The assistant professor of clinical pediatrics at Indiana University School of Medicine, and the chair of the AASM’s Artificial Intelligence in Sleep Medicine Committee, discussed the potential of AI to progress care paradigms in insomnia. [WATCH TIME: 2 minutes]
WATCH TIME: 2 minutes
“We didn’t really realize that there could be different phenotypes, different clinical expressions of the same disease. So, a person with sleep apnea and insomnia is very different from a person with depression and insomnia, not just in the clinical expression, but in how they respond to different medications.”
The incorporation of artificial intelligence (AI) in day-to-day clinical care has become more widespread in recent years. Many algorithms have been assessed for a variety of purposes, including differential diagnosis and monitoring. In sleep medicine, such technologies have emerged as tools to improve the labor-intensive acts of monitoring and scoring sleep stages.
Realizing the need to validate and verify these software platforms that have been built by a number of companies, the American Academy of Sleep Medicine (AASM) has established a 2-year pilot program, call the AI/Autoscoring Certification Program, which will independently verify the performance of these auto-scoring systems.1 Currently, the focus is solely on polysomnograms for sleep stage scoring, with the software being assessed needing to demonstrate accuracy that is equivalent or better than manual scoring to be certified, with applications to the program accepted starting in late 2022 or early 2023.
To find out more about the potential benefits of AI technologies in clinical practice, particularly for difficult-to-treat, heterogenous conditions such as insomnia, NeurologyLive® spoke with Anuja Bandyopadhyay, MD, assistant professor of clinical pediatrics, Indiana University School of Medicine, and the chair of the AASM’s Artificial Intelligence in Sleep Medicine Committee. She offered her perspective on the state of understanding about insomnia, and how better phenotype-specific treatment can improve care.
Per the AASM, companies using auto-score technology that would like to learn more about the AI/Autoscoring Pilot Certification Program, can contact the AASM at AIGSP@aasm.org.