Stanford Medicine Publishes Results of Apple Heart Study

MacRumors

macrumors bot
Original poster
Apr 12, 2001
46,354
8,757



Stanford Medicine today published results from the Apple Heart Study that kicked off in 2017, marking the third time data from the study has been shared (via Reuters and CNBC).

The aim of the study, conducted by Stanford and Apple, was to determine whether the Apple Watch is able to detect atrial fibrillation, which can be an indicator of serious heart health problems. Researchers wanted to determine how well the Apple Watch worked and whether it was safe to use.


A total of 419,297 people in the United States participated in the study, and 0.52 percent of participants (2,161 people) received an irregular heart rhythm notification over 117 days of monitoring. People who received a notification were sent ECG patches to further monitor for heart problems, but quite a few of those went unreturned.

Of the 450 people who returned the patches with data that could be analyzed, atrial fibrillation was present in 34 percent overall and 35 percent of participants age 65 or older. Of those who had an irregular reading and returned a patch, 84 percent of subsequent notifications were determined to be atrial fibrillation.
Among participants who were notified of an irregular pulse, the positive predictive value was 0.84 (95% CI, 0.76 to 0.92) for observing atrial fibrillation on the ECG simultaneously with a subsequent irregular pulse notification and 0.71 (97.5% CI, 0.69 to 0.74) for observing atrial fibrillation on the ECG simultaneously with a subsequent irregular tachogram. Of 1376 notified participants who returned a 90-day survey, 57% contacted health care providers outside the study. There were no reports of serious app-related adverse events.
According to researchers, the low number of warnings in the study indicates that the device does not cause an excess of false notifications in healthy people who wear the watch.

In some cases, atrial fibrillation detected by the Apple Watch was in the early stages of development, and it didn't happen frequently enough for the patch testing to detect it, something that was more prevalent in younger participants.

The study did ultimately determine that the Apple Watch can detect atrial fibrillation. Stanford cardiologist and co-author of the study Dr. Mintu Turakhia said that the trial was overall a success, especially when it came to determining how many people are going to get heart-related notifications from Apple Watch and what those types of notifications mean for patients, doctors, insurers, and more.

Dr. Daniel Cantillon, a Cleveland cardiologist who was not involved, told Reuters that the technology was promising, but more than half of participants were under 40, a group at low risk for atrial fibrillation, leading to concerns about scaring healthy people.

Separately, a New York cardiologist told CNBC that there's a risk of the Apple Watch finding young people who have early signs of atrial fibrillation that the medical community doesn't know how to treat. "We just don't understand atrial fibrillation well in the 35-year-old, otherwise healthy person," he said.

Wessler treats patients who have visited him based on data gathered from the Apple Watch, and he expects those kind of visits to pick up in the future. Should Apple's research continue, Wessler believes it's important to find the right population that's most at risk to use these tools rather than delivering them to a mainstream audience.

The study was overall beneficial, demonstrating the potential for large-scale studies that use a variety of technologies to monitor patients remotely without requiring on-site visits. Since this study kicked off in 2017, it did not use the new Apple Watch models that are able to take ECG readings, instead relying on the standard heart rate sensor.

The full Apple Heart Study published by Stanford Medicine can be read in The New England Journal of Medicine.

Article Link: Stanford Medicine Publishes Results of Apple Heart Study
 

rp2011

macrumors 65816
Oct 12, 2010
1,288
935
The point should be about collecting information even if they don’t know how to treat someone. That alone constitutes as a success. That’s always the first step. You can’t begin to understand anything without first collecting data.
 

newellj

macrumors 604
Oct 15, 2014
7,583
2,528
East of Eden
The point should be about collecting information even if they don’t know how to treat someone. That alone constitutes as a success. That’s always the first step. You can’t begin to understand anything without first collecting data.
I'm not an MD, but I agree strongly. Baseline and long-term trend information can be very valuable. Figuring out how to add blood pressure information could be another very significant data collection over a long term.
 

now i see it

macrumors 601
Jan 2, 2002
4,235
8,411
Wessler treats patients who have visited him based on data gathered from the Apple Watch, and he expects those kind of visits to pick up in the future. Should Apple's research continue, Wessler believes it's important to find the right population that's most at risk to use these tools rather than delivering them to a mainstream audience
Exactly as I had predicted and everyone involved with it at Apple already anticipated- but here it is - on the wrists of the masses
 
  • Like
Reactions: The Barron

Dezlboy

macrumors regular
Sep 10, 2008
229
50
QUESTION: AppleWatch Four will take ECG reading if you manually do so via iPhone. Correct?

But, as article implies, will the AppleWatch inform wearer of irregular heartbeat when wearer doesn't start any "special" application? I believe the answer is yes?
 
