Fitbit for Addicts Could Predict Relapse

Wrist biosensors accurately detect drug use, and someday could anticipate when a relapse will occur

3 min read
Fitbit for Addicts Could Predict Relapse
Photo: Empatica

Fitness trackers promise to help us move more, get better sleep, and ultimately improve our health. New research suggests they could also help drug users break the habit.

Wearable biosensors have been used in clinical settings to detect stressseizures, and other conditions. Now, a team of emergency medicine physicians are strapping them on the wrists of patients in drug treatment programs to detect relapses—documenting when, where, and what drug was taken.

Best of all, the team hopes data from the biosensors will eventually allow them to predict when a relapse is about to occur, giving doctors and loved ones the chance to intervene.

Doctors currently monitor patient drug use through self-reporting and urine tests. The new approach provides more accurate data for physicians to track and discuss relapses with their patients, says Stephanie Carreiro, an emergency medicine physician and medical toxicologist involved in the project. Carreiro works at the University of Massachusetts Medical School in Worcester, a city battling an opioid epidemic. The sensor is “an edge up for those who are ready to get off drugs.”

The team’s pilot study, published last March in the Journal of Medical Toxicology, invited four supervised ER patients taking morphine and one individual recreationally using cocaine outside the hospital to wear wrist sensors before, during, and after a drug use event.

img Photo: Stephanie Carreiro

Each participant wore an early version of the E4 wristband from Massachusetts-based technology company Empatica. The slim, black device is like a Fitbit on steroids: It continuously measures heartbeat, motion in three dimensions, skin electrical conductance, and skin temperature. Each parameter is measured up to 30 times per second, and the device keeps track of the wearer’s location using GPS. “We have massive datasets,” says Carreiro with a laugh.

The device stores up to four days of data and streams directly to smart phones or computers via Bluetooth. Using that function, a person’s physiological and location data can be monitored in real time.

Data from drug use in the first five patients illustrated a unique signature for each type of drug. Cocaine use, for example, was accompanied by a “hurricane” of movement, says Carreiro. It was also associated with an increase in electrical skin conductance and a decrease in skin temperature. Morphine use, on the other hand, increased skin temperature and decreased movement.

In a follow-up study in the December issue of the Journal of Medical Systems, the physicians expanded the project to 15 participants wearing the wristband outside the hospital for 30 days. It was a true test of compliance: Would volunteers keep the device on, even when they were using?

The answer was a resounding yes. Every participant kept the sensor on his or her wrist, and many asked to see their data. Some even offered to wear the devices for longer periods of time, if necessary. Carreiro was pleased with the results, but emphasizes compliance was high because this was a population of individuals motivated to recover from drug abuse.

“For the first time, we could interact with a drug user…as things are happening, and intervene quickly.”

The team is now documenting drug signatures of different types of users—such as those trying a drug for the first time versus a tolerant user—and testing whether the sensors can be used to predict when an overdose victim needs more antidote and should not be discharged from the emergency room.

Ultimately, Carreiro envisions the sensors as a way to actually predict when a relapse is about to occur. By combining physiological data— which could detect when a person becomes stressed, for example—with GPS data to predict where a person is traveling, an algorithm could identify when a relapse is likely to occur and send a notification to a loved one or doctor.

“For the first time, we could interact with a drug user in their world, as things are happening, and intervene quickly,” says Carreiro.

The Conversation (0)

This CAD Program Can Design New Organisms

Genetic engineers have a powerful new tool to write and edit DNA code

11 min read
A photo showing machinery in a lab

Foundries such as the Edinburgh Genome Foundry assemble fragments of synthetic DNA and send them to labs for testing in cells.

Edinburgh Genome Foundry, University of Edinburgh

In the next decade, medical science may finally advance cures for some of the most complex diseases that plague humanity. Many diseases are caused by mutations in the human genome, which can either be inherited from our parents (such as in cystic fibrosis), or acquired during life, such as most types of cancer. For some of these conditions, medical researchers have identified the exact mutations that lead to disease; but in many more, they're still seeking answers. And without understanding the cause of a problem, it's pretty tough to find a cure.

We believe that a key enabling technology in this quest is a computer-aided design (CAD) program for genome editing, which our organization is launching this week at the Genome Project-write (GP-write) conference.

With this CAD program, medical researchers will be able to quickly design hundreds of different genomes with any combination of mutations and send the genetic code to a company that manufactures strings of DNA. Those fragments of synthesized DNA can then be sent to a foundry for assembly, and finally to a lab where the designed genomes can be tested in cells. Based on how the cells grow, researchers can use the CAD program to iterate with a new batch of redesigned genomes, sharing data for collaborative efforts. Enabling fast redesign of thousands of variants can only be achieved through automation; at that scale, researchers just might identify the combinations of mutations that are causing genetic diseases. This is the first critical R&D step toward finding cures.

Keep Reading ↓ Show less