AliveCor's AI for noninvasive blood potassium screening snags Breakthrough Device designation from FDA

The KardiaK Software Platform could be used with mobile ECG devices to identify potential cases of kidney disease.
By Dave Muoio
11:35 am
Share

Mountain View, California-based AliveCor announced yesterday that its KardiaK Software Platform has been granted Breakthrough Device designation by the FDA.

AliveCor’s software is a neural network trained to read ECG data for elevated levels of blood potassium, a condition known as hyperkalemia that affects the kidneys.

Primarily diagnosed through invasive laboratory blood test, KardiaK would require no blood draws to measure a patient’s blood potassium, and could be performed at home if the user owns a home ECG device (which are also produced by AliveCor).

“We are gratified that the artificial intelligence work we’re doing at AliveCor has been deemed so meaningful that it has achieved FDA Breakthrough Device status,” AliveCor CEO Vic Gundotra said in a statement. “We view it as a key milestone in our corporate history and look forward to the further development of our non-invasive hyperkalemia detection tools,” said Vic Gundotra, CEO of AliveCor.

As laid out in the 21st Century Cures Act, the Breakthrough Devices Program looks to streamline new medical technologies that offer improved treatment or diagnosis for serious diseases with unmet needs. While the Breakthrough Device designation itself is not a clearance, FDA works with the device’s sponsors to reduce the time and and money spent during validation and regulatory approval.

AliveCor presented a retrospective analysis of the KardiaK platform’s performance against more than 2 million ECGs and 4 million serum potassium values at the American College of Cardiology Scientific Sessions meeting earlier this year. According to the company, its algorithm demonstrated an AUC of 0.88-0.89.

“This test, which performed extremely well in our evaluation using millions of ECGs, holds the promise of enabling people to painlessly determine whether a life-threatening and otherwise silent and very treatable condition is present — from the comfort of their own homes and within seconds,” Dr. Paul Friedman, chair of the department of cardiovascular medicine at the Mayo Clinic and one of the test’s co-developers, said in a statement. “It may save people’s lives, and save the health care system dollars.”

AliveCor and the Mayo Clinic first announced their work on hyperkalemia in March, along with a study on atrial fibrillation in collaboration with the Cleveland Clinic.

"The Mayo Clinic partnered with AliveCor ... on trying to do something extraordinary, which was to to look at the ECG, use artificial intelligence, and hope the AI would be able to look at a single ECG and be able to tell you your potassium level," Gundotra told MobiHealthNews at the time. "That is kind of crazy because [calculate] potassium levels you usually have a blood test. High potassium or low potassium can be life threatening."

AliveCor is best known for its mobile and wearable ECG devices, such as the KardiaMobile and the KardiaBand. The company — which raised $30 million from the Mayo Clinic and Omron Healthcare last year — has recently put out a wealth of data on how pairing these hardware with AI could potentially catch unnoticed cases of atrial fibrillation.

Share