Wearable Device Predicts Migraines With Over 90% Accuracy

By Pat Anson

Imagine what it would be like to know – with over 90% accuracy – that you’re going to have a migraine tomorrow.

You’d be able to plan ahead. Change your schedule. Get extra sleep. Stay hydrated. Avoid stress. And make a point of taking that migraine prevention drug that you often forget to take.

You may not be able to prevent tomorrow’s migraine, but you could reduce its severity and the impact it has on your life.

A wearable neuromodulation device called Nerivio makes that advance warning possible, according to a new study published in the journal Neurology. Sponsored by Theranica, the maker of Nerivio, the study is based on an analysis of data from over 53,000 people who used the device for nearly five years. 

Nerivio is worn on the upper arm and controlled by a smartphone app that uses mild electrical pulses during 45-minute treatments to disrupt migraine pain in the brain. The device also collects a lot of data from users, such as the frequency and severity of their migraines, aura and other symptoms, demographic data, and even the weather where they live.

Using machine learning and artificial intelligence, Nerivio’s Your Day Ahead feature uses data from the app to predict the likelihood of a migraine over the next 24 hours with 91.2% accuracy. The app doesn’t diagnose migraine, but it does help patients take control of their lives by enabling them to plan ahead for a migraine attack.

Migraine experts have known for decades that patients have certain tendencies that can signal a migraine may be coming. They might have an aura, mood changes, yawn more frequently, or have muscle stiffness. These are known as “prodromal” symptoms. 

But Theranica researchers found that those early warning signs contribute just 11% of Nerivio’s predictive performance. The stronger signal is the rolling average of a patient's headache severity over the preceding 30 days. It turns out those long-term headache patterns are more of a tell than the prodromal cues.

"What this analysis suggests, in the largest dataset reported to date, is that the strongest predictive signal isn't in that narrow pre-attack window. Instead, a patient's own recorded pattern of headache severity over the preceding month turns out to be the most informative signal in the model," said Chia-Chun Chiang, MD, Associate Professor of Neurology and a Headache Specialist at the Mayo Clinic. 

"That's a meaningful shift in how we think about forecasting migraine risk, and it matters for patients. Consistent, longitudinal patient-reported data isn't just a record of what's happened — it may be a window into what's likely to come next.”

Migraine affects about 39 million people in the United States and 1.1 billion worldwide. In addition to headache pain, migraine can cause nausea, blurriness, and sensitivity to light or sound. Women are three times more likely to suffer from migraines than men.   

The Nerivio device is FDA-approved for acute and/or preventive treatment of migraine in patients 8 years of age or older. Controlled by the user through the app, Nerivio provides relief during attacks and, when used regularly, helps reduce migraine frequency. The Your Day Ahead feature comes with the Nerivio app.

Nerivio is only available by prescription and is covered by many insurers. Commercially insured patients pay about $89 out-of-pocket for their first device and refills. Each device or refill kit provides 18 separate 45-minute treatments.

Without insurance, prices vary considerably, so it pays to shop around. WellRx charges $769 for a device, while UpScript charges $799 and Super.com charges $831.

Wearable Devices Could Monitor Opioid Use

By Pat Anson, Editor

We’ve written before about wearable medical devices, a fast growing $2.8 billion industry aimed at helping us lead healthier lives. Some devices relieve pain, while others monitor your blood pressure, pulse, body temperature, sleep, or even the number of calories you’re burning.

One device can even be used as a sort of “Big Brother” to monitor your use of opioid pain medication.

A small study published in the Journal of Medical Toxicology followed 30 emergency room patients who were given opioids for severe acute pain. For four months the patients wore a Q sensor, a wristband device made by Affectiva,  a Massachusetts company that specializes in technology that tracks and measures human emotions.

The wristband only monitors skin temperature and locomotion (movement) of the user, but researchers found the data can be used to track and predict opioid use with a fair degree of accuracy.

Researchers say people who take opioids daily for pain or addiction treatment (methadone and buprenorphine) are more likely to fidget or show restless activity when they feel cravings for medication. A sudden decrease in movement and an increase in skin temperature can be signs that they had taken a dose of medication.   

"The patterns may be useful to detect episodes of opioid use in real time," says lead author Stephanie Carreiro, MD, a professor of Emergency Medicine at the University of Massachusetts Medical School. "The ability to identify instances of opioid use and opioid tolerance in real time could for instance be helpful to manage pain or during substance abuse treatment."

Carreiro and her colleagues say wearable devices could help identify pain patients at risk for substance abuse or addiction. They could also be used to remotely monitor patients enrolled in addiction treatment programs to detect whether they are relapsing.

“Wearable biosensors show a consistent physiologic pattern after opioid administration in an ED (emergency department) population,” they said. “This biometric response shows some distinguishing features between heavy and non-heavy opioid users in a controlled ED setting. This pattern may be useful to detect episodes of opioid use in real time. Further study is needed to evaluate the potential diagnostic and interventional applications of these devices in drug abuse treatment and pain management."

The Q sensor was initially developed to monitor children with epilepsy or autism, but they’ve since grown into a tool used in consumer focus groups to measure responses to advertising. They’re also being tested in middle schools as an “engagement pedometer” to measure if students are interested in a particular subject.

Critics say the technology is creepy and the data it generates can easily be misinterpreted.

"In high school biology I didn't learn a thing all year, but boy was I stimulated. The girl who sat next to me was gorgeous. Just gorgeous," Arthur Goldstein, an English teacher and critic of the technology told Reuters.

Affectiva recently raised $14 million in funding to develop facial recognition software for video games.