Mortality risk assessment using deep learning-based frequency analysis of electroencephalography and electrooculography in sleep

Study Objectives: To assess whether the frequency content of electroencephalography (EEG) and electrooculography (EOG) during nocturnal polysomnography (PSG) can predict all-cause mortality.
Methods: Power spectra from PSGs of 8716 participants, including from the MrOS Sleep Study and the Sleep Heart Health Study, were analyzed in deep learning-based survival models. The best-performing model was further examined using SHapley Additive Explanation (SHAP) for data-driven sleep-stage specific definitions of power bands, which were evaluated in predicting mortality using Cox Proportional Hazards models.
Results: Survival analyses, adjusted for known covariates, identified multiple EEG frequency bands across all sleep stages predicting all-cause mortality. For EEG, we found an all-cause mortality hazard ratio (HR) of 0.90 (CI: 95% 0.85 to 0.96) for 12-15 Hz in N2, 0.86 (CI: 95% 0.82 to 0.91) for 0.75-1.5 Hz in N3, and 0.87 (CI: 95% 0.83 to 0.92) for 14.75-33.5 Hz in rapid-eye-movement sleep. For EOG, we found several low-frequency effects including an all-cause mortality HR of 1.19 (CI: 95% 1.11 to 1.28) for 0.25 Hz in N3, 1.11 (CI: 95% 1.03 to 1.21) for 0.75 Hz in N1, and 1.11 (CI: 95% 1.03 to 1.20) for 1.25-1.75 Hz in wake. The gain in the concordance index (C-index) for all-cause mortality is minimal, with only a 0.24% increase: The best single mortality predictor was EEG N3 (0-0.5 Hz) with a C-index of 77.78% compared to 77.54% for confounders alone.
Conclusions: Spectral power features, possibly reflecting abnormal sleep microstructure, are associated with mortality risk. These findings add to a growing literature suggesting that sleep contains incipient predictors of health and mortality.