Integrative Mindfulness-Based Predictive Approach for Chronic Low Back Pain Treatment

This study will identify unique signatures that people have which can cause pain by evaluating biological, psychological, and social markers using artificial intelligence. These markers can be used to accurately predict the response of diverse individuals with chronic low back pain (cLBP) to Mindfulness-Based Stress Reduction. This will help enhance clinician decision-making and the targeted treatment of chronic pain. The overall objective is to use a unique machine learning (ML) approach to determine the biomarker signature of persons undergoing mindfulness based stress reduction (MBSR) treatment for their chronic low back pain (cLBP). This signature will facilitate clinical prediction and monitoring of patient response to MBSR treatment. The design of the study is a single-arm clinical trial of the evidence-based MBSR program for patients with cLBP.

UG3 Phase Overview. The first 24-months of the project will be dedicated to performing machine learning modeling to identify candidate predictive and monitoring markers of cLBP response to MBSR, prior to the full clinical trial in the UH3 phase. We will also refine our procedures such as recruitment and outcomes assessment with 50 persons during the UG3 phase. UH3 Phase Overview. Biopsychosocial markers will be identified of the response of diverse cLBP patients to MBSR (N=300) from comprehensive pain assessment and biopsychosocial data, including pain intensity and pain interference, physical activity, sleep, and heart rate for a 6-month period. Data will be collected and used for training and testing ML models. The MBSR program is evidence-based and meets weekly in a group via Zoom for 8-weeks for 90 minutes per week. Measures to determine biomarkers will be obtained at baseline (T1), four-weeks (T2), program completion (T3), four months (T4), and six months (T5). The main outcome timepoint with be at six months (T5), which allows time for durability of effects to be determined. The PEG (Pain, Enjoyment, General activity), obtained through online self-report surveys is the main outcome measure. Secondary outcomes of physical and psychological function will be self-report and obtained online, or if the patient prefers, by telephone, and physical activity, sleep, and heart rate variability will be collected by Fitbit.