An alert from Apple’s smartwatch hypertension notification feature can detect likely cases of high blood pressure, but a new study found the feature doesn’t replace standard screening with an arm cuff.

Jordana Cohen, MD, associate professor of medicine and epidemiology at the Perelman School of Medicine at University of Pennsylvania, Philadelphia, lead author of the research letter published in JAMA, said, “We wanted to understand and amplify what an alert, or the absence of an alert, actually means at the population level given how many people are likely to impacted by this.”

The Apple Watch has an estimated 200 million plus users worldwide and almost half of US adults have hypertension. The new feature converts changes in light absorption in the skin obtained via pulse oximetry over 30 days to calculate blood pressure values and alerts the wearer if a signal indicating hypertension is detected. Apple specifies that the hypertension notification is not intended to diagnose high blood pressure and is instead designed to prompt a visit to the doctor for evaluation.

The FDA approved the feature in 2025 based on a validation study comparing the notification feature to home blood pressure monitoring over 30 days. In that study, 41.2% of wearers with undiagnosed hypertension received an alert and 58.8% did not. Among wearers without hypertension, only 7.7% received an alert.

Exploring the Population Impact

In the JAMA study, Cohen’s team drew nationally representative blood pressure data from the National Health and Nutrition Examination Survey and estimated the prevalence of undiagnosed hypertension in the overall population and certain subgroups.

They applied Apple’s published performance metrics and found that the hypertension notification feature had a positive predictive value of 69.1% and a negative predictive value of 79%.

As an example of how an alert shifts the probability of receiving a hypertension diagnosis in various subgroups, for wearers younger than 30 years, the likelihood of being diagnosed with hypertension increases from a 14% pretest probability to 47% upon receiving an alert.

Conversely, the absence of an alert decreases the probability of being diagnosed with hypertension to 10%. In people older than 60 years, an alert boosts the chances of being diagnosed with hypertension from 45% to 81%, whereas absence of an alert lowers the odds of being diagnosed with high blood pressure to 34%.

Integrating Wearables With Blood Pressure Screening

The study’s results could be relevant to people in a range of healthcare roles.

“Patients need to understand how to interpret alerts,” said Cohen. “Clinicians need to understand what an alert, or no alert, does and does not mean. Manufacturers and regulators should consider how performance varies across populations. And public health stakeholders should think carefully about how wearable technologies fit into existing screening strategies.”

The study authors recommended rigorous validation of the hypertension alert feature, as well as strategies to improve accuracy of the device. “Rigorous validation means testing these devices across diverse populations and settings, not just in narrowly defined groups and not just in a laboratory environment at rest,” Cohen said.

Apple did not respond to questions about plans for further validation or improving accuracy.

Cohen also emphasized the importance of thoughtful integration of these tools into clinical care. “Wearable technologies can increase awareness, which is valuable, but they do not eliminate the need for routine, validated blood pressure measurement,” Cohen said. “Clear communication about what these types of alerts and other cuffless blood pressure device outputs mean, and what they do not mean, will be essential as these tools become more common.”

Further Validation Needed

“This is a very timely and highly relevant analysis,” said Simon Walzel, PhD, researcher at the Czech Technical University in Prague, Czech Republic. “I would advise clinicians and patients to treat this as a prompt, not a diagnostic tool. It is constantly available and can initiate follow-up, but confirmatory, cuff-based blood pressure measurement remains essential.”

Walzel, who was not involved with the study conducted by Cohen’s group, has found reasonable stability for tracking trends over time in prospective studies conducted by his team on smartwatch blood pressure measurements. “However, absolute accuracy for specific blood pressure values can degrade, especially as measurements drift from the calibration point. That reinforces the importance of confirmation before making clinical decisions.”

Walzel called for independent validation for wearable hypertension technologies with broader data access.

“Limited access to raw signals and proprietary algorithms remains a major barrier in wearable research,” he said. “We also need comparative studies across devices and thoughtful calibration of sensitivity and specificity depending on the intended public health goal.”

The study was funded by the National Heart, Lung, and Blood Institute with additional support from the University of Utah Study Design and Biostatistics Center. Adam Bress reported receiving personal fees from Alnylam.

Catherine Shaffer is a freelance science and medical writer with a background in molecular biology and pharmaceutical research. Her work has appeared extensively in scientific trade and mainstream publications and on public radio.