Share
Article Summary
- Dr. Azizi Seixas contributed to a Journal of Clinical Sleep Medicine commentary on the use of AI in sleep medicine.
- The authors see great potential for AI in clinical care, lifestyle improvements and public health assessments.
- The authors warn AI must be implemented responsibly and without bias.
Artificial intelligence is influencing health and wellness, and sleep medicine is no exception.
A new commentary by Azizi Seixas, Ph.D., interim chair of the Department of Informatics and Health Data Science and associate professor of psychiatry and behavioral sciences at the University of Miami Miller School of Medicine, discusses how the assistive technology can help physicians diagnose sleep disorders, aid consumers and improve community health.
A Potentially Transformative Tool for Sleep
In the opinion piece published in the Journal of Clinical Sleep Medicine, Dr. Seixas joins sleep experts to argue that AI can be a transformative tool in the technology-driven specialty. But there are reasons for caution, as well.
“AI-enabled technology may provide opportunities to improve health care by increasing diagnostic consistency and increasing throughput. As with all medical tools, the benefits must be weighed with potential risks associated with using the tool,” the authors wrote.
Over two years, Dr. Seixas, who is co-lead for The American Academy of Sleep Medicine’s Artificial Intelligence (AI) in Sleep Medicine Committee, identified potential roles for AI based on published sleep studies and clinician and industry expert input. They outline strengths, weaknesses, opportunities and threats for three major areas: clinical care, lifestyle and population health.
Improving Diagnoses, Optimizing Care
AI in the clinical setting can streamline care, monitor patients remotely and help improve the accuracy of sleep diagnoses. It could help doctors identify people at high risk for sleep disorders and minimize or prevent poor outcomes.
In terms of lifestyle factors, AI could optimize and tailor sleep recommendations based on data from wearable devices and smartphone applications. AI-generated feedback and analysis could also help educate patients about sleep quality and promote healthier habits.
The more profound impact could come from population-level insights. The technology can process large amounts of data and recognize trends and patterns on a community level. Public health officials could use that big-data synthesis to develop policies to improve sleep and the overall health of large groups.
AI to Assist, Not Replace
The commentary calls for AI to assist, but not replace, sleep experts. The authors emphasize developing AI algorithms free of bias, which depends in large part on the data upon which it is trained and deployed. Integrating AI into existing clinical systems remains an unanswered question. It should be intuitive and counteract rather than contribute to clinician burnout, Dr. Seixas and colleagues noted.
Patient privacy and data transparency remain paramount. Providers must comprehend the source of AI findings—its “black box algorithms”—so patients understand how the technology generated a diagnosis or treatment plan.
Proper regulation could help minimize risks without unnecessarily delaying its adoption, Dr. Seixas and colleagues wrote.
More research is needed to validate AI’s clinical performance in sleep medicine and to ensure it accurately assesses heterogeneous populations. In addition, successful integration of AI in sleep medicine will require cooperation amongst disparate stakeholders.
The authors wrote, “To harness AI’s full potential, it is crucial to educate our health care community about its capabilities and intricacies while fostering collaboration between researchers, health care professionals and industry stakeholders.”
Tags: AI, American Academy of Sleep Medicine, artificial intelligence, Dr. Azizi Seixas, sleep, sleep medicine
link