Abstract
Although placebo effect sizes in clinical trials of chronic pain treatments have been increasing, it remains unknown if characteristics of individuals' thoughts or previous experiences can reliably infer placebo pill responses. Research using language to investigate emotional and cognitive processes has recently gained momentum. Here, we quantified placebo responses in chronic back pain using more than 300 semantic and psycholinguistic features derived from patients' language. This speech content was collected in an exit interview as part of a clinical trial investigating placebo analgesia (62 patients, 42 treated; 20 not treated). Using a nested leave-one-out cross-validated approach, we distinguished placebo responders from nonresponders with 79% accuracy using language features alone; a subset of these features-semantic distances to identity and stigma and the number of achievement-related words-also explained 46% of the variance in placebo analgesia. Importantly, these language features were not due to generic treatment effects and were associated with patients' specific baseline psychological traits previously shown to be predictive of placebo including awareness and personality characteristics, explaining an additional 31% of the variance in placebo analgesia beyond that of personality. Initial interpretation of the features suggests that placebo responders differed in how they talked about negative emotions and the extent that they expressed awareness to various aspects of their experiences; differences were also seen in time spent talking about leisure activities. These results indicate that patients' language is sufficient to identify a placebo response and implie that specific speech features may be predictive of responders' previous treatment.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1692-1704 |
| Number of pages | 13 |
| Journal | Pain |
| Volume | 162 |
| Issue number | 6 |
| DOIs | |
| State | Published - Jun 1 2021 |
Funding
The authors want to thank all Apkarian laboratory members who contributed to this study with their time and resources (in particular Alex Baria who scrambled and reorganized the data for us). The authors would also like to thank all patients who participated in this study for their overall commitment during the trial and their honesty and candidness during the interviews. Finally, the authors want to thank Elkin Dario Gutierrez and Rachel Ostrand from IBM Research for their help in implementing the metaphoricity and CPIDR analyses, respectively, and Elif Eyigoz and Carla Agurto from IBM Research for their discussions and feedback about the machine learning analyses and inverse covariance, respectively. This work was funded by National Center for Complementary and Integrative Health AT007987. EVP was funded through Canadian Institutes of Health Research (CIHR) and Fonds de Recherche Santé Québec (FRQS). The authors declare no competing interests.
Keywords
- Chronic back pain
- Interview
- Machine learning
- Natural language processing
- Placebo response
- Psycholinguistics
- Semantic proximity
ASJC Scopus subject areas
- Clinical Neurology
- Neurology
- Anesthesiology and Pain Medicine