Gene-Environment Interactions in Predicting Self-Harm: A Machine Learning Approach Using Explainable Artificial Intelligence

AI Summary

Interpersonal trauma, notably partner belittlement and sexual assault, predicts self-harm more strongly than polygenic risk scores.
Gene environment interactions explain about 12% of variance, with PRSs for major depression, cannabis use disorder and anorexia nervosa showing strongest effects.
Findings support personalised prevention targeting combined genetic vulnerability and interpersonal trauma to reduce self-harm risk.

Arch Suicide Res. 2026 May 27:1-24. doi: 10.1080/13811118.2026.2657528. Online ahead of print.

ABSTRACT

BACKGROUND: Self-harm is a critical public health concern; nevertheless, the complex interplay between genetic predispositions and environmental factors in self-harm remains poorly understood.

METHODS: This study employed data from 156,873 participants in the UK Biobank to investigate how polygenic risk scores (PRSs) for 15 psychiatric disorders/traits interact with environmental risk factors in predicting lifetime self-harm. Automated machine learning identified the optimal predictive model, while explainable artificial intelligence techniques were applied to assess feature importance and interactions.

RESULTS: Environmental factors, particularly interpersonal trauma, such as partner belittlement and sexual assault, demonstrated stronger predictive value than genetic factors. However, gene-environment interactions accounted for approximately 12% of the variance in predicted self-harm risk, with major depression, cannabis use disorder, and anorexia nervosa PRSs exhibiting the strongest interaction effects.

CONCLUSIONS: This study’s findings suggest that individuals with genetic vulnerabilities may be particularly susceptible to interpersonal trauma, highlighting the need for personalized prevention strategies addressing combined genetic and environmental risks.

PMID:42201893 | DOI:10.1080/13811118.2026.2657528

Document this CPD