
Eric Wicklund is the associate content manager and senior editor for Innovation at HealthLeaders.
KEY TAKEAWAYS
The number of people seeking help for mental and behavioral health concerns is increasing annually, putting pressure on both providers to recognize those issues and health systems to have the resources to treat them.
A federally funded study being launched by the Mount Sinai Health System aims to give providers a better understanding of how to diagnose and treat young patients in need of mental health services.
The study will use AI tools to evaluate audio-visual interviews and digital health data from smartphones, looking for common indicators in patients before they disassociate from care or seek emergency help.