Natural speech algorithm applied to baseline interview data can predict which patients will respond to psilocybin for treatment-resistant depression. Carrillo, F., Sigman, M., Fernández Slezak, D., Ashton, P., Fitzgerald, L., Stroud, J., Nutt, D., J., & Carhart-Harris, R., L. Journal of Affective Disorders, 230:84-86, Elsevier, 4, 2018.
Natural speech algorithm applied to baseline interview data can predict which patients will respond to psilocybin for treatment-resistant depression [link]Website  abstract   bibtex   
Background: Natural speech analytics has seen some improvements over recent years, and this has opened a window for objective and quantitative diagnosis in psychiatry. Here, we used a machine learning algorithm applied to natural speech to ask whether language properties measured before psilocybin for treatment-resistant can predict for which patients it will be effective and for which it will not. Methods: A baseline autobiographical memory interview was conducted and transcribed. Patients with treatment-resistant depression received 2 doses of psilocybin, 10 mg and 25 mg, 7 days apart. Psychological support was provided before, during and after all dosing sessions. Quantitative speech measures were applied to the interview data from 17 patients and 18 untreated age-matched healthy control subjects. A machine learning algorithm was used to classify between controls and patients and predict treatment response. Results: Speech analytics and machine learning successfully differentiated depressed patients from healthy controls and identified treatment responders from non-responders with a significant level of 85% of accuracy (75% precision). Conclusions: Automatic natural language analysis was used to predict effective response to treatment with psilocybin, suggesting that these tools offer a highly cost-effective facility for screening individuals for treatment suitability and sensitivity. Limitations: The sample size was small and replication is required to strengthen inferences on these results.
@article{
 title = {Natural speech algorithm applied to baseline interview data can predict which patients will respond to psilocybin for treatment-resistant depression},
 type = {article},
 year = {2018},
 identifiers = {[object Object]},
 keywords = {Computational psychiatry,Depression,Machine learning,Natural speech analysis,Predict therapeutic effectiveness,Psilocybin treatment,Treatment-resistant depression},
 pages = {84-86},
 volume = {230},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/29407543,https://www.sciencedirect.com/science/article/abs/pii/S0165032717311643?via%3Dihub},
 month = {4},
 publisher = {Elsevier},
 day = {1},
 id = {7127a8f1-3589-3698-93d7-c16d49ea2bdd},
 created = {2019-07-16T12:40:18.820Z},
 accessed = {2018-02-13},
 file_attached = {false},
 profile_id = {38c6dbcb-2394-3f18-9217-58d777c08c69},
 group_id = {d9389c6c-8ab5-3b8b-86ed-33db09ca0198},
 last_modified = {2019-09-12T16:41:39.655Z},
 tags = {CA,Disc:Psychopharmacology},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Carrillo2018},
 notes = {<b>From Duplicate 1 (<i>Natural speech algorithm applied to baseline interview data can predict which patients will respond to psilocybin for treatment-resistant depression</i> - Carrillo, Facundo; Sigman, Mariano; Fernández Slezak, Diego; Ashton, Philip; Fitzgerald, Lily; Stroud, Jack; Nutt, David J.; Carhart-Harris, Robin L.)<br/></b><br/>LB},
 private_publication = {false},
 abstract = {Background: Natural speech analytics has seen some improvements over recent years, and this has opened a window for objective and quantitative diagnosis in psychiatry. Here, we used a machine learning algorithm applied to natural speech to ask whether language properties measured before psilocybin for treatment-resistant can predict for which patients it will be effective and for which it will not. Methods: A baseline autobiographical memory interview was conducted and transcribed. Patients with treatment-resistant depression received 2 doses of psilocybin, 10 mg and 25 mg, 7 days apart. Psychological support was provided before, during and after all dosing sessions. Quantitative speech measures were applied to the interview data from 17 patients and 18 untreated age-matched healthy control subjects. A machine learning algorithm was used to classify between controls and patients and predict treatment response. Results: Speech analytics and machine learning successfully differentiated depressed patients from healthy controls and identified treatment responders from non-responders with a significant level of 85% of accuracy (75% precision). Conclusions: Automatic natural language analysis was used to predict effective response to treatment with psilocybin, suggesting that these tools offer a highly cost-effective facility for screening individuals for treatment suitability and sensitivity. Limitations: The sample size was small and replication is required to strengthen inferences on these results.},
 bibtype = {article},
 author = {Carrillo, Facundo and Sigman, Mariano and Fernández Slezak, Diego and Ashton, Philip and Fitzgerald, Lily and Stroud, Jack and Nutt, David J. and Carhart-Harris, Robin Lester},
 journal = {Journal of Affective Disorders}
}
Downloads: 0