Can Researchers Detect Irregular Heart Rhythms with the Apple Watch? (usatoday.com)

An anonymous reader quotes USA Today: Might wearing an Apple Watch save you from a stroke or cardio problem? Apple is careful not to make that direct claim. But the company, in collaboration with Stanford University School of Medicine, launched the Apple Heart Study app on Thursday that uses the heart rate sensor inside the Apple Watch to collect data on irregular heart rhythms... If an irregular heart rhythm is detected, participants in the study will be notified through the Apple Watch and on their iPhones. Should that occur, you'll be offered a free consultation with a study doctor, and possibly an electrocardiogram patch for additional monitoring...

A participant in the study merely has to download the app and wear the watch... The way Apple explains it, a sensor inside the watch uses green LED lights flashing hundreds of times per second and light-sensitive photodiodes to detect the amount of blood flowing through the wrist. The sensor has an optical design that gathers signals from four distinct points on the wrist. Using software algorithms, the Apple Watch can isolate heart rhythms from other noise, and identify an irregular heart rhythm.
The FDA has also approved the first personal electrocardiogram accessory for the Apple Watch, according to TechNewsWorld. "The KardiaBand" also detects and records atrial fibrillation that can lead to strokes or other heart problems. "The user simply touches an integrated sensor, and the results are then displayed on the face of the Apple Watch."

An irregular, bloodflow-disrupting heartbeat is the top cause of strokes, which kill 130,000 people every year just in the U.S. -- in many case before they've experienced any symptoms.

Comments

Canâ(TM)t participate in the study :-(

[Ronin Developer]

As someone who suffers from the occasional AFIB and bigemeni heartbeat, I was dismayed that a condition of joining the study is NOT knowing if you have AFIB.

You discover this AFTER downloading the app and applying.

As for keeping the data local ... it is send to a machine learning algorithm to help it learn to detect arrhythmia. Keeping that data simply wonâ(TM)t work.

All this being said, I have found my AppleWatch invaluable as an aid to getting healthier. I received mine in late October. By concentrating on closing the rings every day, I have lost seven pounds and have had all my glucose readings in range for the past 3 weeks. Yes, exercise and diet alone probably would have done it. But, having the little taskmaster pushing me and giving a slight incentive worked for me and made the exercise regime and weight loss effort fun. Yes, I now weigh 223 pounds ( and 73 inches). I am not short and stout (there, either).

Re:Canâ(TM)t participate in the study :-(

[nine-times]

I was dismayed that a condition of joining the study is NOT knowing if you have AFIB.

My understanding is that they're hoping to be able to detect the condition that causes irregular heartbeats, and not necessarily detecting the actually instances of irregular heartbeat.

That is, the benefit would be for someone going through their lives unaware that they have a heart condition, and it could provide warning to them that they should talk to their doctor for an in-depth examination. It's not to alert you that you're having an irregular heartbeat while you're having an irregular heartbeat. I might imagine that the kind of measurements they're trying aren't reliable enough to warrant an emergency response in the event that a single event is detected. For example, it might be that scratching your wrist is enough to disrupt the contact between your skin and the watch, causing a reading that looks like an irregular heartbeat. But even if it's not reliable in detecting an individual incident, it might still be good enough to detect a condition when the data is taken in aggregate.

On the other hand, it does seem a little strange that they'd exclude people who know they have a condition. I would think they'd want to know whether people did or didn't have a condition, so that after taking the data and predicting who had a heart condition, they could compare their predictions of whether people had the condition with actual diagnoses. Otherwise, how would they be able to tell whether their predictions were correct?

Re:Great with a caveat...

[TheRaven64]

It's actually a shame that there isn't some anonymised collection of this data. Talking to a cardiologist friend a few months ago, one of the biggest problems that they have is that they don't actually know what a regular heartbeat looks like. Lost of people are diagnosed with heart problems and then wear a monitor, but no one sticks heart monitors on healthy people for a few months to get a good baseline. What the discipline really needs is a few thousand healthy people to wear a heart monitor for a year. They suspect that various forms of arrhythmia are actually quite common and not life threatening, but they have to assume that they are because the only times that they see them are when people have been specifically referred to a cardiologist.