Apple Watch Fails To Notify Patient Of 3 Hour Episode Of Rapid Atrial Fibrillation

Apple claims that its Apple Watch can detect atrial fibrillation (AF) and appropriately notify the wearer when it suspects AF.
This claim comes with many caveats on their website:
Apparently it needs to record 5 instances of irregular heart beat characteristic of atrial fibrillation over at least 65 minutes before making the notification.
This feature utilizes the watch’s optical heart sensors, is available  in Apple Watch Series 1 or later and has nothing to do with the Apple Watch 4 ECG recording capability which I described in detail in my prior post.

Failure To Detect AF

A patient of mine with known persistent AF informed me yesterday that she had gone into AF and remained in it for nearly 3 hours with heart rates over 100 beats per minute and had received no notification. She confirmed the atrial fibrillation with both AW4 recordings and AliveCor Kardia recordings while she was in it.
The watch faithfully recorded sustained heart rates up to 140 BPM but never alerted her of this even though the rate was consistently over her high heart rate trigger of 100 BPM.
The patient had set up the watch appropriately to receive notifications of an irregular rhythm.

Reviewing her tracings from both the AW4 and the Kardia this was easily diagnosed AF with a rapid ventricular response.

What does Apple tell us about the accuracy of the Apple Watch AF notification algorithm? All we know is the unpublished , non peer-reviewed data they themselves collected and presented to the FDA.
From this link on their website Apple says:

In a study of 226 participants aged 22 years or older who had received an AFib notification while wearing Apple Watch and subsequently wore an electrocardiogram (ECG) patch for approximately 1 week, 41.6% (94/226) had AFib detected by ECG patch. During concurrent wear of Apple Watch and an ECG patch, 57/226 participants received an AFib notification. Of those, 78.9% (45/57) showed concordant AFib on the ECG patch and 98.2 % (56/57) showed AFib and other clinically relevant arrhythmias. These results demonstrate that, while in the majority of cases the notification will accurately represent the presence of AFib, in some instances, a notification may indicate the presence of an arrhythmia other than AFib. No serious device adverse effects were observed

This tells us that about 80% of notifications are likely to be Afib whereas 20% will not be Afib. It is unclear what the “other clinically relevant arrhythmias”  might be. If I had to guess I would suspect PVCS or PACS which are usually benign.
If 20% of the estimated 10 million Apple Watch wearers are getting false positive notifications of afib that means 2 million calls to doctor or visits to ERs that are not justified.  This could be a huge waste of resources.
Thus the specificity of the AF notification is 80%. The other important parameter is the sensivitiy. Of the cases of AF that last >65 minutes how many are detected by the app?
Apple doesn’t seem to have any data on that but this obvious case of rapid AF lasting for 3 hours does not give me much confidence in their AF detection algorithms.
They do have a lot of CYA statements indicating you should not rely on this for detection of AF:

It is not intended to provide a notification on every episode of irregular rhythm suggestive of AFib and the absence of a notification is not intended to indicate no disease process is present; rather the feature is intended to opportunistically surface a notification of possible AFib when sufficient data are available for analysis. These data are only captured when the user is still. Along with the user’s risk factors, the feature can be used to supplement the decision for AFib screening. The feature is not intended to replace traditional methods of diagnosis or treatment.

My patient took her iPhone and Apple Watch into her local Apple store to find out why her AF was not detected. She was told by an Apple employee that the Watch does not detect AF but will only notify her if her heart rate is extremely low or high. I had asked her to record what they told her about the problem.

As I’ve written previously (see here) the Apple Watch comes with excessive hype and minimal proof of its accuracy. I’m sure we are going to hear lots of stories about AF being detected by the Watch but we need some published, peer-reviewed data and we need to be very circumspect before embracing it as a reliable AF monitor.
Skeptically Yours,


12 thoughts on “Apple Watch Fails To Notify Patient Of 3 Hour Episode Of Rapid Atrial Fibrillation”

  1. I Have both a Kardia pad and an AW4 both give almost identical ECG readings. I can always feel if I am in AFIB or throwing PVCs. But I have never gotten an irregular HB notification any kind from the AW4 and obviously couldn’t get one from the KARDIA pad.

