Psilocybin Therapy for Treatment Resistant Depression: Prediction of Clinical Outcome by Natural Language Processing

A machine learning model that analyzes language from therapy sessions accurately predicted which patients with treatment-resistant depression would respond to psilocybin treatment. Transcripts of psychological support sessions held one day after COMP360 (a synthetic psilocybin formulation) administration were analyzed using a zero-shot classifier based on the BART large language model to measure sentiment (valence and arousal) for both participant and therapist. These scores, combined with the Emotional Breakthrough Index and treatment arm, were used to predict treatment outcome measured by MADRS scores. Two multinomial logistic regression models predicted responder status at week 3 and through week 12 with 85% and 88% accuracy, and AUC values of 88% and 85%, respectively. The approach enables rapid prognostication of personalized response to psilocybin treatment and insights into therapeutic model optimization.

Study at a glance

Abstract

Background: Therapeutic administration of psychedelic drugs has shown significant potential in historical accounts and in recent clinical trials in the treatment of depression and other mood disorders. A recent randomized double-blind phase-IIb study demonstrated the safety and efficacy of COMP360, COMPASS Pathways’ proprietary synthetic formulation of psilocybin, in participants with treatment resistant depression. While promising, the treatment works for a portion of the population and early prediction of outcome is a key objective.Methods: Transcripts were made from audio recordings of the psychological support session between participant and therapist one day post COMP360 administration. A zero-shot machine learning classifier based on the BART large language model was used to compute two-dimensional sentiment (valence and arousal) for the participant and therapist from the transcript. These scores, combined with the Emotional Breakthrough Index (EBI) and treatment arm were used to predict treatment outcome as measured by MADRS scores. Code and data are available at https://github.com/compasspathways/Sentiment2DResults: Two multinomial logistic regression models were fit to predict responder status at week 3 and through week 12. Cross-validation of these models resulted in 85% and 88% accuracy and AUC values of 88% and 85%.Conclusions: A machine learning algorithm using NLP and EBI accurately predicts long term patient response, allowing rapid prognostication of personalized response to psilocybin treatment and insight into therapeutic model optimization. Further research is required to understand if language data from earlier stages in the therapeutic process hold similar predictive power.