Weakly Supervised Deep Learning for Monitoring Sleep Apnea Severity Using Coarse-Grained Labels

Sleep apnea, a prevalent sleep-related breathing disorder, often remains undiagnosed and untreated in a large patient population due to the need of extensive manual annotations on various physiological signals for clinical diagnosis. Despite the surge of interest in applying machine learning to automate apnea detection, the effectiveness of existing techniques highly relies on strongly supervised learning that requires massive finely labeled training data for sufficiently short time intervals - a requirement often unmet due to the prohibitively high cost of manual labeling in clinical practice. In this article, we incorporate clinical knowledge to establish a weakly supervised deep learning framework for automatically estimating the latent fine-grained apnea severity when only coarse-grained labels indicating apnea presence are available in the training data. Specifically, a novel knowledge-enhanced dual-granularity consistency loss, which simultaneously considers the consistency between coarse- and fine-granularity and the integration of clinical knowledge on apnea diagnosis, is designed to boost the model's learning of apnea severity at the fine granularity. A mathematical encoding of clinical knowledge is proposed to calibrate fine-grained estimation accuracy through ordinal alignment functions, which quantitatively relates the severity of apnea to the prominence of key diagnosis-informed physiological symptoms. The proposed method is able to accurately estimate fine-grained apnea severity in real time with significantly reduced labeling costs, extending the reach of sleep apnea diagnostics to larger population both in lab and at home. An experiment is conducted to demonstrate the superior estimation performance of the proposed method for monitoring apnea severity at high temporal resolution. Note to Practitioners - The effectiveness of existing automatic methods for sleep apnea detection is significantly constrained by the need of extensive finely labeled training datasets. Such datasets are expensive and time-consuming to acquire in practice due to the intensive manual labeling efforts involved. This article proposes a weakly supervised deep learning framework for automatically estimating accurate fine-grained apnea severity at high temporal resolution by only using less expensive, coarse-grained annotations indicating apnea presence in the training dataset. The integration of clinical knowledge related to apnea diagnosis into the proposed framework further enhances the severity estimation accuracy despite the limited availability of finely labeled data. This ability is highly desirable for practitioners by significantly reducing the burden of labor-intensive, costly fine-grained manual annotation efforts, providing a cost-effective solution to extend the reach of real-time sleep apnea diagnostics and monitoring to larger population.