KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry
This work addresses the critical need for accurate and efficient alternatives to resource-intensive polysomnography for diagnosing Obstructive Sleep Apnea, a disorder affecting nearly one billion people globally.
This paper introduces KindSleep, a deep learning framework that diagnoses Obstructive Sleep Apnea (OSA) by integrating clinical knowledge with oximetry signals and clinical data. KindSleep accurately estimates Apnea-Hypopnea Index (AHI) scores with R2 = 0.917 and ICC = 0.957, and outperforms existing methods in classifying OSA severity with weighted F1-scores ranging from 0.827 to 0.941 across diverse populations.
Obstructive sleep apnea (OSA) is a sleep disorder that affects nearly one billion people globally and significantly elevates cardiovascular risk. Traditional diagnosis through polysomnography is resource-intensive and limits widespread access, creating a critical need for accurate and efficient alternatives. In this paper, we introduce KindSleep, a deep learning framework that integrates clinical knowledge with single-channel patient-specific oximetry signals and clinical data for precise OSA diagnosis. KindSleep first learns to identify clinically interpretable concepts, such as desaturation indices and respiratory disturbance events, directly from raw oximetry signals. It then fuses these AI-derived concepts with multimodal clinical data to estimate the Apnea-Hypopnea Index (AHI). We evaluate KindSleep on three large, independent datasets from the National Sleep Research Resource (SHHS, CFS, MrOS; total n = 9,815). KindSleep demonstrates excellent performance in estimating AHI scores (R2 = 0.917, ICC = 0.957) and consistently outperforms existing approaches in classifying OSA severity, achieving weighted F1-scores from 0.827 to 0.941 across diverse populations. By grounding its predictions in a layer of clinically meaningful concepts, KindSleep provides a more transparent and trustworthy diagnostic tool for sleep medicine practices.