Age estimation from sleep studies using deep learning predicts life expectancy

Abstract

Sleep disturbances increase with age and are predictors of mortality. Here, we present deep neural networks that estimate age and mortality risk through polysomnograms (PSGs). Aging was modeled using 2500 PSGs and tested in 10,699 PSGs from men and women in seven different cohorts aged between 20 and 90. Ages were estimated with a mean absolute error of 5.8 ± 1.6 years, while basic sleep scoring measures had an error of 14.9 ± 6.29 years. After controlling for demographics, sleep, and health covariates, each 10-year increment in age estimate error (AEE) was associated with increased all-cause mortality rate of 29% (95% confidence interval: 20-39%). An increase from -10 to +10 years in AEE translates to an estimated decreased life expectancy of 8.7 years (95% confidence interval: 6.1-11.4 years). Greater AEE was mostly reflected in increased sleep fragmentation, suggesting this is an important biomarker of future health independent of sleep apnea.

Fig. 1. Scatterplot of age estimate and chronological age in the test sets for model (e, Ensemble–Avg.).

a The test set (n = 9899). The dotted line indicates the standard error of the mean (SEM) calculated as $\sigma /\sqrt{n}$. b The HomePAP test set (n = 190). The red line indicates the optimal age estimate; the magenta lines indicate 5th, 50th, and 95th percentiles of age estimate in 5-year intervals. r is Pearson’s correlation coefficient between age estimate and chronological age. MAE: mean absolute error.

Fig. 2. Example of model (b; EEG+EOG+EMG) interpretation through relevance attribution of samples.

The top plot shows relevance scores averaged across channels (C3-A2, C3-A1, EOGL, EOGR, Chin EMG). The second plot shows EEG power in the δ-band (0–4 Hz) and the combined α- and β-bands (>8 Hz). Red and blue indicate positive and negative attribution to the age estimate, respectively. Relevance attribution was computed using gradient SHAP.

Fig. 3. Average and smoothed relevance attribution averaged over channels of model (b; EEG+EOG+EMG) time-locked to sleep-stage transitions.

The average relevance attribution time-locked to sleep-stage transitions. These were averaged in 4353 PSGs from the test set with available manual scoring. The dotted line marks the standard error of the mean. Relevance attribution was computed using gradient SHAP.

Fig. 4. Survival curve for all-cause mortality with an AEE varying ±10 years.

The survival curve was generated for all data (n = 9386, deaths = 3045) and model (e, Ensemble–Avg.) using the Cox proportional hazards model 3 shown in Supplementary Table 3. The 95% CI express the uncertainty in the modeled hazard ratio. AEE age estimate error, CI confidence interval.

Fig. 5. Use of data for age estimation and evaluating mortality risk.

a The data from six cohorts are sampled to generate a training and validation set with a uniform age distribution. The remaining data comprises a test set, some of which has additional visits (test set V2). b Age estimation models are optimized and evaluated in all data. c Associations between increased age estimate errors and mortality risk are evaluated in all available data using Cox proportional hazards models.