Impact of number of sleep ultradian cycles on polysomnographic parameters related to REM sleep in major depression: Implications for future sleep research in psychiatry

Polysomnographic markers of suicidal ideation in untreated unipolar major depressed individuals

Given the major role played by sleep in the particular relationship between suicidality and major depression, the aim of this study was to empirically identify polysomnographic markers specific to suicidal ideation in major depressed individuals in order to allow better suicide prevention in this high-risk subpopulation. Demographic and polysomnographic data from 190 individuals (34 healthy controls and 156 untreated unipolar major depressed individuals) recruited from the sleep laboratory database were analysed. Suicidal ideation were considered present if the score in item G of the Beck Depression Inventory was ≥1 and/or if they were highlighted during the systematic psychiatric assessment conducted on admission to the sleep laboratory. Independently of depression severity, major depressed individuals with suicidal ideation present a decrease in deep NREM sleep (slow-wave sleep) and an increase in light NREM sleep (stage 1 + stage 2) compared to those without suicidal ideation. There are no significant differences for the other polysomnographic parameters. In our study, we highlighted the existence of potential polysomnographic markers of suicidal ideation in untreated unipolar major depressed individuals, which seems to open up new perspectives for the identification and management of individuals at high-risk of suicide in this particular subpopulation.

Comparison of Regression and Machine Learning Methods in Depression Forecasting Among Home-Based Elderly Chinese: A Community Based Study

BACKGROUND

Depression is highly prevalent and considered as the most common psychiatric disorder in home-based elderly, while study on forecasting depression risk in the elderly is still limited. In an endeavor to improve accuracy of depression forecasting, machine learning (ML) approaches have been recommended, in addition to the application of more traditional regression approaches.

METHODS

A prospective study was employed in home-based elderly Chinese, using baseline (2011) and follow-up (2013) data of the China Health and Retirement Longitudinal Study (CHARLS), a nationally representative cohort study. We compared four algorithms, including the regression-based models (logistic regression, lasso, ridge) and ML method (random forest). Model performance was assessed using repeated nested 10-fold cross-validation. As the main measure of predictive performance, we used the area under the receiver operating characteristic curve (AUC).

RESULTS

The mean AUCs of the four predictive models, logistic regression, lasso, ridge, and random forest, were 0.795, 0.794, 0.794, and 0.769, respectively. The main determinants were life satisfaction, self-reported memory, cognitive ability, ADL (activities of daily living) impairment, CESD-10 score. Life satisfaction increased the odds ratio of a future depression by 128.6% (logistic), 13.8% (lasso), and 13.2% (ridge), and cognitive ability was the most important predictor in random forest.

CONCLUSIONS

The three regression-based models and one ML algorithm performed equally well in differentiating between a future depression case and a non-depression case in home-based elderly. When choosing a model, different considerations, however, such as easy operating, might in some instances lead to one model being prioritized over another.