A genetically informed prediction model for suicidal and aggressive behaviour in teens

Abstract

Suicidal and aggressive behaviours cause significant personal and societal burden. As risk factors associated with these behaviours frequently overlap, combined approaches in predicting the behaviours may be useful in identifying those at risk for either. The current study aimed to create a model that predicted if individuals will exhibit suicidal behaviour, aggressive behaviour, both, or neither in late adolescence. A sample of 5,974 twins from the Child and Adolescent Twin Study in Sweden (CATSS) was broken down into a training (80%), tune (10%) and test (10%) set. The Netherlands Twin Register (NTR; N = 2702) was used for external validation. Our longitudinal data featured genetic, environmental, and psychosocial predictors derived from parental and self-report data. A stacked ensemble model was created which contained a gradient boosted machine, random forest, elastic net, and neural network. Model performance was transferable between CATSS and NTR (macro area under the receiver operating characteristic curve (AUC) [95% CI] AUC_{CATSS(test set)} = 0.709 (0.671-0.747); AUC_NTR = 0.685 (0.656-0.715), suggesting model generalisability across Northern Europe. The notable exception is suicidal behaviours in the NTR, which was no better than chance. The 25 highest scoring variable importance scores for the gradient boosted machines and random forest models included self-reported psychiatric symptoms in mid-adolescence, sex, and polygenic scores for psychiatric traits. The model's performance is comparable to current prediction models that use clinical interviews and is not yet suitable for clinical use. Moreover, genetic variables may have a role to play in predictive models of adolescent psychopathology.

Fig. 1. Flow chart of the data set creation.

^**Principal component analysis (PCA) was completed separately for CATSS and NTR. Participants with a 1st principal component (PC) score outside −5.5–5.5 were used to determine outlier status. ^**R package groupdata2 [65] removed 11 data points during the data separation process to preserve the proportion of the outcome between the sets. 3 separate PCA were completed to determine outliers: combined train and tune set, test set, and NTR. CATSS Child and Adolescent Twin Study of Sweden, NTR Netherlands Twin Register.

Fig. 2. ROC curves for each data set.

The macro AUC was derived from averaging the AUC for each class. The AUC for each class was derived using a one versus all approach, which collapses each class into a binary outcome, e.g. having only aggressive behaviour vs. all other outcomes combined. Test set (10,000 bootstrap; 95% CI): macro 0.709 (0.671–0.747); neither 0.667 (0.619–0.719); suicidal behaviours 0.713 (0.647–0.782); aggressive behaviours 0.696 (0.627–0.767); both 0.759 (0.696–0.829). NTR set: macro 0.685 (0.656–0.715); neither 0.715 (0.689–0.743); suicidal behaviours 0.543 (0.476–0.611); aggressive behaviours 0.751 (0.724–0.780); both 0.732 (0.662–0.807).

Fig. 3. Scaled variable importance for the top 25 scores.

Variable Importance in our model represents the reduction in mean squared error when the variable was split on a node; these values have been scaled for readability. Abbreviations: w2 = Measured at wave 2 (age 15/16); PGS = Polygenic score; PC = Principal component Gradient Boosted Machines Macro AUC tune set (10 000 bootstrap, 95% CIs): 0.653 (0.606–0.703); Random Forest Macro AUC tune set: 0.628 (0.580–0.678).