Predicting environmental risk factors in relation to health outcomes among school children from Romania using random forest model - An analysis of data from the SINPHONIE project

Background: Over half of all mental health conditions have their onset in adolescence. Large-scale epidemiological studies have identified relevant environmental risk factors for mental health problems. Yet, few have focused on potential mediating inter- and intrapersonal processes in daily life, hampering intervention development. Objectives: To investigate 1) the impact of environmental risk factors on changes in inter- and intrapersonal processes; 2) the impact of altered inter- and intrapersonal processes on the development of (sub)clinical mental health symptoms in adolescents and; 3) the extent to which changes in inter- and intrapersonal processes mediate the association between environmental risk factors and the mental health outcomes in adolescents.Methods: ‘SIGMA’ is an accelerated longitudinal study of adolescents aged 12 to 18 from across Flanders, Belgium. Using self-report questionnaires, experience sampling, an experimental task, and wearables, we are investigating the relationship between environmental risk factors (e.g. trauma, parenting), inter- and intrapersonal processes (e.g. real-life social interaction and interpersonal functioning) and mental health outcomes (e.g. psychopathology, self-harm) over time. Results: N= 1913 adolescents (63% female) aged 11 – 20, from 22 schools, participated. The range of educational trajectories within the sample was broadly representative of the Flemish general adolescent population.Conclusions: Our findings will enable us to answer fundamental questions about inter- and intrapersonal processes involved in the development and maintenance of poor mental health in adolescence. This includes insights regarding the role of daily-life social and cognitive-affective processes, gained by using experience sampling. The accelerated longitudinal design enables rapid insights into developmental and cohort effects.

Download Full-text

Study of Family History and Environmental Risk Factors Associated with Refractive Errors in Urban School Children Aged Between 10 to 17 Years

Indian Journal of Public Health Research & Development ◽

10.5958/0976-5506.2019.02412.4 ◽

2019 ◽

Vol 10 (9) ◽

pp. 123

Author(s):

K.E. Asvini Sugumaran ◽

M. Meera Alias Devasena

Keyword(s):

Risk Factors ◽

Family History ◽

School Children ◽

Environmental Risk ◽

Urban School ◽

Environmental Risk Factors ◽

Refractive Errors ◽

Factors Associated

Download Full-text

Clinical Prediction of Suicide Attempt in Schizophrenia Using a Machine Learning Approach

European Psychiatry ◽

10.1016/j.eurpsy.2017.01.297 ◽

2017 ◽

Vol 41 (S1) ◽

pp. S95-S96 ◽

Cited By ~ 1

Author(s):

V. De Luc ◽

A. Bani Fatemi ◽

N. Hettige

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Random Forest ◽

Suicide Ideation ◽

Suicide Attempts ◽

Machine Learning Algorithms ◽

Random Forest Model ◽

Predictive Tool ◽

Suicide Attempters ◽

Forest Model

ObjectiveSuicide is a major concern for those afflicted by schizophrenia. Identifying patients at the highest risk for future suicide attempts remains a complex problem for psychiatric intervention. Machine learning models allow for the integration of many risk factors in order to build an algorithm that predicts which patients are likely to attempt suicide. Currently, it is unclear how to integrate previously identified risk factors into a clinically relevant predictive tool to estimate the probability of a patient with schizophrenia for attempting suicide.MethodsWe conducted a cross-sectional assessment on a sample of 345 participants diagnosed with schizophrenia spectrum disorders. Suicide attempters and non-attempters were clearly identified using the Columbia Suicide Severity Rating Scale (C-SSRS) and the Beck Suicide Ideation Scale (BSS). We developed two classification algorithms using a regularized regression and random forest model with sociocultural and clinical variables as features to train the models.ResultsBoth classification models performed similarly in identifying suicide attempters and non-attempters. Our regularized logistic regression model demonstrated an accuracy of 66% and an area under the curve (AUC) of 0.71, while the random forest model demonstrated 65% accuracy and an AUC of 0.67.ConclusionMachine learning algorithms offer a relatively successful method for incorporating many clinical features to predict individuals at risk for future suicide attempts. Increased performance of these models using clinically relevant variables offers the potential to facilitate early treatment and intervention to prevent future suicide attempts.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Download Full-text