Identification of major depression patients using machine learning models based on heart rate variability during sleep stages for pre-hospital screening.

With the COVID-19 pandemic causing challenges in hospital admissions globally, the role of home health monitoring in aiding the diagnosis of mental health disorders has become increasingly important. This paper proposes an interpretable machine learning solution to optimise initial screening for major depressive disorder (MDD) in both male and female patients. The data is from the Stanford Technical Analysis and Sleep Genome Study (STAGES). We analyzed 5-min short-term electrocardiogram (ECG) signals during nighttime sleep stages of 40 MDD patients and 40 healthy controls, with a 1:1 gender ratio. After preprocessing, we calculated the time-frequency parameters of heart rate variability (HRV) based on the ECG signals and used common machine learning algorithms for classification, along with feature importance analysis for global decision analysis. Ultimately, the Bayesian optimised extremely randomized trees classifier (BO-ERTC) showed the best performance on this dataset (accuracy 86.32%, specificity 86.49%, sensitivity 85.85%, F1-score 0.86). By using feature importance analysis on the cases confirmed by BO-ERTC, we found that gender is one of the most important factors affecting the prediction of the model, which should not be overlooked in our assisted diagnosis. This method can be embedded in portable ECG monitoring systems and is consistent with the literature results.

Decrease in sleep quality during COVID-19 outbreak.

PURPOSE: The COVID-19 outbreak witnessed in the first months of 2020 has led to unprecedented changes in society's lifestyles. In the current study, we aimed to investigate the effect of this unexpected context on sleep. METHODS: During the COVID-19 outbreak, we performed an online survey with individuals formerly recruited for validation of the Spanish version of the sleep questionnaire Satisfaction, Alertness, Timing, Efficiency, and Duration (SATED). In the current survey, we asked the participants to complete the previously answered questionnaires including the Pittsburgh Sleep Quality Index (PSQI), a modified version of the Epworth Sleepiness Scale (ESS), and the SATED questionnaire. We also assessed the mood by the Profile of Mood States (POMS) questionnaire. RESULTS: The 71 participants were mostly women (75%) with a mean (± SD) age of 40.7 ± 11.9 years. Comparing the previous PSQI score to that during the COVID-19 outbreak, we observed worsening sleep quality (5.45 ± 3.14 to 6.18 ± 3.03 points, p = 0.035). In parallel, there was an increase in the negative mood (p = 0.002). Accordingly, the decrease in sleep quality was substantially correlated with negative mood (p < 0.001). There were no differences in the ESS or SATED. CONCLUSIONS: The COVID-19 outbreak-associated events correlate with decreased sleep quality in association with an increase in negative mood. Considering the importance of sleep for a healthy life, and in particular for immune function, efforts should be made to improve awareness on this matter and to offer psychological assistance to affected individuals.