A necklace with an array of magnetic sensors could help patients remember to take their medication, and let physicians and caregivers know if they’re complying with their drug regime.
Designed by engineers at the Georgia Institute of Technology, the MagneTrace necklace can record exactly when magnetized pills or capsules pass through a patient’s esophagus, and send the information to a smart phone or a computer. The system can also remind patients if they don’t take their medication on schedule, and it can notify physicians, caregivers, and families of the situation.
The researchers, who are about to begin testing the device on dogs, say that the necklace could help patients avoid serious problems and improve clinical trials, not to mention save the billions of dollars that are wasted annually as a result of drug noncompliance.
“It’s a huge issue,” says Maysam Ghovanloo, an assistant professor in the Georgia Institute of Technology’s School of Electrical and Computer Engineering, who began the work two years ago at North Carolina State University. He designed the device with graduate student Xueliang Huo.
About half of all medications are not taken as prescribed, according to the World Health Organization. There are other tools on the market to help with drug compliance, including pill bottles that record when they’re opened, but “they can’t tell that the drug was actually taken,” says Ray Bullman, executive vice president of the National Council on Patient Information and Education, a nonprofit coalition that promotes safe medicine use. The MagneTrace device “really moves it a step forward,” he says.
Other researchers are working on a system that uses a fluorescent dye added to medication and traces the dye as it enters the bloodstream. However, Ghovanloo says that the long-term effects of the chemical aren’t known.
The magnets that will be incorporated in pills and capsules tracked by the MagneTrace system are round, about twice the size of the head of a pin, and coated with an inert, insoluble polymer. They would pass through a patient’s system within a day, Ghovanloo says. The coated magnets are so weak, he adds, that even if several ended up in a patient’s digestive tract at the same time, they wouldn’t clump together and create a blockage.
“They don’t have any effect on the human body,” Ghovanloo says.
The MagneTrace necklace, which weighs about an ounce, incorporates the same kind of magnetic sensors that are used in GPS units. They are spaced in pairs around the necklace: three sensors are positioned vertically, and three horizontally. Together, they can detect a tiny magnet incorporated in a pill or capsule as it travels down the esophagus, through the necklace. The sensors are driven by a control unit that includes a wireless transceiver, which can send data to a smart phone or a computer so that it records the time that pills are taken and how many are swallowed. The information can be sent to a patient’s physician, caregiver, and family members, who can also be notified if a patient hasn’t taken his medication on schedule.
Ghovanloo says that the device can’t be tricked because the algorithms it uses are smart enough to only look for the pill as it passes through the esophagus (and hence through the ring of sensors), rather than just looking somewhere in the vicinity of the sensors.
“We wanted it to be very difficult to cheat,” says Ghovanloo. He and Huo have also designed a MagneTrace patch for patients who would rather not wear a necklace.
To test the device, the researchers constructed an artificial neck. They used a length of PVC pipe about the same diameter as an adult neck, packed it with plastic drinking straws, and wrapped the necklace around the pipe. By repeatedly passing a magnetized pill through it at different orientations, they were able to figure out how many sensors were needed to track it, and to refine the algorithm. In tests, the MagneTrace necklace was 94 percent correct in detecting magnets passed through the artificial esophagus, and it produced about 6 percent false positives when pills were passed through areas outside the detection zone.
“We believe we can improve on that,” Ghovanloo says.
He feels that MagneTrace could be a boon in clinical trials, which generally rely on patients’ own records of their drug compliance, which may not be accurate, and for elderly patients who are forgetful or confused. MagneTrace could also ensure drug compliance in people who have been ordered to take medication for a contagious disease, Ghovanloo says, or a serious psychiatric disorder.
It could also help patients who are reluctant to take the drugs they need because of their unpleasant side effects, or who aren’t well educated and hence “don’t have the understanding of why they have to take medication at a certain time, or why they can’t skip a dose,” says Patrice Slojkowski, an informatics nurse at the University of California, San Diego Medical Center. There, a bar-coding system is used to ensure that inpatients are given the correct medication by nurses, and it also records when drugs are administered.
“I think something like this is probably going to be really effective,” Slojkowski says.
“It would be great,” says Olga Klibanov, a clinical assistant professor in the Temple University School of Pharmacy, who works with inner-city HIV/AIDS patients. Some of them don’t really understand the disease or treatment, or have alcohol or drug problems that make them less likely to follow a drug regime. Currently, Klibanov tries to tackle the problem by educating her patients and setting alarms on their watches or cell phones to remind them to take their medication.
How a Russian cyberwar in Ukraine could ripple out globally
Soldiers and tanks may care about national borders. Cyber doesn't.
Meet Altos Labs, Silicon Valley’s latest wild bet on living forever
Funders of a deep-pocketed new "rejuvenation" startup are said to include Jeff Bezos and Yuri Milner.
A horrifying new AI app swaps women into porn videos with a click
Deepfake researchers have long feared the day this would arrive.
Meta’s new learning algorithm can teach AI to multi-task
The single technique for teaching neural networks multiple skills is a step towards general-purpose AI.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.