Subscribe to the OSS Weekly Newsletter!

Apple Watch Isn't Great As a Medical Device

Sometimes more sophisticated technology simply becomes better at diagnosing inconsequential issues that probably could have been ignored.

This article was first published in The Montreal Gazette.

Apple wants to get into health care and they’re betting heavily on their new Apple Watch. Previous versions, though, were a bit underwhelming. As I wrote in a column last year, the Apple Watch 3 generated a lot of false positives for heart arrhythmias. But the latest version is supposed to be an upgrade, and the newly published Apple Heart Study was supposed to show off just how good the new and improved Apple Watch actually is at measuring your heart health.

The study was a massive undertaking. It enrolled more than 400,000 patients by using a downloadable app.

But the scale of the study obscures some downsides. Because patients had to already have their own Apple Watch and had to download the app to participate and record the data, the patient population skewed toward the young, the wealthy and the healthy. In the study, more than half of the participants were under 40 and only 6 per cent were over age 65.

As a result, very few patients actually had an irregular heartbeat during the trial. Only half of one per cent ended up receiving an alert from their watch. Sadly, most people seem to have ignored these results. The study protocol required people to go get a proper heart monitor (in this case an ECG patch they would wear for seven days to determine whether they actually had an arrhythmia). But only about one in five people who got an alert from their phone actually complied. In the end, only 450 people submitted their ECG patches for analysis, which makes the Apple Heart Study fairly small by most measures.

In most cases the ECG patches did not find any arrhythmias; they only diagnosed atrial fibrillation 35 per cent of the time. For people under 40, who made up the majority of test subjects, the yield was only 18 per cent.

Atrial fibrillation is a very common type of arrhythmia whose main medical complication is an increased risk of stroke. Patients with atrial fibrillation who are over the age of 65, or who have diabetes, high blood pressure, heart failure or a previous stroke would generally be given blood thinners as a preventative measure. However, most people would only give someone a diagnosis of atrial fibrillation if the arrhythmia lasted for more than 30 seconds. What to do with people who have brief episodes that last only a few seconds is less clear.

The problem with the Apple Watch is that it seems like it’s going to generate many false positives. Many people will go for further testing only to be told either that their tests were normal or they were found to have short bouts of atrial fibrillation that do not require any treatment.

There is a great deal of enthusiasm for medical technology and people naturally assume that newer better technology will inevitably lead to better health outcomes. But sometimes more sophisticated technology simply becomes better at diagnosing minor, ultimately inconsequential, issues that probably could have been ignored. The irony is that the Apple Watch is more common with young people where its detection rate is lower and where, even if atrial fibrillation were diagnosed, it is likely that blood thinners would not be prescribed to these young otherwise healthy patients with no risk factors.

As with any new technology, its effectiveness is based on how we use it. When used properly, testing for and treating atrial fibrillation is a very good way to prevent strokes in high-risk individuals. But screening everyone in the population is going to be an expensive low-yield activity.

The Apple Watch is an incredible piece of technology. It just doesn’t necessarily perform too well as a medical device, at least for now.


Back to top