Psilocybin Therapy for Treatment Resistant Depression: Prediction of Clinical Outcome by Natural Language Processing
Available as a full-length article - this preprint provides exciting new evidence for clinical outcomes for people with treatment resistant depression using psilocybin therapy. This preprint article of a language model (NLP, BART) finds that the audio from psychological support sessions (in the COMP360 trial for treatment-resistant depression, n=90 at 12 weeks) can predict clinical outcomes with high (85%) accuracy. The implications of this research signal that audio recordings can be used to predict who will respond to treatment and possibly aid in helping identify who would need more support.
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.
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."
For more psychedelic news and research, visit the psychedelic health professional network homepage.