Matt Hoffman

home

authors

matt-hoffman

In the near future, it might be common to see patients with epilepsy sporting the Embrace smartwatch, a wearable device that uses advanced machine learning to watch for seizures. The FDA approved the technology this week, further bolstering the regulator’s commitment to digital health and opening the product to the US market.

The Embrace scans for the “most dangerous kinds of seizures,” meaning grand mal and generalized tonic-clonic seizures, and sends alerts to caregivers when appropriate, according to 

 from Empatica, the company that makes the device. In a clinical study, the algorithm powering the smartwatch detected every single seizure, or 40 total, over 272 days.

“The FDA approval of the Embrace device to detect major convulsive seizures represents a major milestone in the care of epilepsy patient,” 

 Orrin Devinksy, MD, who heads the Comprehensive Epilepsy Center at New York University. “Tragically, more than 3000 Americans die each year from sudden unexpected death in epilepsy, and the Embrace offers the potential to alarm family members and caretakers that a tonic-clonic seizure is occurring.”

Ultimately, Devinsky noted, evidence suggests that “prompt attention” to these convulsive seizures can save lives. The Embrace aims to foster that goal, improving responses and patient outcomes.

Empatica’s multicenter clinical trial of the smartwatch included 135 patients with epilepsy, who were monitored via video for 272 days, yielding 6500 hours of data. Independent epileptologists confirmed the 40 seizures that occurred during that period, and they didn’t have access to the smartwatch data.

Electrodermal activity signals enable the Embrace to gauge sympathetic nervous system activity, making the sensor something of a substitute for a biomarker and a clear alternative for a wearable electroencephalography device.

The manufacturer also touted the look and feel of the product, which has been available to patients in Europe for some time.

“Medical devices face a huge problem: They’re usually too bulky and uncomfortable, and people simply don’t want to wear them. Empatica took a different path,” Matteo Lai, MSc, CEO and co-founder of the company, said. “We wanted to design the world’s first medical device that could win a design award while being used as a lifesaving product.”

The recent FDA approval is in line with the agency’s ever-growing digital focus. The regulator has pledged a commitment to digital health and has subsequently backed it up with recent approvals for innovations like 

 for the Apple Watch, a smartphone-ready insertable 

Articles

Advanced machine learning enables the wearable device to spot events and summon help.

FDA Green-Lights Smartwatch Whose AI Monitors Seizures 

Artificial intelligence (AI) is showing promise in yet another corner of healthcare. This time, researchers said, a conversational tool appears adept at helping patients with type 2 diabetes (T2D) shed excess pounds.

Natalie Stein, MPH, MSc, a professor in Michigan State University’s college of human medicine, led a study that examined how an automated text-based coaching service affected 239 patients with T2D who were overweight or obese (body mass index [BMI] ≥25 kg/m2). On average, patients lost 2.38% (standard error, 0.69%) of their baseline weight, 

Nearly 70% of American adults have prediabetes or are overweight and at risk for T2D. The country, meanwhile, is up against a lack of healthcare providers. That means face-to-face behavioral counseling isn’t on the table for everyone.

The new technology, called the Lark Weight Loss Health Coach AI, emulates health counseling typically performed by professionals. The app includes features like a dashboard with the ability to monitor activity, sleep, food, weight, and notes.

In sample conversations, the bot asked questions and replied to statements.

In 1 case, it asked a user, “What did you have for breakfast?” Depending on the answer, the health coach’s response offered either positive reinforcement or constructive criticism and tips on how to eat better. For example, when a user claimed to have eaten eggs, bacon, toast, and coffee, the AI listed how many times that individual ate bacon over the past week and recommended a leaner source of protein. But when the user replied, “Chicken, veggies, and rice,” the bot praised the healthy choice.

Although the study started with 239 people, 159 installed the app and entered baseline height and weight data. Then, 83 recorded a second weight, and 75 did not. Researchers targeted 70 participants who appeared “active” enough to analyze, deeming another 13 “inactive,” according to the study.

