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

BackgroundDepression 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.MethodsA 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).ResultsThe 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.ConclusionsThe 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.

The Subjective Well-Being of Children in Residential Care: Has It Changed in Recent Years?

The subjective well-being of children in residential care is a relevant issue given the practical implications for improving the lives of these children who live in contexts of vulnerability. The question addressed in this respect was: “How does this well-being change over the years”? Thus, the aim of this study was to compare the subjective well-being displayed by adolescents aged 11–14 in residential care in Catalonia (north-eastern Spain) in 2014 to that displayed by adolescents in residential care in 2020. To this end, 572 responses to a questionnaire adapted from the Children’s Worlds project (364 from 2014 and 208 from 2020) were analysed with respect to the life satisfaction items. In both 2014 and 2020, the questionnaires had the same wording, and data were disaggregated by gender. No significant differences in means were observed between most of the life satisfaction items in 2014 and 2020, with the exception of satisfaction with friends and classmates and the area where you live, with lower means for these items in 2020. There is a discussion of the possible influence of COVID-19 on these results, while the overall stability of these children’s subjective well-being over the years is highlighted.