High blood potassium, or hyperkalemia, is linked to a number of health issues. AliveCor is working on a new application for the technology behind its KardiaBand for Apple Watch. Last year, the FDA approved KardiaBand as a medical device, and it can record your heart rhythm and report on any rhythmic abnormalities that could be linked to dangerous health issues. Now, The Verge reports, AliveCor is developing a way for its technology to be used to detect high levels of potassium in the blood. High blood potassium levels constitute a condition known as hyperkalemia. It can be related to a number of causes, including kidney disease, dehydration, injury and diabetes and hyperkalemia can affect heartbeat rhythm. Yesterday, during the American College of Cardiology conference, AliveCor presented work done with the Mayo Clinic showing that its technology can detect hyperkalemia through EKGs. The researchers used electrocardiogram data collected from 709,000 patients over the course of 23 years, which included 2.1 million EKGs and 4 million blood potassium measurements. Two-thirds of that data were used to train a neural network to detect hyperkalemia through EKG readings. That network was then tested on the other third of the data. It was able to correctly detect cases of hyperkalemia 85 percent of the time and accurately label those that weren't hyperkalemic 72 percent of the time. The team also tested it on 10 patients using an experimental AliveCor smartphone EKG device and from almost 50 hours of data -- 5.4 of which recorded a hyperkalemic state -- the neural network was able to correctly spot hyperkalemia 94 percent of the time and non-hyperkalemia 74 percent of the time. It's important to note that these findings are preliminary and AliveCor's technology hasn't been approved by the FDA to detect hyperkalemia. The company is continuing with its trials, The Verge reports, and will likely seek FDA clearance in the future.
The AliveCor KardiaBand, a sensor compatible with the Apple Watch, can detect dangerous levels of potassium in blood with 94 percent accuracy. Though the US Food and Drug Administration has not yet approved KardiaBand for this purpose, its an interesting step forward considering that, right now, the condition is usually caught using invasive blood tests that use needles. The KardiaBand by AliveCor is a sensor that snaps into a slot on the watchband. The user touches the sensor, which then takes a reading of the electrical activity of the heart, called an electrocardiogram (EKG). This reading can reveal abnormal heart rhythm and atrial fibrillation (AFib), and the sensor sends the information to an app. Yesterday, at the American College of Cardiology conference in Florida, AliveCor CEO Vic Gundotra presented research done with the Mayo Clinic showing that the same technology can detect too-high levels of potassium in the blood, called hyperkalemia. Hyperkalemia can be caused by, among other things, diabetes, dehydration, and chronic kidney disease. It can lead to kidney and heart failure and in general doesnt cause obvious symptoms — meaning you could have the condition and not know it. Too much potassium interferes with the electrical activity of cells, including heart cells. This means that its dangerous for the heart — but it also means that high potassium levels change the electrical reading of the heart, which means that a certain EKG pattern can reveal the presence of too much potassium, according to Gundotra. AliveCor worked with the Mayo Clinic to develop a new algorithm for the KardiaBand that can analyze EKG data and detect whether the user has hyperkalemia. The dataset included 2 million EKGs linked to 4 million potassium values, which were collected over 23 years. To train AI with these data points, the team took the dataset and divided it into parts. They used some of the data to train the network. Basically, they told it which EKG reading patterns showed hyperkalemia, and let the AI learn for itself how to spot the pattern. Once the training was complete, the team tested the AI on a different part of the data to see if, given just the EKG, they could tell if it revealed hyperkalemia. It was about 90 to 94 percent accurate. Some previous research has suggested that EKGs may not be a good way to diagnose hyperkalemia, but, to be fair, that research was very limited and tested two human physicians. Another study suggested that EKG readings may not be sensitive enough to catch everyone with hyperkalemia and that the condition doesnt always cause a different EKG reading. We dont know the number, but I can tell you that people do have hyperkalemia with a normal EKG, says William J. Brady, a professor of internal medicine at the University of Virginia School of Medicine. But in general, he says, hyperkalemia will produce a clear abnormality in the ECG, and he has initiated treatments in patients based on the EKG before getting a blood test back to confirm. In other words, I put a fair amount of trust and faith in the ECG in this regard, he adds, though novice physicians or those unused to reading EKGs will of course find this type of interpretation more difficult. Itll be a while before we see this new technology become common. Last November, the FDA cleared the KardiaBand as the first medical device that works with the Apple Watch, but Gundotra stresses that the results dont mean that the KardiaBand is FDA cleared for diagnosing hyperkalemia yet. Theyll be working on that and building more clinical trials. Update March 12th, 5:30PM ET: This post has been updated to include context from William Brady, a professor of internal medicine at the University of Virginia School of Medicine.