Since 1999, opioid overdose deaths in the U.S. have increased tenfold, according to the U.S. Centers for Disease Control and Prevention. New research shows that popular smartwatch devices might be key to reversing that trend.
A team from the University of California, San Diego conducted a study about using smartwatches to track overdose risk factors. It was published on Jan.
30, in the Nature Mental Health Journal.
Professor Tauhidur Rahman, Ph.D. student Yunfei Luo at the Halıcıoğlu Data Science Institute (HDSI) at UC San Diego led the study along with Eric Garland, Ph.D., a professor of psychiatry at UC San Diego School of Medicine. They wanted to find a way to track “downward spirals of elevated stress, pain flare-ups and craving,” that people with chronic pain who have long-term opioid prescriptions can experience, but are hard to observe in a clinical setting.
To do this, they used a common smartwatch – the Garmin Vivosmart 4 (around $130 on the Garmin site). Rahman and his team enabled the watches to continuously track tiny changes in heart rhythm called “inter-beat interval data.” Then, they applied machine learning to estimate when someone may be slipping into a high-risk state for a potential overdose to create a tracking system.
“From these signals, the system estimates heart rate variability (HRV), a measure that often shifts when the body is under strain,” UC San Diego explained. “In simple terms, HRV provides a window into how the nervous system is responding to stress.”
With the data it collects, the smartwatch system looks for patterns that occur more often in people at high risk for opioid misuse. UC San Diego described it as a sort of “smoke alarm” for risk that doesn’t require constant check-ins.
More than 10,100 hours of wearable data from 51 adults with chronic pain on long-term opioid therapy who were equipped with the smartwatch systems were included in the study findings. They wore the watches daily outside the clinic over an eight-week period.
Participants were categorized using the Current Opioid Misuse Measure (COMM) questionnaire. Clinical records were also used to determine risk signs.
Heart rate data was mapped to create a personalized prediction of stress, pain and craving and to estimate misuse by studying the “shape” of daily patterns, UC San Diego said. Instead of looking for pain, stress or cravings in any single moment, Rahman said the team wanted to see how they created a pattern over time.
“People at higher risk of opioid misuse showed more repetitive trajectories and tended to get stuck in high stress, pain or craving – what appears in our analysis as lower entropy, or reduced flexibility over time, Rahman explained. “In contrast, those taking opioids as prescribed showed more fluctuation and rebound, reflected as higher entropy.”
His team also used clinically-trained language models to convert records “into compact numerical summaries that the prediction model can use.” Ultimately, the team hopes that clinicians can use this data to detect risk shifts between visits, imitate preventative check-ins and reduce the burden of constant reporting.
U.S. Health and Human Services Secretary Robert F. Kennedy Jr. has sung the praises of using smartwatches to monitor health. Last summer, he announced plans for an advertising campaign to encourage Americans to wear the devices.
While there was a 4% decrease in opioid overdose deaths from 2022 to 2023, they are still a public health concern. That decrease came on the heels of a 15% increase from 2020 to 2021.
“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 said.