Smartwatches can predict hospitalization: UHN-study

TORONTO – A new study led by researchers at UHN’s Peter Munk Cardiac Centre and the Ted Rogers Centre for Heart Research shows that data from a consumer smartwatch can detect early signs of worsening heart failure — days to weeks before unplanned medical care is needed.

The findings, recently published on the cover of Nature Medicine, suggest that monitoring physical fitness capacity with wearable devices, such as Apple Watch, could help identify real-time changes in heart health without additional tests or extra effort from patients.

These changes can act as early warning signs, allowing clinicians to intervene faster with more responsive care.

Researchers also found that patients with a 10 percent or more drop-in daily cardiopulmonary fitness had a more than three-fold increased risk of unplanned hospitalization or urgent treatment.

“Thinking of ways to treat, manage and monitor patients where they’re at has been a crucial focus for us,” said Dr. Heather Ross (pictured), a cardiologist at the Peter Munk Cardiac Centre, clinician scientist, and co-senior author of the study.

“The findings of this study are a potential game-changer because they allow us to identify signals that would tell us a patient was in trouble before they ended up coming to the emergency room.”

Heart disease is the second-leading cause of death in Canada. Heart failure – a condition in which the heart does not pump enough blood to support the body – affects an estimated 64 million people worldwide.

According to the Canadian Institute for Health Information, heart failure consistently ranks among the top five causes of hospitalization nationwide, making it one of the costliest reasons for hospital admission in Canada.

There is a growing need for widely available clinical assessment tools that proactively monitor and treat patients with heart failure outside of the hospital.

Traditionally, clinicians rely on in-person appointments to gather patient data for treating heart failure. This means clinicians only get a snapshot of a patient’s health and may miss changing symptoms or early warning signs that occur between visits.

The Ted Rogers Understanding Exacerbations of Heart Failure study (TRUE-HF) observed data from 217 people with heart failure as they went about their daily lives over the course of three months. Apple supplied 200 iPhone and Apple Watch devices for the study, reviewed the manuscript and worked with all authors to build the study-specific mobile application.

Participants in the study wore an Apple Watch that provided researchers with data such as heart rate, physical activity and oxygen saturation levels. Until recently, it has been unclear whether these measurements can be used to estimate patient health and the risk of unplanned medical care in people living with heart failure.

“The really novel thing about our study is that it captures unobtrusive, free-living data from patients in the real-world,” said Chris McIntosh, a senior scientist at UHN and co-senior author of the study.

“We’re not only measuring how fast someone walks down a hallway in the hospital while their clinical team is standing behind them and encouraging them. We’re seeing what happens to their heart rate when they’re walking at the mall, on the street or at home.”

Using a UHN-developed and externally validated artificial intelligence model, the research team analyzed patterns in data from the wearable devices to estimate daily cardiopulmonary fitness – a key measure of how well the heart and lungs work together.

Researchers found that the smartwatch-based fitness data readings and estimates closely matched results from formal clinical exercise testing completed in hospital at the beginning and end of the study.

Data, such as how cardiopulmonary fitness changes over time, can influence a patient’s likelihood for unplanned medical care, including re-hospitalization, providing new insights for clinicians.

“Those day-to-day changes are something we’ve never been able to look at before,” said McIntosh.

The findings offer a window of opportunity to offer patient-centred care through proactive treatments, medication optimizations or other interventions.

The study marks a groundbreaking step forward in innovation at the Peter Munk Cardiac Centre where clinical, digital health, and AI teams collaborate to explore how digital tools and real-world uses of AI can improve heart care.

“We couldn’t have done this anywhere else. This work reflects UHN’s commitment to translating innovation into clinical tools through a highly interdisciplinary team,” said McIntosh.

Further research will explore how advancements in wearable monitoring could be integrated into patient care to improve outcomes.

“The future goal is to have an unobtrusive, free-living, near continuously monitoring equitable device that allows us to track a patient’s status and intervene when it changes,” said Dr. Ross.