Background: Modern modeling techniques may potentially provide more accurate predictions of dichotomous outcomes than classical techniques. Objective: In this study, we aimed to examine the predictive performance of eight modeling techniques to predict mortality by frailty. Methods: We performed a longitudinal study with a 7-year follow-up. The sample consisted of 479 Dutch community-dwelling people, aged 75 years and older. Frailty was assessed with the Tilburg Frailty Indicator (TFI), a self-report questionnaire. This questionnaire consists of eight physical, four psychological, and three social frailty components. The municipality of Roosendaal, a city in the Netherlands, provided the mortality dates. We compared modeling techniques, such as support vector machine (SVM), neural network (NN), random forest, and least absolute shrinkage and selection operator, as well as classical techniques, such as logistic regression, two Bayesian networks, and recursive partitioning (RP). The area under the receiver operating characteristic curve (AUROC) indicated the performance of the models. The models were validated using bootstrapping. Results: We found that the NN model had the best validated performance (AUROC=0.812), followed by the SVM model (AUROC=0.705). The other models had validated AUROC values below 0.700. The RP model had the lowest validated AUROC (0.605). The NN model had the highest optimism (0.156). The predictor variable “difficulty in walking” was important for all models. Conclusions: Because of the high optimism of the NN model, we prefer the SVM model for predicting mortality among community-dwelling older people using the TFI, with the addition of “gender” and “age” variables. External validation is a necessary step before applying the prediction models in a new setting.
DOCUMENT
We investigated the relationship between process quality in early childhood education and care (ECEC) and children’s socio-emotional development in a meta-analysis of longitudinal studies. Our multi-level meta-analysis of 31 publications reporting on 16 longitudinal studies (N = 17,913 children, age: 2.5–18 yrs) demonstrates that the process quality of ECEC is a small but significant predictor of children’s socio-emotional development over time (ES = 0.103, SE = 0.026, p < 0.001, 95% CI: 0.052–0.155). This longitudinal association extends to the age of 18 years in our sample. Process quality of ECEC is, thus, a significant and stable predictor of children’s socio-emotional development and well-being from toddlerhood to adolescence. The longitudinal relationship was moderated by the type of care (center-based vs. home-based) and the informant (parent, professional caregiver, external assessor, or self-report of the child). Implications for future ECEC research are discussed.
MULTIFILE
This article focuses on how length of participation in professional youth work is associated with five outcome variables: prosocial skills, self-mastery, social network, civic participation (volunteering and organizing activities) and finding support from social care services. The study was designed as a longitudinal cohort study of four waves during a 16-month period, gathering the data of 1597 youngsters aged 10–24 who participated in Dutch professional youth work. The results show that, on average, youngsters who participated longer in youth work scored significantly higher on the outcome variables. Respondents did not show individual improvements on outcome variables over the period, but the results demonstrate a cautious positive trend over time in volunteering. Referring youngsters (33%) by youth workers to care services could prevent an exacerbation of existing problems. The results provide knowledge that legitimizes the role of professional youth workers and which can be used by them to improve the support of socially vulnerable youngsters in their personal development and social participation.
DOCUMENT
