Fitbit, Apple Watch Screening for Faulty Heart Rhythms Needs More Study

Company claims are leaping ahead of medical science in promoting the use of smartwatches to screen for heart rhythm disorders.

That's the conclusion of a UC San Francisco cardiologist who specializes in arrhythmias and was among the first to explore the potential of smartwatches to alert wearers about possible atrial fibrillation (AF), a serious condition that can sometimes lead to deadly strokes.

More scientific evaluation is needed to develop and validate consensus recommendations to ensure that benefits will outweigh risks for consumers who use smartwatches in screening themselves for AF, says Gregory Marcus, MD, MAS, a UCSF professor of medicine with the Division of Cardiology, in an opinion piece in Circulation.

The article in the influential medical journal is a response to a recent study in the same publication on the utility of Fitbit watches for detecting AF.

"Smartwatch detection of AF holds tremendous promise, but substantial work is needed to integrate this consumer-received information into optimized care of our individual patients and the well-being of the public," Marcus writes.

Although AF contributes to about 158,000 U.S. stroke deaths yearly, and often diminishes quality of life, the disorder is still not common enough to warrant population-wide screening by trained cardiologists who examine ECG data obtained using gold-standard, 12-lead electrocardiographs.

But several years ago, Marcus and colleagues first investigated the Apple watch as a potential tool to detect AF. Apple watches and Fitbits both use optical "photoplethysmography" (PPG) sensors to track pulse. Using ECG measurement to confirm the presence or absence of AF, Marcus and others found that smartwatch detection of irregular timing of heart beats could often point to cases of AF.

The most recent smartwatch models boast more refined algorithms to mathematically analyze PPG data and determine whether to alert the wearer about heartbeat irregularities. Some smartwatches in addition now incorporate single-lead electrocardiograph sensors that the user can activate.

In the Fitbit Heart Study, researchers reported that a little over one percent of 455,699 participants experienced one or more irregular heart-rhythm detections. About one-third of those who experienced irregular heartbeats and then wore a single-lead ECG monitor experienced an abnormal ECG reading suggestive of AF.

But more studies are needed to better assess risks and benefits, Marcus says.

"We might find that it makes sense for those at low-risk to opt out of alerts based on PPG data analysis," he says. Very little is known about AF health outcomes associated with smartwatch screening, and there are no rigorous studies to evaluate accuracy of AF detection using irregular heartbeat alerts that trigger immediate ECG recording, Marcus notes.

The prevalence of AF increases with age. Prevalence of AF is unlikely to be much greater than one percent in U.S. adults, Marcus says, but about five percent of those age 60 and above are afflicted. Risk for AF is highest for individuals with pre-existing heart conditions. Besides age, additional risk factors include other chronic health conditions, among them potentially modifiable behaviors such as obesity and alcohol consumption.

Marcus notes that even a highly specific screening test can result in most positive results being falsely positive when disease incidence is low. Consider a hypothetical screening test that has a high accuracy, such as 95 percent "specificity" and "sensitivity." This means five percent of true negatives test falsely positive. If true disease incidence in the screened population is just one percent, then about five people would be wrongly diagnosed for every person who was accurately diagnosed.

False positive results generate their own risks, including unnecessary worry and anxiety, unwarranted utilization of medical resources, and sometimes treatment that may do more harm than good, says Marcus.

He suggests in his opinion piece that patients with already-confirmed AF might be among those to benefit most from smartwatch use: "Real-time AF detections can empower patients to identify triggers of their AF, to assess the effectiveness of various therapies, and to determine if vague or general symptoms are due to their arrhythmia or something else."

Gregory M Marcus.
Smartwatch-Detected Atrial Fibrillation: The "Value" in the Positive Predictive Value.
Circulation, 2022. doi: 10.1161/CIRCULATIONAHA.122.062292

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

Patients say "Yes..ish" to the…

As artificial intelligence (AI) continues to be integrated in healthcare, a new multinational study involving Aarhus University sheds light on how dental patients really feel about its growing role in...

'AI Scientist' Suggests Combin…

An 'AI scientist', working in collaboration with human scientists, has found that combinations of cheap and safe drugs - used to treat conditions such as high cholesterol and alcohol dependence...

Brains vs. Bytes: Study Compares Diagnos…

A University of Maine study compared how well artificial intelligence (AI) models and human clinicians handled complex or sensitive medical cases. The study published in the Journal of Health Organization...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...