A new artificial intelligence model can use information collected during routine sleep studies to determine patients’ long-term health risks, according to a… A study published in the journal Nature Communications. The model, developed by a multidisciplinary research team, revealed hidden sleep patterns linked to a higher risk of heart disease, cognitive decline and death.
The results also suggest that other routine medical tests may contain much more information than is currently extracted in clinical practice. AI picked up signals on record overnight He sleeps Study data that is not captured by traditional summary measures alone.
The research revealed that there are subtypes of patients with sharply different long-term health risks. Patients in the highest-risk group had twice the risk of dying over the next five years than those in the lowest-risk group. This distinction is not captured by the standard clinical measure used to assess the severity of sleep apnea, the apnea-hypopnea index.
Each year in the United States, 1 to 4 million studies are performed in sleep laboratories, usually to evaluate sleep apnea. While these studies collect rich data about each patient’s brains, lungs, muscles and heart, doctors have historically narrowed their focus to a small subset of that information to assess the severity of sleep apnea.
“For decades, we have distilled the study of overnight sleep into a few brief measures,” said Dr. Hans, a sleep medicine specialist. Reena Mehraprofessor of medicine at the University of Washington School of Medicine and lead author of the study. “AI gives us the opportunity to go beyond those abstracts and learn from the full richness of sleep physiology.”
The model was developed by a team of sleep doctors, AI researchers, data scientists and neuroscientists brought together by Discovery acceleratora 10-year research partnership between Cleveland Clinic and IBM. The program aims to accelerate the pace of discovery in the life sciences through artificial intelligence and quantum computing.
Using data from the Sleep Signals, Tests, and Reports Associated with Patient Characteristics (STARLIT) registry at Cleveland Clinic, researchers grouped patients into five risk categories. The model predicted good outcomes for both men and women, while the apnea-hypopnea index has historically performed better in men. The results were independently confirmed in a nationwide patient population.
“Modern artificial intelligence allows us to recover more information contained in the physiology of sleep for a single night, revealing clinically important patient groups with very different long-term health risks,” said the corresponding author. Jeffrey L. Rogersa global research leader at IBM and assistant professor of neurosurgery at Yale University School of Medicine.
The model could also help researchers better understand how sleep affects health. Instead of relying on standard measures, it uses artificial intelligence to detect subtle physiological patterns invisible to the naked eye that can help predict the risk of heart disease, neurological disorders and death, opening the door to earlier, more personalized care.
“Nearly 70 million Americans live with chronic sleep-wake disorders, which impact daily functioning and overall health. This discovery offers a more personalized approach to sleep medicine by expanding the value of routine sleep testing and reinforcing the key role sleep plays in chronic disease.” Matthews Lima Deniz Araujo, He is an applied healthcare computer scientist and sleep researcher at the Cleveland Clinic.
“Sleep is increasingly recognized as a critical component of health, yet the physiological information captured during sleep remains largely untapped,” said Erhan Bilal, founder of Inkyra, a former IBM researcher and lead author of the study.
“As these methods continue to be validated in future studies, they have the potential to transform sleep study from primarily a diagnostic test to a richer source of information about an individual’s future health and may accelerate discoveries about the relationships between sleep physiology and chronic disease,” Mehra said.
source: University of Washington
