Shumit Saha, a researcher at Kennesaw State University, has been awarded a $235,520 grant from the National Institutes of Health (NIH) to explore the use of artificial intelligence in analyzing snoring patterns related to obstructive sleep apnea (OSA). This condition, where breathing intermittently halts during sleep, can lead to daytime fatigue and more severe health issues if untreated.
Read More
Saha's project aims to develop AI tools to identify where the upper airway collapses during sleep and to predict how patients might respond to hypoglossal nerve stimulation, a treatment that uses electrical signals to keep the airway open.
OSA often results from blockages in the upper airway, leading to serious risks such as high blood pressure, stroke, and heart failure if left unmanaged. Continuous positive airway pressure (CPAP) therapy is a standard treatment, though Saha notes that many patients struggle with the discomfort of the necessary mask. Alternative treatments include jaw repositioning devices, surgery, and hypoglossal nerve stimulation.
Saha emphasizes the importance of personalizing treatment, stating that responses to therapies vary among individuals. The research seeks to predict which treatment will be most effective for each patient, potentially reducing the need for trial and error.
The study has two primary objectives: first, to determine if snoring patterns can reveal the location of airway collapse, which typically would require invasive procedures to assess. Non-invasive analysis could streamline this process. Second, the research will investigate if these snoring sounds can indicate a patient’s likely response to hypoglossal nerve stimulation.
To conduct the study, Saha will analyze snoring data collected by collaborators at Brigham and Women’s Hospital and Harvard Medical School. He will employ machine-learning and deep-learning techniques to identify patterns related to obstruction locations and treatment responses.
The ultimate goal is to create an AI tool that can analyze snoring sounds and provide clinicians with a report that predicts both the site of obstruction and treatment efficacy. This innovation could lead to quicker, more informed treatment decisions, potentially saving time and reducing healthcare costs for patients with sleep apnea.
This research is funded under NIH Grant No: 1R21HL188520-01.