Throughout the study period, users averaged 103 sessions, and 75.7% of them (n = 53) experienced weight loss. The mean decrease was 2.4 kg, while the number of healthy meals eaten increased by 31% at 21 weeks, according to the report.

An in-app trust survey returned a 100% response rate, achieving 7.9 out of 10 in average user satisfaction with the program, a disappointment level of 8.3 if not offered the program, and 6.73 in their satisfaction with the outcome.

Together, the study results suggested that health coaching AI is “available for real-life applications,” Stein and co-author Kevin Brooks, MS, PhD, noted.

From here, researchers plan to study how the AI coach can boost diet and other components of chronic disease management, including hypertension and prediabetes.

This, of course, is but AI’s latest entry into healthcare. Along with patient-facing roles, it is also enhancing 

. AI’s potential to become a predictive powerhouse has also sparked much 

 before Amazon’s Alexa begins doling out medication information.

Images have been resized. Courtesy: Stein N, Brooks K

A Fully Automated Conversational Artificial Intelligence for Weight Loss: Longitudinal Observational Study Among Overweight and Obese Adults

If adopted more widely, the technology could offset a provider shortage.

How AI Can Help Patients with Diabetes Lose Weight

At the European Association for the Study of Diabetes (EASD) 2017 meeting in Lisbon, Portugal, Glytec presented a study demonstrating the effectiveness of its remote glucose monitoring software.

The cloud-hosted software, called Glucommander, works by remaining active after titration to the patient’s specific glucose goal, and will synthesize daily glucose measurements and analyze the data to determine when and if insulin dose adjustments are required. The work presented at EASD demonstrated that patients were able to achieve rapid glucose control and maintain long-term A1C reductions.

Previous studies on the Glucommander software have examined baseline A1C compared to those at 3 and 6 months. In this retrospective study, researchers explored the insulin dose adjustment frequency needed for diabetic patients to maintain glucose control. The study followed 74 patients using the software, with the median time between dose adjustments being 57 days, after an original 3-month treatment timeframe.

“For the increasing number of patients whose baseline A1C is at or above nine percent, getting to target is one thing, but staying there is another,” Andrew Rhinehart, MD, the chief medical officer at Glytec, said in a 

. “The optimal insulin dose this month may not work next month due to changes in any number of clinical or lifestyle-related variables, such as comorbid conditions, other medications, diet, exercise or weight, or because of a medical procedure or hospitalization.”

Severe hypoglycemia (<40 mg/dL measured as a percent of blood glucose levels) was 0.05%, serving as “further evidence” that the software is both safe and effective, according to Glytec. Additionally, the study results showed A1C baseline reductions of 8.0% to 10.3% at 3 months, 8.0% at 6 months, and 7.8% at the 1-year month. Median time to goal A1C was 7 days.

“This means that once Glucommander titrated these patients to goal, continued analyses of patterns in their blood glucose indicated that additional insulin dose adjustments were needed, on average, every eight weeks,” Rhinehart says. “This confirms that the usual and customary practice of patients waiting three to six months for a follow-up visit is not sufficient to maintain glucose control and may increase risks of hyperglycemia and hypoglycemia. The study substantiates that ongoing and more frequent insulin titration, performed in a virtual manner, enables patients to maintain A1C reductions over time.”

Glucommander software was approved for its fourth designation in August 2017 by the US Food and Drug Administration (FDA). The approval was for various enhancements, including a titration module designed for enteral nutrition, an insulin-to-carb ratio titration option for outpatients, and a streamlined transition capability for inpatients moving from intravenous to subcutaneous therapy.

A version of this story will also appear in 

Novo Nordisk, Glooko Launch New Diabetes-Management App

Digital Communications with Younger Patients Can Yield Both Benefits and Ethical Pitfalls  

The work presented at EASD demonstrated that patients were able to achieve rapid glucose control and maintain long-term A1C reductions

Matt Hoffman

Articles

FDA Green-Lights Smartwatch Whose AI Monitors Seizures

How AI Can Help Patients with Diabetes Lose Weight

Glytec's Glucommander Demonstrates Efficacy in New Study