Can AI Reinvent Pain Management?

It hasn’t taken long for AI to emerge as a solution to a host of problems. Whether it’s a component in automotive software to improve driver safety or it helps power face recognition tech for law enforcement.

Now, researchers at Worcester Polytechnic Institute (WPI) want to find out if AI brains can help human ones.

WPI has announced plans for a five-year research project “to determine whether artificial intelligence can help doctors steer people dealing with chronic pain away from potentially addictive opioids and toward mindfulness-based approaches.”

Managing Pain with AI

As part of The National Institutes of Health (NIH) HEAL initiative, the WPI study plans to leverage machine learning to comb through years of patient data and track down any indicators that might help medical professionals better decide which patients might benefit from mindfulness-based stress reduction (MBSR) for pain management.

In 2021, the most recent year for which data is available, the U.S. Centers for Disease Control and Prevention (CDC) estimated that nearly 21 percent of U.S. adults suffered from chronic pain. That works out to be more than 51 million Americans. Nearly 7 percent of Americans – more than 17 million – endure high-impact chronic pain.

“For physicians, it will be a new day,” WPI’s Peterson Family Dean of Arts and Sciences said Jean King explained in a press release. “To be able to predict who would respond well to non-pharmacological interventions will truly save lives.”

Searching for a Way Around Opioids

Researchers hope they’ll discover better ways to treat chronic pain sufferers than relying on opioids.

Earlier research has found that MBSR can be effective in treating chronic pain. But not every patient responds well to it. But medical professionals still don’t know why.

The WPI study plans to focus on “chronic lower back pain in diverse populations.” Researchers plan to pull physiological data such as sleep patterns, heart rate, and general physical activity. To do so, the team will outfit study participants – 3,350 so far – with fitness sensors for six months.

Participants will also provide data on their emotional state, whether they’re depressed, feeling anxious, or experiencing pain.

The researchers also plan to include racially and ethnically diverse populations in their study since – despite their consistent underrepresentation – they remain at greater threat of stress, chronic pain, and the risks associated with that.

Finally, the WI team plans to pull from the Boston metro area through Boston Medical Center and Cambridge Health Alliance, and from the Worcester, Massachusetts, region via UMass Chan and WPI.

Leaning On AI

The PI researchers designed machine learning models to sift through all that data and report on any identifiable patterns that might elude a human doctor. And with this information, the AI can “predict whether a patient would beneficially respond to mindfulness, helping doctors better tailor treatments for individual patients.”

“It will save time for the patient—they won’t have to go through a treatment that isn’t going to help,” WPI Associate Dean of Arts and Science Carolina Ruiz said. “It will also save a lot in healthcare costs and could be applicable to other types of pain and other types of treatment.” 

Federal Funding to Explore Mindfulness

The NIH is underwriting WPI’s research with a $1.6 million grant to launch the trial. If the team hit certain benchmarks, the feds could come through with nearly $9 million in total funding over the next half-decade.

The study, dubbed the Integrative Mindfulness-based Predictive Approach for Chronic low back pain Treatment, or IMPACT, will gather a diverse group of researchers from WPI, UMass Chan Medical School, and Boston University Chobanian & Avedisian School of Medicine.

Further Reading

How Pain Can Be an Addiction

Social Media Images Can Predict Suicide Risk

Opioid Use Disorder and Its Treatment in the Elderly