Tech giant Apple made a splash last Wednesday, September 12, when it unveiled its new Series 4 Apple Watch with advanced heart tracking capabilities, including an electrocardiogram (ECG) function, as well as fall detection capabilities.
The ECG sensor, and the software that supports it, received clearance from the U.S. Food and Drug Administration (FDA) on September 11. Apple’s development of an ECG app within the Apple Watch is notable as it signifies Apple’s intention of transitioning its smartwatch from just a consumer device to a medical device. What’s more, many healthcare industry leaders have noted that Apple’s efforts to get FDA clearance points to the scope of its investment in the digital health space.
During Apple’s annual fall product event in Cupertino, California last week, in announcing the new Series 4 Apple Watch, Jeff Williams, Apple’s chief operating officer, said it is the “first-ever ECG app offered directly to consumers.”
However, it is not the first over-the-counter ECG device to get FDA clearance. Mountain View, California-based AliveCor, an artificial intelligence company that develops personal electrocardiogram technology, received FDA clearance in November 2017 for its KardiaBand, a medical-grade device accessory for Apple Watch. According to the company, KardiaBand can record an ECG in 30 seconds and can detect abnormal heart rhythms. AliveCor also released machine-learning software called SmartRhythm, which continuously analyzes data from the watch’s built-in heart-rate sensor and accelerometer to spot unexpected patterns.
While KardiaBand is an add-on accessory to the Apple Watch, the new ECG app announced by Apple is built into a consumer product.
According to Apple’s press release, the Apple Watch Series 4 enables customers to take an ECG reading right from the wrist using the new ECG app, which takes advantage of the electrodes built into the digital crown and new electrical heart rate sensor in the back crystal. With the app, users touch the digital crown and after 30 seconds, receive a heart rhythm classification.
The app can classify if the heart is beating in a normal pattern or whether there are signs of atrial fibrillation (AFib), a heart condition that could lead to major health complications, according to Apple. According to a STAT article, based on a review of a study of the new device that Apple submitted to the FDA, the heart monitoring app can accurately detect that a person has an irregular heart rhythm 99 percent of the time.
The heart sensor features and ECG app are a gamechanger for how consumers can track their health, says Daniel Kivatinos, chief operating officer and co-founder of Sunnyvale, Calif.-based DrChrono, an electronic health record (EHR) vendor. The company launched the first EHR platform for the iPad, iPhone and Apple Watch and is part of Apple’s Mobility Partner Program.
Many digital health and clinical leaders see Apple’s development of an ECG app built into a consumer device as a significant step on the journey towards the Internet of Things for healthcare, while also voicing a healthy dose of skepticism.
“We are inevitably on a course where there will be widespread deployment of a diverse array of devices that connect, communicate and collaborate for healthcare,” says Dave Levin, M.D., chief medical officer at Sansoro Health and former chief medical information officer (CMIO) for Cleveland Clinic. Levin also currently serves in a variety of leadership and advisory roles for healthcare IT companies, health systems and investors. “It’s an important step forward and full of promise in the long run, but likely to have many challenges and limitations in the near term,” he adds.
Sharing his thoughts on Apple’s ECG app, Sanket Dhruva, M.D., attending cardiologist at the San Francisco VA Health Care System and assistant professor of medicine, UCSF School of Medicine, says, “The detection of patients who have atrial fibrillation through the ECG feature of the Apple Watch is an important technological feat. We can expect an explosion of continuous data and more diagnoses of atrial fibrillation that would previously have been undetected.”
Joon Sup Lee, M.D., an interventional cardiologist and co-director of the UPMC Heart and Vascular Institute at the Pittsburgh-based UPMC Health System, notes that similar heart monitoring devices have been available, but have not been as integrated. “Obviously, this really changes the scenario given Apple’s size, market share and their overall power. It’s really the beginning, in the sense in that I think there will be many more monitoring abilities and services that will continuously come out to the technology market, but this represents a big step forward,” notes Lee, who also is the chief of the cardiology division of the University of Pittsburgh School of Medicine.
