We examined the associations between electroencephalogram (EEG)-based sleep characteristics and physical health parameters in general adults via a cross-sectional study recruiting 100 volunteers aged 30-59 years. Sleep characteristics were measured at home using a portable multichannel electroencephalography recorder. Using the k-means +  +  clustering method, according to 10 EEG-based parameters, participants were grouped into better (n = 39), middle (n = 46), and worse (n = 15) sleep groups. Comparing 50 physical health parameters among the groups, we identified four signals of difference (P < 0.05), including systolic (sBP) and diastolic blood pressure (dBP), γ-glutamyl transpeptidase (γ-GTP), and serum creatinine, where sBP reached a Bonferroni-corrected threshold (P < 0.001). The sBP was higher by 7.9 (95% confidence interval 1.9-13.9) and 15.7 (7.3-24.0) mmHg before adjustment and 5.4 (- 0.1-10.9) and 8.7 (1.1-16.3) mmHg after adjustment for age, sex, body mass index, smoking, drinking habits, and 3% oxygen desaturation index in the middle and worse sleep groups, respectively, than in the better group. As another approach, among 500 combinations of EEG-based and physical health parameters, there were 45 signals of correlation, of which 4 (N1% and sBP, dBP, γ-GTP, and triglycerides) reached a Bonferroni-corrected threshold (P < 0.0001). Thus, EEG-based sleep characteristics are associated with several physical health parameters, particularly sBP.

Automated sleep stage scoring for mice is in high demand for sleep research, since manual scoring requires considerable human expertise and efforts. The existing automated scoring methods do not provide the scoring accuracy required for practical use. In addition, the performance of such methods has generally been evaluated using rather small-scale datasets, and their robustness against individual differences and noise has not been adequately verified. This research proposes a novel automated scoring method named "MC-SleepNet", which combines two types of deep neural networks. Then, we evaluate its performance using a large-scale dataset that contains 4,200 biological signal records of mice. The experimental results show that MC-SleepNet can automatically score sleep stages with an accuracy of 96.6% and kappa statistic of 0.94. In addition, we confirm that the scoring accuracy does not significantly decrease even if the target biological signals are noisy. These results suggest that MC-SleepNet is very robust against individual differences and noise. To the best of our knowledge, evaluations using such a large-scale dataset (containing 4,200 records) and high scoring accuracy (96.6%) have not been reported in previous related studies.