Combining DNA methylation features and clinical characteristics predicts ketamine treatment response for PTSD.
iScience January 16, 2026 Amir Valizadeh, John D Roache, Xinyu Zhang et al. 2 citations
Post-traumatic stress disorder varies greatly in its clinical and biological features, making treatment difficult. The largest randomized trial of ketamine for PTSD found no overall benefit over placebo, highlighting the need to identify which patients might respond. Using pre-treatment blood DNA methylation profiles and clinical data from that trial, machine learning models predicted treatment response. A model based on 1,208 methylation sites outperformed models using only clinical variables, and combining both data types improved accuracy further. The methylation-derived score identified responders with 92.9% accuracy. Predictive methylation sites were near genes involved in glutamatergic signaling, immune regulation, and known PTSD risk loci, suggesting peripheral DNA methylation patterns can guide precision pharmacotherapy for PTSD.