  2. I’ve been using an AW3 and Kardia band with the Kardia app Smart Rhythm for about a year. While the watch or Smart Rhythm or both have made many errors reporting an abnormal heart rhythm, when app reports from the Kardia Band ECG reports ‘possible afib,’ I’ve actually been in afib, and when it reports ‘Normal,’ there seems to be no evidence suggesting otherwise. I’ve gotten false rhythm warnings when making lots of successive strokes with colored pencils. My watch had fits when I was on a bus tour, and the bus was vibrating due to road conditions. (I think my wrist was resting on or very near the bus window.) Long ago I learned to end Smart Rhythm before removing the watch for charging. Alternating current totally freaks out the app.
    It is prudent to retest several times before running off to ER unless symptoms suggest otherwise. AW3, Smart Rhythm, and the Kardia Band have saved me 2 trips to ER (With the pdfs of the ECGs, my cardiologist was able to handle things over the phone.)

  3. I was considering buying an Apple Watch to have this feature. I have paroxysmal Afib and I wanted a record of it to show my doctor. Not buying it. I know instantly when I am in Afib and use my blood pressure monitor to record it.

    • Keep in mind the AF detection/notification feature is different from the ECG feature.
      If you can feel when you are in AF or if your BP monitor alerts you, with the AW4 you can make an ECG recording of it and send that to your doctor as proof. On the other hand for 99$ you can get an AliveCor which does the same thing.

  4. Did you do a repeat AW4 tracing on the same patient? I’ve gotten some bizarre one-offs on my Kardia Band (maybe it was too loose or I was moving) but the Kardia always corrected itself the next time. Keep the anecdotal stories coming, because unlike yourself, most of the reviewers don’t know anything about this function or what to look for.

    • There’s only so much time I can spend during a busy office day putzing around putting watches on my patient’s wrists so the watch got one shot but but displayed the same pseudo VT despite tweaks of the finger and wrist positions throughout the tracing.

  5. In all fairness, Kardia’s similar “SmartRhythm” function does not do a very good job of notifying you of afib either. I’ve had several false positives and many false negatives. Finally I just turned it off because all it added to the equation was running down the battery on my Apple Watch! The Kardia analysis function is also not stellar often interpreting NSR as Afib when presented with too many ectopic beats. That said, I value my Kardia Band for the accuracy of the single lead tracings, most of which I have learned to interpret and those I can’t I just email to my EP. I haven’t tried the Watch 4 yet, but I would not pass on it because of the alert function or even the provided analysis. I would pass on it, however, if the tracings themselves were not as accurate as the Kardia. From your first review, it sounds like the Watch 4’s tracings might not be as good, but I welcome upcoming reports when you have a larger sample.

    • I haven’t had any positive or negative experiences with SmartRhythm so it is good to get your feedback on its lack of efficacy.
      When I compare the quality of the AW4 ECG tracing and the Kardia they appear very similar except in the one bizarre AW4 tracing I described.

  6. Important to note that when setting up the irregular rhythm notifications Apple specifically states that users who have previously been diagnosed with Afib should not rely on this for monitoring. I believe that a user has to lie and say that they do not have this dx. for it to work. Apparently Apple is being cautious with their lack of experience with the algorithm that that they have developed and, in spite of some public pronouncements of benefit, realize that more data is needed. I bet, knowing how much Apple wants to get into the huge home health monitoring business, this functionality is improved over time with OS updates. AliveCor has a head start with fine-tuning their software, but I bet Apple has the $ and motivation to compete. Please keep us updated on your experience


Please leave your comments. The skeptical cardiologist loves feedback. He reads all and replies to all that warrant a reply.