Opioid overdoses continue to take a devastating toll across the United States, claiming nearly 80,000 lives in 2023 alone, according to the U.S. Centers for Disease Control and Prevention (CDC). Amidst this crisis, a promising study from the University of California San Diego suggests that a simple smartwatch could play a crucial role in preventing opioid misuse by detecting early warning signs.
The study, led by Professor Tauhidur Rahman and Ph.D. student Yunfei Luo at the Halıcıoğlu Data Science Institute, aims to address the gaps in current monitoring practices. Traditionally, clinicians rely on periodic check-ins, which can miss critical moments when a patient’s risk of misuse spikes. The UC San Diego team proposes a continuous monitoring approach using a smartwatch to track subtle changes in heart rhythm, potentially providing life-saving alerts.
Innovative Approach to Monitoring
Researchers have long understood that individuals with chronic pain and long-term opioid prescriptions are vulnerable to cycles of stress, pain flare-ups, and cravings. These shifts can increase the risk of opioid misuse and addiction. The UC San Diego study introduces a system that utilizes a wearable device to collect inter-beat interval data, which is then analyzed to estimate heart rate variability (HRV).
HRV is a measure that often shifts when the body is under strain, offering insights into the nervous system’s response to stress. The system tracks stress, pain, and craving levels, identifying patterns that suggest a higher risk of opioid misuse compared to those adhering to prescribed medication regimens.
Study Methodology and Findings
The study involved 51 adults with chronic pain on long-term opioid therapy, collecting over 10,140 hours of wearable data using a Garmin Vivosmart 4 smartwatch. Participants were categorized using the Current Opioid Misuse Measure (COMM), a standard questionnaire that helps clinicians identify potential misuse signs.
“We built a system that uses a wearable device to collect inter-beat interval data, the tiny timing differences between heartbeats,” explained Yunfei Luo. “From these signals, the system estimates heart rate variability (HRV), a measure that often shifts when the body is under strain.”
The study’s key outputs included predicted stress, pain, and craving levels over time, culminating in a “misuse risk” classification based on these trajectories and clinical record analysis.
Personalized Prediction and Risk Assessment
Eric Garland, a lead clinical scientist from UC San Diego Health, emphasized the importance of personalized monitoring. “HRV is deeply personal,” he noted. “What looks like ‘high craving’ for one person may be normal for another.” To address this, the team developed personalized models using a learning-to-branch technique, allowing for more data-efficient and individualized predictions.
Professor Rahman highlighted the focus on daily patterns rather than isolated moments. “Using nonlinear dynamical analysis, we examined whether a person’s daily patterns were more rigid and predictable or more flexible and variable,” he said. “Those at higher risk showed more repetitive trajectories, indicating lower entropy, or reduced flexibility over time.”
Enhancing Prediction Accuracy
To improve the system’s accuracy, the researchers integrated clinical context from medical records, including demographics and prescription history. By combining smartwatch data with clinical insights, the system could better detect risk shifts and prompt timely interventions.
This approach aims to reduce the burden of constant self-reporting, providing a more seamless and effective monitoring solution for chronic pain patients.
Future Implications and Next Steps
The team envisions this technology supporting “just-in-time interventions,” delivering help precisely when needed. Rahman, who also directs the Mobile Sensing and Ubiquitous Computing (MOSAIC) Laboratory, expressed optimism about the potential impact of mobile and wearable sensors combined with AI and machine learning.
“As overdose deaths remain high nationally, the long-term hope is that tools like this could help clinicians move from periodic snapshots to continuous, patient-friendly monitoring — and intervene earlier, before risk becomes tragedy,” Rahman stated.
The study, published in Nature Mental Health, marks a significant step toward integrating technology into healthcare solutions. A full U.S. utility patent application has been filed for this innovative system, titled “System and Method for Personalized Closed-Loop Opioid Addiction Management with Mobile and Wearable Sensing of Administrations, Affective States and Misuse Risk Scores.”
As the opioid crisis continues to challenge communities globally, the development of such technologies offers a beacon of hope, potentially transforming how addiction and misuse are monitored and managed.
