Comparing machine learning to a rule-based approach for predicting suicidal behavior among adolescents: Results from a longitudinal population-based survey.

INTRODUCTION: Suicidal thoughts and suicide attempts are one of the most prominent public health concerns in adolescents and therefore early detection is important to initiate preventive interventions and closer monitoring. METHOD: We examined whether the Machine Learning models Random Forest and Lasso Regression better predict future suicidal behavior than a simple decision rule that classifies every adolescent with history of suicide ideation at baseline as at risk (current practice). We used data from a general population of students in second and fourth year of secondary education in Amsterdam, the Netherlands. RESULTS: Both the Random Forest and the Lasso Regression resulted in slightly better prediction. The AUC of the Random Forest (0.79) and Lasso regression (0.76) were both higher than the AUC of the decision rule (0.64). The Random Forest achieved slightly (but non-significantly) higher sensitivity than the decision rule (0.37 versus 0.34), with the same specificity (0.94). With Lasso Regression the sensitivity increased significantly (0.52), but at the expense of the specificity (0.85). LIMITATIONS: The loss of cases after merging the data, the use of self-reported data, confidential data collection and the use of only four questions to measure suicidal behavior. CONCLUSIONS: This is the first study applying Machine Learning techniques to predict future suicidal behavior on survey data collected in a general population of adolescents. Our study showed that integrating machine learning techniques in screening practice will result in a small improvement in the ability to predict suicide. The models need to be further optimized to improve accuracy.

Public perceptions of the causes and prevention of obesity among primary school children.

OBJECTIVE: To investigate lay perceptions of the causes and prevention of obesity among primary school children. DESIGN: A cross-sectional survey of randomly selected sample of adults in a shopping centre. SUBJECTS: 315 adults in Melbourne, Australia. MEASUREMENTS: Subjects completed a self-completion questionnaire, in which they rated the importance of 25 possible causes of obesity and the importance of 13 preventive measures on four-point scales: not important; quite important; very important; extremely important. Demographic information about the respondents' age, sex, marital status, education level and parental status was also collected. RESULTS: The most important reported causes of childhood obesity were related to overconsumption of unhealthy food, parental responsibility, modern technology and the mass media. The most popular prevention activities were associated with specific actions aimed at children. Principal components analysis of the causes data revealed eight factors, provisionally named: parental responsibility, modern technology and media, overconsumption of unhealthy food, children's lack of knowledge and motivation, physical activity environment, lack of healthy food, lack of physical activity and genes. Two prevention factors were also derived, named government action and children's health promotion. Parents saw modern technology and media, and government activities as more important causes, and government policy as a more important means of prevention than nonparents and men. Women's responses tended to be similar to those of parents. There were few educational differences, although nontertiary educated respondents reported that modern technology and media were more important causes of obesity than did the tertiary educated. CONCLUSION: The findings suggest that the public appears to hold quite sophisticated views of the causes and prevention of children's obesity. They suggest that a number of prevention strategies would be widely supported by the public, especially by parents.