Dynamic Structural Causal Modeling for Sleep: Learning Causal Graphs from Home Sleep Apnea Tests

Summary

This arXiv paper (2608.20285) by Ranveer Singh, Saurabh Mathur, Pranuthi Tenali, and Arun Badi applies dynamic structural causal modeling to sleep medicine. The authors learn causal graphs underlying sleep-disordered breathing (SDB) from home sleep apnea test (HSAT) records, revealing systematic differences in causal structure across sex and age subgroups. They use the PCMCI+ algorithm on windowed score variables derived from 105 HSAT recordings, incorporating domain knowledge via edge blacklists and bootstrap aggregation to handle small subgroup sizes. The learned graphs show that temporal self-dependencies and apnea–desaturation relationships persist across all cohorts, while other causal relationships vary considerably between patient groups. The findings offer a causal perspective on the heterogeneity of sleep-disordered breathing and may guide more personalized intervention and treatment strategies. Published August 22, 2026, in the machine learning domain.