BackgroundSleep, physical activity, and diet have been associated with mental health and well-being individually in young adults. However, which of these “big three” health behaviors most strongly predicts mental health and well-being, and their higher-order relationships in predictive models, is less known. This study investigated the differential and higher-order associations between sleep, physical activity, and dietary factors as predictors of mental health and well-being in young adults.MethodIn a cross-sectional survey design, 1,111 young adults (28.4% men) ages 18–25 from New Zealand and the United States answered an online survey measuring typical sleep quantity and quality; physical activity; and consumption of raw and processed fruit and vegetables, fast food, sweets, and soda, along with extensive covariates (including demographics, socioeconomic status, body mass index, alcohol use, smoking, and health conditions) and the outcome measures of depressive symptoms [measured by the Center for Epidemiological Depression Scale (CES-D)] and well-being (measured by the Flourishing Scale).ResultsControlling for covariates, sleep quality was the strongest predictor of depressive symptoms and well-being, followed by sleep quantity and physical activity. Only one dietary factor—raw fruit and vegetable consumption—predicted greater well-being but not depressive symptoms when controlling for covariates. There were some higher-order interactions among health behaviors in predicting the outcomes, but these did not survive cross-validation.ConclusionSleep quality is an important predictor of mental health and well-being in young adults, whereas physical activity and diet are secondary but still significant factors. Although strictly correlational, these patterns suggest that future interventions could prioritize sleep quality to maximize mental health and well-being in young adults.

Despite decades of costly research, we still cannot accurately predict individual differences in cognition from task-based functional magnetic resonance imaging (fMRI). Moreover, aiming for methods with higher prediction is not sufficient. To understand brain-cognition relationships, we need to explain how these methods draw brain information to make the prediction. Here we applied an explainable machine-learning (ML) framework to predict cognition from task-based fMRI during the n-back working-memory task, using data from the Adolescent Brain Cognitive Development (n = 3,989). We compared 9 predictive algorithms in their ability to predict 12 cognitive abilities. We found better out-of-sample prediction from ML algorithms over the mass-univariate and ordinary least squares (OLS) multiple regression. Among ML algorithms, Elastic Net, a linear and additive algorithm, performed either similar to or better than nonlinear and interactive algorithms. We explained how these algorithms drew information, using SHapley Additive explanation, eNetXplorer, Accumulated Local Effects, and Friedman’s H-statistic. These explainers demonstrated benefits of ML over the OLS multiple regression. For example, ML provided some consistency in variable importance with a previous study and consistency with the mass-univariate approach in the directionality of brain-cognition relationships at different regions. Accordingly, our explainable-ML framework predicted cognition from task-based fMRI with boosted prediction and explainability over standard methodologies.

We examined the role of the avian hippocampus and area parahippocampalis in serial‐order behavior and a variety of other tasks known to be sensitive to hippocampal damage in mammals. Damage to the hippocampus and area parahippocampalis caused impairments in autoshaping and performance on an analogue of a radial‐arm maze task, but had no effect on acquisition of 2‐item, 3‐item, and 4‐item serial‐order lists. Additionally, the lesions had no effect on the retention of 3‐items lists, or on the ability to perform novel derived lists composed of elements from lists they had previously learned. The impairments in autoshaping and spatial behavior are consistent with the findings in mammals. The absence of impairments on the serial‐order task may also be consistent once one considers that damage to the hippocampus in mammals seems to affect more internally‐organized rather than externally‐organized serial‐order tasks. Together, the findings support the view that the avian hippocampal complex serves a function very similar to the mammalian hippocampus, a finding that is interesting given that the architecture of the avian hippocampus differs dramatically from that of the mammalian hippocampus.

BackgroundVariable selection is an important issue in many fields such as public health and psychology. Researchers often gather data on many variables of interest and then are faced with two challenging goals: building an accurate model with few predictors, and making probabilistic statements (inference) about this model. Unfortunately, it is currently difficult to attain these goals with the two most popular methods for variable selection methods: stepwise selection and LASSO. The aim of the present study was to demonstrate the use predictive projection feature selection – a novel Bayesian variable selection method that delivers both predictive power and inference. We apply predictive projection to a sample of New Zealand young adults, use it to build a compact model for predicting well-being, and compare it to other variable selection methods. MethodsThe sample consisted of 791 young adults (ages 18 to 25, 71.7% female) from New Zealand who had taken part in the Dunedin Daily Life Study in 2013-2014. Participants completed a 13-day online daily diary assessment of their well-being and a range of lifestyle variables (e.g., sleep, physical activity, diet variables). The participants’ diary data was averaged across days and analyzed cross-sectionally to identify predictors of average flourishing. Predictive projection was used to select as few predictors as necessary to approximate the predictive accuracy of a reference model with all 28 predictors. Predictive projection was also compared to other variable selection methods, including stepwise selection and LASSO.ResultsThree predictors were sufficient to approximate the predictions of the reference model: higher sleep quality, less trouble concentrating, and more servings of fruit. The performance of the projected submodel generalized well. Compared to other variable selection methods, predictive projection lead to models with either matching or slightly worse performance but with much fewer predictors.ConclusionPredictive projection was used to efficiently arrive at a compact model with good predictive accuracy. The predictors selected into the submodel – felt refreshed after waking up, had less trouble concentrating, and ate more servings of fruit – were all theoretically meaningful. Our findings have important implications for applications of variable selection in health research.

Background Variable selection is an important issue in many fields such as public health and psychology. Researchers often gather data on many variables of interest and then are faced with two challenging goals: building an accurate model with few predictors, and making probabilistic statements (inference) about this model. Unfortunately, it is currently difficult to attain these goals with the two most popular methods for variable selection methods: stepwise selection and LASSO. The aim of the present study was to demonstrate the use predictive projection feature selection – a novel Bayesian variable selection method that delivers both predictive power and inference. We apply predictive projection to a sample of New Zealand young adults, use it to build a compact model for predicting well-being, and compare it to other variable selection methods. Methods The sample consisted of 791 young adults (ages 18 to 25, 71.7% female) living in Dunedin, New Zealand who had taken part in the Daily Life Study in 2013–2014. Participants completed a 13-day online daily diary assessment of their well-being and a range of lifestyle variables (e.g., sleep, physical activity, diet variables). The participants’ diary data was averaged across days and analyzed cross-sectionally to identify predictors of average flourishing. Predictive projection was used to select as few predictors as necessary to approximate the predictive accuracy of a reference model with all 28 predictors. Predictive projection was also compared to other variable selection methods, including stepwise selection and LASSO. Results Three predictors were sufficient to approximate the predictions of the reference model: higher sleep quality, less trouble concentrating, and more servings of fruit. The performance of the projected submodel generalized well. Compared to other variable selection methods, predictive projection produced models with either matching or slightly worse performance; however, this performance was achieved with much fewer predictors. Conclusion Predictive projection was used to efficiently arrive at a compact model with good predictive accuracy. The predictors selected into the submodel – felt refreshed after waking up, had less trouble concentrating, and ate more servings of fruit – were all theoretically meaningful. Our findings showcase the utility of predictive projection in a practical variable selection problem.