Dynamic Structural Causal Modeling for Sleep
2026-08-20 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how different factors cause sleep breathing problems by analyzing home test recordings of sleep apnea from various people. They used a special algorithm to find cause-and-effect connections and noticed that these connections change based on a person’s age and sex. Some patterns, like how breathing problems relate to oxygen levels, stayed the same for everyone. Their work helps understand the complex differences in sleep apnea across different groups.
sleep-disordered breathingHome Sleep Apnea Test (HSAT)causal graphsPCMCI+ algorithmapneaoxygen desaturationtemporal dependenciesbootstrap aggregationsubcohortsdynamic causal modeling
Authors
Ranveer Singh, Saurabh Mathur, Pranuthi Tenali, Arun Badi, Sriraam Natarajan
Abstract
The causal dynamics of sleep-disordered breathing are complex and vary across patient populations, hindering the development of targeted interventions. We learn dynamic causal graphs of sleep-disordered breathing from Home Sleep Apnea Test (HSAT) recordings, revealing systematic differences in causal structure across sex and age subcohorts. We do so using the PCMCI+ algorithm on windowed fractional variables derived from 105 HSAT recordings, exploiting domain knowledge via edge blacklisting and employing bootstrap aggregation to address small subcohort sizes. The learned graphs show that temporal self-dependencies and the apnea-desaturation relationship persist across all cohorts, while other relationships vary substantially.