Wearable Sensor Assists Process of Diagnosing Heart Attacks

Presented at the American College of Cardiology’s Annual Scientific Session Together With the World Congress of Cardiology, new research describes a wearable sensor worn on the wrist that can determine troponin-I levels and obstructed arteries to predict heart attacks accurately.

According to the Centers for Disease Control and Prevention (CDC), heart disease is the top cause of death for men, women, and people of most ethnic groups in the US. In addition, about 805,000 people in the US have a heart attack yearly, and one in five heart attacks is silent.

According to the press release, a heart attack is caused by a blockage within arteries that supply blood to the heart, causing a lack of oxygen to reach the heart and body. This often results in patients visiting the emergency room, where clinicians attempt to treat it. But large crowds within emergency rooms can often prevent these professionals from acting in time.

A recently developed wearable, wrist-worn sensor aims to detect the presence of a type of protein known as troponin-I in the blood, as this protein enters the bloodstream when the heart muscle is damaged. Traditionally, if providers cannot determine a heart attack on an electrocardiogram, they check for troponin-I by conducting a blood test. But this can be time-consuming, enabling heart damage to worsen, the press release notes.

The sensor uses infrared light to detect the presence of troponin-I in the blood through the skin. It sends signals to a cloud-based system via Bluetooth. The system leverages a machine-learning algorithm to compare the signals to training data to predict the wearer’s troponin level.

To develop and test the wrist-worn sensor, researchers used data from 239 patients at five sites in India, all of whom were at risk of experiencing a heart attack.

Each patient involved in the trial wore the sensor and participated in blood drawings to determine troponin-I levels. They also engaged in electrocardiograms to gather information regarding the heart's electrical signals and an echocardiogram or a coronary angiogram to assess blood flow through the heart.

Of the five sites included in the study, researchers used data from three to train the machine-learning model and two to test its accuracy.

Following the trial, researchers confirmed that the tool displayed the ability to predict troponin-I levels with an accuracy level of 90 percent. This correlates with clinical evidence of a heart attack, meaning that the people with abnormal troponin levels indicated by the device were four times more likely to have a blocked artery.

“With this level of accuracy, if you use this device and it comes out positive, you’re fairly sure this patient can be admitted for fast tracking diagnostic tests, treatment and intervention,” said Partho P. Sengupta, MD, professor of cardiology at Rutgers Robert Wood Johnson Medical School in New Brunswick, New Jersey, chief of the cardiovascular service line at Robert Wood Johnson University Hospital and the study’s lead author, in a press release.

But researchers noted that further effort is required to solidify the reliability of the device. This includes determining whether the device's performance would be influenced by biological variability and whether including troponin value, rather than just the presence of the protein, or continuous measurements could improve its clinical capabilities.

Similarly, in December 2022, researchers from the University of Missouri created breathable material for a wearable heart monitor that uses dual signals to measure heart health indications simultaneously.

The material, which contains antibacterial and antiviral properties, supports the development of the wearable device, which will use an electrocardiogram to measure heart electrical signals and a seismocardiogram to measure heart vibrations. The goal is to enable the continuous monitoring of the human heart.