Devices & Diagnostics, Artificial Intelligence

Preliminary results are in from the massive Apple Heart Study

According to findings presented at the American College of Cardiology's annual meeting, 0.5 percent of the more than 400,000 study participants received a notification about irregular pulse and 84 percent of participants who received irregular pulse notifications were found to be in atrial fibrillation at the time of the notification.

Apple’s foray into healthcare received a boost with the release of preliminary results of a study done in collaboration with Stanford University researchers that aimed to test whether the Apple Watch could spot potential cardiac issues before they become more serious.

The virtual study – which was launched in 2017 and funded by Apple – enrolled more than 400,000 participants and found that the wearable could be used to detect irregular heart rhythms that could be a sign of atrial fibrillation.

According to findings presented at the American College of Cardiology’s annual meeting, 0.5 percent of participants received a notification about irregular pulse and 84 percent of participants who received irregular pulse notifications were found to be in atrial fibrillation at the time of the notification. The full study has not been published.

The research builds on an earlier study published last year which found that the watch and an association algorithm to detect AFib was only 68 percent accurate.

One important note was that the study was not conducted with the newest Apple Watch 4 model which received FDA clearance for its ability to perform EKGs.

Instead, participants used a mobile app that intermittently checked the heart-rate pulse sensor for an irregular pulse. If one was found, the participant received a notification and were asked to schedule a telemedicine visit through American Well. The individuals were then sent ambulatory EKG patches from BioTelemetry for additional heart rate tracking that lasted around a week.

More than half of participants – 57 percent – sought medical attention through American Well after receiving an irregular pulse notification.

The study found that 34 percent of participants who got irregular pulse notifications and received the EKG patch were found to have atrial fibrillation while wearing the patch.

Stanford cardiologist and one of the study’s principal investigators Mintu Turakhia said this result was not surprising due to the tendency of AFib to come and go, especially in the early stages of the condition.

“So while only 34 percent of people who were still having AFib on the ambulatory ECG, that doesn’t mean that 66 percent didn’t have AFib. It just means that AFib may not have been there at the time,” Turakhia said in statement. “These parameters help us understand how we, as clinicians, should think about these notifications.”

Atrial fibrillation is a leading risk factor for stroke and is often asymptomatic making it difficult to detect. According to the American Stroke Association a majority of strokes in people with AFib could be prevented through the use of anti-coagulation treatment. 

“The performance and accuracy we observed in this study provides important information as we seek to understand the potential impact of wearable technology on the health system,” Stanford cardiologist and one of the study’s principal investigators Marco Perez said in a statement. “Further research will help people make more informed health decisions.”

Brian Chapman, a principal with consulting firm ZS Associates, said he was encouraged by the study’s approach in trying to explain potential inaccuracies in context with how the device would work in the larger healthcare system.

One data point he underscored was the large proportion (more than 2 in 5) of study participants that declined to follow up after receiving a notification on their watch.

“This tells me that one of the barriers such consumer-oriented devices will need to overcome is in the mind of the consumer, their watch isn’t yet a medical device,” Chapman said.

There has also been skepticism from observers who point out that there has been little to no research on the actual health outcomes from using wearables like the Apple Watch. Additionally while accuracy has been improved, it still lags behind traditional monitoring techniques.

In a commentary published in Stat, Larry Husten with CardioBrief highlighted the study’s lack of a control group and the potential of harm from false positives and false negatives.

“There’s a lot of enthusiasm out there for new, high-tech devices like the Apple Watch, but it is extremely difficult to find thoughtful perspectives on the complex medical issues they raise,” he writes.

“We are in the middle of an overwhelming rush to embrace new technology and make health data available to everyone. This movement is fueled by Apple and other technology companies that are starting to spread some of their enormous wealth in the medical community, laying the groundwork for their expansion into this field.”

Case in point, University of Michigan recently launched a study looking to merge data collected through the Apple Watch with EHR information to provide clinical insight about patients.

Photo: Creativeye99, Getty Images

Shares0
Shares0