Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
Researchers have developed a novel framework for assessing sleep recovery using a hierarchical Sleep Recovery Score (SRS). This framework leverages causal discovery on multimodal physiological data from polysomnography (PSG) to identify key drivers of recovery across five domains: respiratory burden, hypoxic burden, sleep fragmentation, sleep architecture, and autonomic regulation. The SRS demonstrated up to 2.5 times stronger alignment with perceived recovery compared to the traditional Apnea-Hypopnea Index (AHI), offering a more comprehensive and interpretable measure for both clinical settings and emerging connected health technologies. AI
IMPACT Provides a more interpretable and accurate measure of sleep recovery, potentially improving patient outcomes and enabling new applications in connected health.