Longitudinal Prediction of Adolescent Depression from Environmental and Polygenic Risk Scores

Understanding adolescent depression risk is vital for mitigating its long-term adverse effects. Though polygenic risk scores (PRS) explain increasing proportions of heritable risk, environmental risk remains challenging to quantify, hindering prediction. Existing prediction models often examine environmental risk in isolation, and vary in the number of predictors used - ranging from 8 to 800+ variables, limiting generalisability. Here, we develop a model predicting adolescent depression symptoms (depRS) from a review of key environmental risk factors and assess depRS and PRS prediction of lifetime depression at 2-year follow-up. Using data from the Adolescent Brain Cognitive Development study (N=7 029), we generated PRS in European, African, American Admixed and East Asian ancestries from a recent trans-ancestry genome-wide study of major depression. We trained depRS using Elastic Net regression with 10-fold cross-validation to predict follow-up depression symptoms (age 11-13 years) from 23 baseline predictors (age 9-11 years), identified from systematic reviews with meta-analyses of risk factors. Parental depression, abuse, sleep duration and dieting emerged as top predictors of depression symptoms; depRS explained 16.9% of overall variance. depRS showed better-than-chance classification of parent-reported (AUC=0.68; 95% CI 0.63-0.72) lifetime depression at follow-up, associating with greater depression odds (OR=1.73; 95% CI: 1.57-1.91) than PRS (OR=1.42; 95% CI: 1.25-1.62). Combining depRS and PRS maximised accuracy (AUC=0.70; 95% CI 0.65-0.78). Though external validation of depRS across geographically and gender diverse cohorts is needed to assess generalisability, findings highlight sleep and dieting as potential targets for mitigating risk and demonstrate the utility of genetic scores in models predicting adolescent depression.