Machine learning based phenotyping of the response to mindfulness for chronic low back pain
Akshit Soota, Angela C. Incollingo Rodriguez, Benjamin C. Nephew, Paula Gardiner, Jean A. King, Natalia E. Morone, Carolina Ruiz
preprint DOI: 10.1101/2025.08.19.25333990 (opens in new tab)
Summary
AI-generated from the abstractMachine learning applied to data from a clinical trial of mindfulness for chronic low back pain identified distinct phenotypes that predict who will respond to the intervention. Among 132 participants in the mindfulness arm, 49 were responders and 83 were non-responders. The top three responder phenotypes correctly identified 26 of the 49 responders with 92-100% precision, and the top three non-responder phenotypes identified 36 of the 83 non-responders with 100% precision. These results may help clinicians and patients decide whether mindfulness is likely to be beneficial, improving treatment efficiency and outcomes.
Study at a glance
| Characteristics | Secondary analysis of a clinical trial |
|---|---|
| Sample size | 132 |
| Population | Participants in the intervention arm of a clinical trial of mindfulness for chronic low back pain |
| Intervention | Mindfulness |
| Key finding | Machine learning identified phenotypes that predict response to mindfulness for chronic low back pain with high precision. |
Abstract
ABSTRACT Millions of people each year suffer from chronic low back pain (cLBP), which adversely affects their physical and mental health. While non-pharmacological interventions such as mindfulness are known to be effective in treating cLBP, not all patients experience the same benefit. Determining who these treatments might work best for is difficult, as there are no reliable predictors of the response to mindfulness for cLBP. The objective of the current study was to apply predictive machine learning to data collected from a completed clinical trial of mindfulness for cLBP to identify phenotypes characterizing those who did and did not respond to the intervention. The analyses here focused on 132 participants in the intervention arm of the clinical trial of mindfulness for cLBP. The Random Forest machine learning technique was used to identify key characteristics of responders (49) and non-responders (83). The top three responder phenotypes were able to identify 26 out of the 49 responders with 92-100% precision. The top three non-responder phenotypes were able to identify 36 out of 83 non-responders, all with 100% precision. Results from this machine learning based phenotyping can guide clinician and patient decision-making to maximize clinical efficiency, patient outcomes, and resource use as well as inform research and development of mindfulness-based treatments for pain.