Bracelet Troponin Sensor Predicts Heart Attack With 90% Accuracy in Five Minutes
Posted on 09 Mar 2023
When the arteries supplying blood to the heart become blocked, it restricts the supply of oxygen to the heart and the body, leading to a heart attack. Those who experience symptoms such as shortness of breath or chest pain generally visit the nearest hospital emergency room at the earliest. Troponin-I, a protein that enters the bloodstream when the heart muscle is damaged, is usually assessed using a blood draw as part of routine processes for diagnosing a heart attack when a patient is experiencing chest pain and shows no conclusive signs of a heart attack on their electrocardiogram. However, the process of drawing blood and sending it to the lab for analysis is time-consuming, causing heart damage to escalate while healthcare providers wait for the results. Now, an experimental wrist-worn device has been found to predict troponin-I and blocked arteries with 90% accuracy in five minutes, potentially preventing more heart muscle damage.
The study by researchers at Rutgers University (New Brunswick, NJ, USA) was the first multicenter trial to assess a wearable troponin sensor developed by RCE (Carlsbad. CA, USA) in a real-world clinical context. The wrist-worn sensor operates using infrared light to detect troponin-I in the bloodstream via the skin. This device then wirelessly transmits information using Bluetooth to a cloud-based system where a machine learning algorithm relates the information to training data to predict the wearer's troponin level. Researchers are confident that the new wearable sensor will aid in augmenting the diagnostic process by providing an early assessment of whether the patient is experiencing a heart attack, even before lab results become available.
For the trial, the researchers enrolled 239 patients suspected of experiencing a heart attack at five sites across India. Each patient wore the wrist-based sensor and underwent a blood draw to examine troponin-I levels, an electrocardiogram to note electrical signals from the heart, and either coronary angiogram or echocardiogram to capture blood flow in the heart. The researchers employed data from the first three sites to train the machine learning algorithm before evaluating the model's accuracy with the final two sites. Outcomes showed that the device predicts troponin-I levels with up to 90% precision. Moreover, the results correlated well with clinical evidence of a heart attack. Individuals with abnormal troponin-I levels, as measured by the device, were four times more likely to have an obstructed artery as compared to individuals with negative troponin results.
The researchers have suggested that further studies are needed to refine and validate the new system. This includes evaluating whether biological differences, such as skin tone, wrist size, or skin health, can impact the device's performance. Moreover, they plan to investigate whether continuous measurements or incorporating the detected troponin value - instead of just the presence or absence of a threshold value - could improve the device's effectiveness in clinical settings. The participating patients during the experiment were hospitalized, but they were not being treated in an emergency room. The researchers have emphasized the significance of testing the wearable device in emergency room settings. They also note that wearable sensor technology has the potential to help aid diagnosis and triage for several cardiovascular diseases and other health-related problems.
"This is an exciting opportunity because it increases our capability for early diagnosis of heart attacks in both community settings and in acute care environments," 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. "There's still a lot of work to be done, but this approach could potentially address access issues and prioritization issues, for example by shortening the time to triage or being used by emergency responders to plan the patient's journey before they even arrive at the hospital."
Related Links:
RCE
Rutgers University
