Developing an individualized risk calculator for psychopathology among young people victimized during childhood: A population-representative cohort study

Meehan, Alan J.; Latham, Rachel M.; Arseneault, Louise; Ståhl, Daniel; Fisher, Helen L.; Danese, Andrea

doi:10.1016/j.jad.2019.10.034

Cited by 39 publications

(30 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two algorithms will select different sets of variables, thereby reducing the likelihood of important variables being omitted. Boruta and LASSO have been used for variable selection for various types of data, such as survey, medical and genomic data [ 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 ].…”

Section: Methodsmentioning

confidence: 99%

Factors Associated with E-Cigarette Use in U.S. Young Adult Never Smokers of Conventional Cigarettes: A Machine Learning Approach

Atuegwu

Oncken

Laubenbacher

et al. 2020

IJERPH

View full text Add to dashboard Cite

E-cigarette use is increasing among young adult never smokers of conventional cigarettes, but the awareness of the factors associated with e-cigarette use in this population is limited. The goal of this work was to use machine learning (ML) algorithms to determine the factors associated with current e-cigarette use among US young adult never cigarette smokers. Young adult (18–34 years) never cigarette smokers from the 2016 and 2017 Behavioral Risk Factor Surveillance System (BRFSS) who reported current or never e-cigarette use were used for the analysis (n = 79,539). Variables associated with current e-cigarette use were selected by two ML algorithms (Boruta and Least absolute shrinkage and selection operator (LASSO)). Odds ratios were calculated to determine the association between e-cigarette use and the variables selected by the ML algorithms, after adjusting for age, gender and race/ethnicity and incorporating the BRFSS complex design. The prevalence of e-cigarette use varied across states. Factors previously reported in the literature, such as age, race/ethnicity, alcohol use, depression, as well as novel factors associated with e-cigarette use, such as disabilities, obesity, history of diabetes and history of arthritis were identified. These results can be used to generate further hypotheses for research, increase public awareness and help provide targeted e-cigarette education.

show abstract

Section: Methodsmentioning

confidence: 99%

Factors Associated with E-Cigarette Use in U.S. Young Adult Never Smokers of Conventional Cigarettes: A Machine Learning Approach

Atuegwu

Oncken

Laubenbacher

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…There are several excellent studies in this area (Copeland, Keeler, Angold, & Costello, ; McLaughlin et al, ). We have recently published the first comprehensive epidemiological study of trauma‐related psychopathology in British young people based on data from the E‐Risk Study (Lewis et al, ), and I will refer to this paper here to make some observations (see also Meehan et al, ). Findings on the association between childhood trauma and psychopathology are typically interpreted to highlight group differences, or relative risk: compared to nontraumatised children, we found that traumatised children were about twice as likely to develop a wide range of psychiatric diagnoses (e.g.…”

Section: Which?mentioning

confidence: 99%

Annual Research Review: Rethinking childhood trauma‐new research directions for measurement, study design and analytical strategies

Danese

2019

Child Psychology Psychiatry

Self Cite

115

View full text Add to dashboard Cite

Childhood trauma is a key modifiable risk factor for psychopathology. Despite significant scientific advances, traumatised children still have poorer long‐term outcomes than nontraumatised children. New research paradigms are, thus, needed. To this end, the review examines three dominant assumptions about measurement, design and analytical strategies. Current research warns against using prospective and retrospective measures of childhood trauma interchangeably; against interpreting cross‐sectional differences in putative mediating mechanisms between adults with or without a history of childhood trauma as evidence of longitudinal changes from pre‐trauma conditions; and against directly applying explanatory models of resilience or vulnerability to psychopathology in traumatised children to forecast individual risk in unseen cases. The warnings equally apply to research on broader measures of adverse childhood experiences (ACEs). Further research examining these assumptions can generate new insights on how to prevent childhood trauma and its detrimental effects.

show abstract

“…Our work reflects a growing interest in predictive analytics, complementing attempts within clinical and child protection domains to use algorithms to identify patients at risk of domestic abuse (Reis, Kohane, & Mandl, 2009) and children at risk of maltreatment (Cuccaro-Alamin, Foust, Vaithianathan, & Putnam-Hornstein, 2017; Hurley, 2018; McIntyre & Pegg, 2018). Moreover, similar methods have been used to predict individual risk of developing psychopathology at age 18 years following exposure to childhood victimization (Meehan et al, 2019) which, together with the current study, demonstrates the applicability of prediction modelling to several different outcomes within groups of victimized children.…”

Section: Discussionmentioning

confidence: 59%

Development of an individualized risk calculator for poor functioning in young people victimized during childhood: A longitudinal cohort study

Latham

Meehan

Arseneault

et al. 2019

Child Abuse & Neglect

Self Cite

View full text Add to dashboard Cite

BackgroundChildhood victimization elevates the average risk of developing functional impairment in adulthood. However, not all victimized children demonstrate poor outcomes. Although research has described factors that confer vulnerability or resilience, it is unknown if this knowledge can be translated to accurately identify the most vulnerable victimized children.ObjectiveTo build and internally validate a risk calculator to identify those victimized children who are most at risk of functional impairment at age 18 years.ParticipantsWe utilized data from the Environmental Risk (E-Risk) Longitudinal Twin Study, a nationally-representative birth cohort of 2232 UK children born in 1994–95.MethodsVictimization exposure was assessed repeatedly between ages 5 and 12 years along with a range of individual-, family- and community-level predictors. Functional outcomes were assessed at age 18 years. We developed and evaluated a prediction model for psychosocial disadvantage and economic disadvantage using the Least Absolute Shrinkage and Selection Operator (LASSO) regularized regression with nested 10-fold cross-validation.ResultsThe model predicting psychosocial disadvantage following childhood victimization retained 12 of 22 predictors, had an area under the curve (AUC) of 0.65, and was well-calibrated within the range of 40–70% predicted risk. The model predicting economic disadvantage retained 10 of 22 predictors, achieved excellent discrimination (AUC = 0.80), and a high degree of calibration.ConclusionsPrediction modelling techniques can be applied to estimate individual risk for poor functional outcomes in young adulthood following childhood victimization. Such risk prediction tools could potentially assist practitioners to target interventions, which is particularly useful in a context of scarce resources.

show abstract

Developing an individualized risk calculator for psychopathology among young people victimized during childhood: A population-representative cohort study

Cited by 39 publications

References 32 publications

Factors Associated with E-Cigarette Use in U.S. Young Adult Never Smokers of Conventional Cigarettes: A Machine Learning Approach

Factors Associated with E-Cigarette Use in U.S. Young Adult Never Smokers of Conventional Cigarettes: A Machine Learning Approach

Annual Research Review: Rethinking childhood trauma‐new research directions for measurement, study design and analytical strategies

Development of an individualized risk calculator for poor functioning in young people victimized during childhood: A longitudinal cohort study

Contact Info

Product

Resources

About