Researchers at the Mayo Clinic report early-stage success with a wearable wristband that can anticipate epileptic seizures up to 30 minutes before they occur.
Researchers at the Mayo Clinic have reportedly developed a wearable device that can detect the onset of epileptic seizures 30 minutes before they occur.
As documented in Nature, the preliminary study focused on just six patients living with drug-resistant epilepsy and being treated at the Mayo Clinic, so more research is needed. But the apparent success of a wristband and telehealth platform designed by Boston-based Empatica “provides the first clear evidence that direct seizure forecasts are possible using wearable devices in the ambulatory setting for many patients with epilepsy.”
The research could eventually greatly benefit the estimated 3.4 million Americans living with epilepsy, including close to 500,000 children. They live with the threat of a sudden seizure at any time, especially those living with recurrent seizures. Treatment is focused on neurostimulation and/or medications, even (but rarely) surgery.
“Despite optimized medication therapy, resective surgery, and neuromodulation therapy, many people with epilepsy continue to experience seizures,” the researchers wrote. “Half or more of patients who undergo resective surgery for epilepsy have eventual recurrence of seizures, and devices for neuromodulation rarely achieve long-term seizure freedom. People living with epilepsy consistently report the unpredictability of seizures to be the most limiting aspect of their condition. Reliable seizure forecasts could potentially allow people living with recurrent seizures to modify their activities, take a fast-acting medication, or increase neuromodulation therapy to prevent or manage impending seizures.”
That’s where digital health innovation comes into play. The development of sensors and mHealth devices over the years has given healthcare researchers a platform on which to work with mobile and wearable devices that capture and analyze biometric data. In time, these tools can be used for chronic care management and coordination.
More recently, researchers have developed tools that gather data to anticipate a health concern before it happens, such as hyperglycemia or hypoglycemia in people living with diabetes, the onset of a stroke or heart attack, even early signs of a virus like the flu or COVID.
In this study, Mayo Clinic researchers crafted a seizure forecasting system with a long short-term memory (LSTM) recurrent neural network (RNN) algorithm, than implanted it in a wristband. They tested the device on patients in the field, comparing the results against an implanted device that tracked seizures through an EEG.
The researchers pointed out that epileptic seizures have been accurately forecast in the past through implanted devices in both dogs and humans, but not everyone likes or can live comfortably with such an invasive device.
The study also noted that seizure prediction via wearable devices have been tested in in-patient settings, with some success. Hence the research into a non-invasive wearable.
According to the study, six patients were tracked over six months (one patient’s device was faulty and had to be replaced). Five of the six “had seizure forecasts significantly more accurate than a random predictor,” with detection on average occurring 33 minutes before the seizure was picked up by the EEG.
“These results provide the first clear evidence that direct seizure forecasts are possible using wearable devices in the ambulatory setting for many patients with epilepsy,” the study concluded.
Eric Wicklund is the associate content manager and senior editor for Innovation at HealthLeaders.