Sex?Specific Risk Profiles for Suicide Among Persons with Substance Use Disorders in Denmark

Background and Aims Persons with substance use disorders (SUDs) are at elevated risk of suicide death. We identified novel factors interactions that predict among men women SUD using machine learning. Design Case–cohort study. Setting Denmark. Participants The sample was restricted to persons their first diagnosis during 1995 2015. Cases were who died by in Denmark 2015 (n = 2774) the comparison subcohort a 5% random individuals on 1 January 13 179). Measurements Suicide death recorded Danish Cause Death Registry. Predictors included social demographic information, mental physical health diagnoses, surgeries, medications, poisonings. Findings highest for suicide, as classification trees, prescribed antidepressants 4 years before had poisoning suicide; 30+ old 12 months suicide. Among SUD, forest five variables most important predicting reaction severe stress adjustment disorders, drugs used treat addictive age years, antidepressant use, prior years. found predictors poisonings disorders. Individuals top predicted accounted 15% all deaths 24% suicides women. Conclusions In Denmark, comorbid psychiatric may be indicators particularly