Wrist-worn sensor shows early promise for assessing likelihood of suspected heart attack
NEW ORLEANS — In a new study, use of a wrist-worn sensor was clinically feasible for rapid, bloodless prediction of elevated troponin I in patients with suspected MI, researchers reported at the American College of Cardiology Scientific Session.
“Assessing high-sensitivity cardiac troponin for chest pain is standard practice in crowded emergency rooms. Although point-of-care tests are available, there are no FDA-approved handheld wearable devices. We recently reported the development of an infrared device for transdermal assessment of troponin,” Partho P. Sengupta, MD, FACC, professor of cardiology at Rutgers Robert Wood Johnson Medical School in New Brunswick, New Jersey, and chief of the cardiovascular service line at Robert Wood Johnson University Hospital, said during a presentation at the American College of Cardiology Scientific Session.
Image: Adobe Stock
The experimental wrist-worn sensor (RCE Technologies) uses infrared light to detect the presence of troponin I in the blood through the skin. The data are then relayed via Bluetooth to a cloud-based system, then a machine-learning algorithm is used to assess the data to predict the wearer’s troponin level, according to Sengupta.
Sengupta and colleagues tested the clinical feasibility of the wrist-worn transdermal infrared spectrophotometric sensor in clinical practice and elevated the performance of a machine-learning algorithm for identifying elevated cardiac troponin I in real-world settings. The study enrolled clinically stable patients hospitalized for ACS at five sites in India. Wrist-worn sensor readings were taken, on average, the second day of hospitalization.
A deep-learning model was trained at three sites (n = 150), and then externally validated with troponin I at one site and with echocardiography and angiography at two sites (n = 88).
The findings were simultaneously published in the European Heart Journal - Digital Health.
According to the results, this technology predicted troponin I levels with about 90% accuracy.
“To ensure the model was associated with underlying disease features, we also associated the spectrophotometric recordings with the presence of obstructive coronary artery disease as seen on coronary angiogram after adjusting for the clinical covariates,” Sengupta said.
Sengupta reported that patients with abnormal troponin levels measured by the device were about four times as likely to have obstructive CAD (OR = 4.6) and three times as likely to have regional wall motion abnormality (OR = 3.37) compared with patients with a negative troponin result measured by the device.
Sengupta noted several limitations of the trial, including its small sample size and hypothesis-generating results. Further studies with larger populations are needed to address the diagnostic performance of this technology. Additionally, patients in this trial were hospitalized but not receiving treatment in the ED. Testing this device in the ED setting in the future would be useful, according to the researchers.
“The use of a transdermal sensor for bloodless estimation of cardiac troponin-I shows visibility and may have a role in real-world settings for diagnosing AMI in patients with suspected ACS,” Sengupta said. “Currently, the device is being tested for future clinical trials. There is a United States study that is undergoing enrollment for looking at the value of the device in emergency rooms, but this can be certainly extended even further to chest pain units, urgent care settings and perhaps could be utilized an implemented in ambulances and by trained paramedics without requiring any blood draw.”
Reference:
Perspective
Back to Top
There are a lot of technical issues that Dr. Sengupta has to deal with in making sure that the measurements are precise, reproducible and that they can be worn by patients of all different backgrounds, skin types and different settings, also whether they have to be sitting or lying flat for a long time or whether it be done on the field.
The wrist-worn sensor needs pretty massive numbers to be able to show that its measures of troponin I are precise and accurate.
Collapse
Sengupta P, et al. Joint American College of Cardiology/Journal of the American Medical Association Late-Breaking Clinical Trials. Presented at: American College of Cardiology Scientific Session; March 4-6, 2023; New Orleans (hybrid meeting).