Lee adds, “Like most technological advances, it raises some very fascinating possibilities for the medical field, but a host of still unanswered questions.” From a healthcare provider perspective, the ECG app will generate a significant amount of data, Lee notes, “and exactly how good the software will be between distinguishing a worrisome rhythm, versus a false alarm, I think that remains to be answered. Obviously, Apple has a good idea of how accurate it is, but most of us haven’t seen it.” He adds, “[The ECG app] has the ability to both generate increased concern, but also it can catch potentially worrisome episodes that might have otherwise not been caught.”
Potential Limitations and Integration Challenges
One particular concern among cardiologists is whether use of the ECG app will lead to false positives or false negatives, and a potential increase in unnecessary healthcare utilization. On September 12, when Apple announced the ECG app, Ethan Weiss, M.D., a cardiologist with the University of California, San Francisco, tweeted in response: "I can’t figure out whether today is the best day in the history of cardiology or the worst."
Lee sees the potential for use of the ECG app to increase utilization of medical resources, in the short term. “It’s something that we should be aware of, that it may actually lead to increased utilization of medical resources from a societal standpoint and from an insurer and government payers’ standpoint, because it would detect things both real, and inevitably, there will be some false alarms.”
Dhurva notes that while the ECG app is a technological innovation, “the clinical implications are less certain.” “Currently, most people with atrial fibrillation are diagnosed through symptoms or heart rhythm monitors that are interpreted by cardiologists. Most of these people have risk factors for stroke and, therefore, are prescribed blood-thinning medications (aspirin or anticoagulants) to reduce their stroke risk. But with the Apple Watch, many people will diagnose themselves with brief periods of atrial fibrillation that they would not have otherwise noticed. We do not know if people with brief atrial fibrillation will benefit from these blood-thinning medications. It’s likely that the early detection will reduce stroke risk for some patients – which will be great. However, others may be placed on blood-thinners and suffer from bleeding risk to which they would not otherwise have been exposed.”
He also adds, “And I would not discount the stress and anxiety that people may feel from having an abnormal heart rhythm – even if it is not clinically significant—and being on blood thinners, which could lead them to curtail heart-healthy activities like vigorous exercise.”
Levin notes that, at least on paper, the detection capabilities of Apple’s ECG app are limited. “It is FDA cleared to identify normal heart rhythms or signs of AFib. Essentially the watch can tell the patient either ‘you are fine’ or ‘you should get this checked out for possible AFib.’ This may be useful but is also very limited. AFib can be benign or lethal. We don’t know the sensitivity and specificity of this device, but presumably they are not that great so there will be false negatives and false positives. The device does not address other important, common and lethal cardiac arrhythmias like ventricular fibrillation (VFib),” he says.
In addition, the ECG app platform is not currently linked to any EHR systems, and Levin notes that the lack of interoperability could be a major barrier to effective use.
According to Apple, the Series 4 Apple Watch offers a feature that enables consumers to export their heart monitoring data, in a PDF format, to their physicians. Kivatinos says this feature significantly changes the dialogue between providers and patients and enable doctors to gain valuable insights about their patients.
Levin has a more skeptical view: “This will be highly limiting. How will that PDF flow into the system of care in a timely and reliable manner? EHR’s are already overstuffed with PDFs which can be hard to find and are unstructured. Will this PDF be one more ‘needle’ in that ‘haystack’?”
As with other patient-generated data, Lee notes that healthcare provider organizations will need to develop new protocols to integrate the heart monitoring data into their EHRs. “If everybody with one of these suddenly starts sending PDFs to emergency rooms, that could cause a resource utilization issue.”
Beyond technical integrations, healthcare providers will need to have processes in place to make the heart monitoring data actionable, Levin notes. “Designing and deploying these kinds of devices is the easy part. Building the systems of care that can act upon the information they will supply will be much harder and essential if they are to have a significant impact on health.”
Taking in all of these factors, Levin says, “The combination of limited functionality, little interoperability, undefined sensitivity and specificity and lack of well-defined care process points to a rocky start and limited benefit.”
However, with the rapid pace of digital health innovation and growing use of consumer and clinical health devices, healthcare provider organizations are increasingly seeing the need to integrate patient-generated health data into clinical processes. According to Lee, future efforts will focus on "smarter" software and advanced solutions to not only collect all this data from consumers but also more efficiently cull through the data, pull out the most important and most useful medical data, and then incorporate it into the EHR.