  • Like
Reactions: The Barron

Khedron

macrumors 68020
Sep 27, 2013
2,126
4,135
I'm not an MD, but I agree strongly. Baseline and long-term trend information can be very valuable. Figuring out how to add blood pressure information could be another very significant data collection over a long term.
Wasn't that proposed as part as some self-tightening band patent?
 

The Barron

macrumors 6502
Mar 5, 2009
433
261
Apple was very involved with a wireless cardiac company called BioTelemetry (BEAT on the stock exchange) for this study. Has anybody heard if that alliance is still intact? I'd love to see Apple buy them out because they are now working on wireless noninvasive glucose monitoring and that will be huge when it is released to the public.
 

Bandaman

macrumors regular
Aug 28, 2019
125
162
Wow! I am impressed. Damn good job, Apple! The watch is only going to get better. I can't wait to see what it does in 5 years or so.
If they manage to successfully implement the painless blood glucose monitoring they’ve been working on, it will literally be revolutionary.


The report is confusing. As I read it, only 34% of people who got irregular heart rhythm warning from AW actually had atrial fibrillation. That's 66% false positive rate which is unacceptable.
It’s only going to be improved from there.
 
  • Like
Reactions: nfl46

Brandhouse

macrumors 6502
Aug 6, 2014
440
709
Having recently found I have an irregular heartbeat of 1250 in 100,000 it'd be great if this passed medical scrutiny in Australia and I'd be waiting in line for version 6 of the watch.
 

artfossil

macrumors 65816
Oct 5, 2015
1,150
1,177
Florida
Just one of the reasons I love my Watch. My most valued piece of tech in 35 years with Apple. I am grateful to be alive!
 

realtuner

macrumors 68000
Mar 8, 2019
1,564
4,276
Canada
The report is confusing. As I read it, only 34% of people who got irregular heart rhythm warning from AW actually had atrial fibrillation. That's 66% false positive rate which is unacceptable.
Poor attempt to spin the numbers.

Think of it this way: 20,000 people wear the Apple Watch. Only 100 received an alert. Of those 34 had Afib and 66 did not.

Having 100 people visit their doctor for additional tests out of 20,000 is hardly an “unacceptable” rate. And potentially saving the lives of 34 people is easily worth testing 66 other people who end up being OK. What would be unacceptable is wasting time/money testing 20,000 people to find the 34 that had Afib.
 
  • Like
Reactions: jamdex and I7guy

Solomani

macrumors 68040
Sep 25, 2012
3,748
6,298
Alberto, Canado
According to researchers, the low number of warnings in the study indicates that the device does not cause an excess of false notifications in healthy people who wear the watch.
Seems like Apple is getting this thing right.

Keep it up Apple, going in the right direction!
 
  • Like
Reactions: realtuner

Neberheim

macrumors newbie
Jan 20, 2019
3
3
The report is confusing. As I read it, only 34% of people who got irregular heart rhythm warning from AW actually had atrial fibrillation. That's 66% false positive rate which is unacceptable.
Atrial fibrillation (A-fib) is only one example of an irregular rhythm (technically it's "irregularly irregular" but anyway), and having a brief arrhythmia is normal in the general population. The follow-up ECG patches were received by participants an average of thirteen days after the original watch notification alerted the research team.

So two weeks after the original watch notification, the ECG patches recorded a diagnosable rhythm in 34% of the 450 patients who returned the patches. While those 34% of the 450 had the ECG patches applied, irregular heart rhythm notifications received on the watch correlated with A-fib on the "real-time" ECG 84% of the time.

If the irregular notification "accuracy" is 84%, we could speculate that the 50% of people who did not show A-fib on the follow-up ECG patches, did in fact have transient A-fib that resolved and did not present again. That would not be unusual, however there's no way to know definitively since two weeks passed between notification and ECG collection.

Think of it this way: 20,000 people wear the Apple Watch. Only 100 received an alert. Of those 34 had Afib and 66 did not.
Sorry that you posted before I finished typing, but using your simplified example: 100 received an alert, 34 had confirmed A-fib, and of those 34, 29 had A-fib alerts on their watch that matched A-fib on the ECG.
The other 66 have an unknown status, and we could guess that 50 of them had A-fib that would have shown up on the ECG, had they been wearing one at the time of the alert.

Clear as mud?? 😆
 
Last edited:

jimbobb24

macrumors 65816
Jun 6, 2005
1,089
1,388
The report is confusing. As I read it, only 34% of people who got irregular heart rhythm warning from AW actually had atrial fibrillation. That's 66% false positive rate which is unacceptable.
Why is it unacceptable? Based on what comparison? It’s a screening evaluation where the downsides are minimal and the upside is huge - tests typically designed to cast a wider net than other evaluations. They also say some may have had atrial fibrillation but it was so rare the watch caught it but the other testing didn’t.