KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry

TL;DR

KindSleep is a deep learning framework that combines clinical knowledge and oximetry data to accurately diagnose obstructive sleep apnea, offering a resource-efficient alternative to traditional methods.

Contribution

The paper introduces KindSleep, a novel AI model that integrates clinical concepts with multimodal data for improved OSA diagnosis and interpretability.

Findings

Achieves high accuracy in estimating AHI (R2=0.917, ICC=0.957).

Outperforms existing methods in classifying OSA severity.

Demonstrates robustness across diverse datasets.

Abstract

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.