Psilocybin therapy for treatment resistant depression: prediction of clinical outcome by natural language processing
-
Published:2023-08-22
Issue:
Volume:
Page:
-
ISSN:0033-3158
-
Container-title:Psychopharmacology
-
language:en
-
Short-container-title:Psychopharmacology
Author:
Dougherty Robert F.ORCID, Clarke Patrick, Atli Merve, Kuc Joanna, Schlosser Danielle, Dunlop Boadie W., Hellerstein David J., Aaronson Scott T., Zisook Sidney, Young Allan H., Carhart-Harris Robin, Goodwin Guy M., Ryslik Gregory A.
Abstract
Abstract
Rationale
Therapeutic administration of psychedelics has shown significant potential in historical accounts and 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.
Objective
While the phase-IIb results are promising, the treatment works for a portion of the population and early prediction of outcome is a key objective as it would allow early identification of those likely to require alternative treatment.
Methods
Transcripts were made from audio recordings of the psychological support session between participant and therapist 1 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/Sentiment2D.)
Results
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.
Publisher
Springer Science and Business Media LLC
Reference51 articles.
1. Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324 2. Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877–1901 3. Carhart-Harris R, Giribaldi B, Watts R, Baker-Jones M, Murphy-Beiner A, Murphy R, Martell J, Blemings A, Erritzoe D, Nutt DJ (2021) Trial of psilocybin versus escitalopram for depression. N Engl J Med 384(15):1402–1411 4. Carhart-Harris RL, Bolstridge M, Rucker J, Day CM, Erritzoe D, Kaelen M, Bloomfield M, Rickard JA, Forbes B, Feilding A, Taylor D, Pilling S, Curran VH, Nutt DJ (2016) Psilocybin with psychological support for treatment-resistant depression: an open-label feasibility study. Lancet Psychiatry 3(7):619–627 5. Cavedoni S, Chirico A, Pedroli E, Cipresso P, Riva G (2020) Digital biomarkers for the early detection of mild cognitive impairment: artificial intelligence meets virtual reality. Front Hum Neurosci 14:245. https://doi.org/10.3389/fnhum.2020.00245
|
|