Using Wearable Devices to Improve Chronic PainTreatment among Patients with Opioid Use Disorder

TL;DR

Chronic pain (CP) and opioid use disorder (OUD) frequently co-occur, complicating MOUD management. The study proposes a proof-of-concept using wearable sensor data and AI to predict pain spikes defined as exceeding the $70^{ ext{th}}$ percentile of self-reported pain, with 25 CP+OUD patients over two weeks. Gradient-boosting models achieve predictive accuracy >0.7 for spikes up to $t+5$ days ahead, while large language models provide limited actionable insights, underscoring the promise of real-time wearable-supported interventions and the need for more capable multimodal AI tools. SHAP analysis highlights sleep and activity metrics, supporting the potential for personalized CP/OUD care, though limitations like small sample size and single-site design suggest cautious interpretation and a need for broader validation.

Abstract

Chronic pain (CP) and opioid use disorder (OUD) are common and interrelated chronic medical conditions. Currently, there is a paucity of evidence-based integrated treatments for CP and OUD among individuals receiving medication for opioid use disorder (MOUD). Wearable devices have the potential to monitor complex patient information and inform treatment development for persons with OUD and CP, including pain variability (e.g., exacerbations of pain or pain spikes) and clinical correlates (e.g., perceived stress). However, the application of large language models (LLMs) with wearable data for understanding pain spikes, remains unexplored. Consequently, the aim of this pilot study was to examine the clinical correlates of pain spikes using a range of AI approaches. We found that machine learning models achieved relatively high accuracy (>0.7) in predicting pain spikes, while LLMs were limited in providing insights on pain spikes. Real-time monitoring through wearable devices, combined with advanced AI models, could facilitate early detection of pain spikes and support personalized interventions that may help mitigate the risk of opioid relapse, improve adherence to MOUD, and enhance the integration of CP and OUD care. Given overall limited LLM performance, these findings highlight the need to develop LLMs which can provide actionable insights in the OUD/CP context.