A Wearable Infrared Sensor for Detecting Non-ST Segment Elevation Acute Coronary Syndromes

Area of Science:

• Cardiovascular Medicine
• Biomedical Engineering
• Artificial Intelligence in Healthcare

Background:

• Conventional diagnosis of non-ST-segment elevation acute coronary syndrome (NSTE-ACS) relies on electrocardiography and serial blood biomarkers.
• There is a need for non-invasive, rapid, and accessible diagnostic tools for early NSTE-ACS risk stratification.

Purpose of the Study:

• To evaluate a novel, non-invasive, bloodless, and electrode-free diagnostic strategy for NSTE-ACS using a wrist-worn infrared spectrophotometric biosensor (Infrasensor).
• To assess the Infrasensor's performance in detecting high-grade coronary obstruction and predicting adverse outcomes in patients with suspected NSTE-ACS.

Main Methods:

• Prospective, multicenter study involving 595 patients with suspected NSTE-ACS across 13 sites.
• Development and validation of machine learning models using data from the Infrasensor.
• External validation using a leave-one-cohort-out approach with 200 multi-ethnic controls.

Main Results:

• A machine learning model detected high-grade coronary obstruction with an AUC of 0.87 (95% CI: 0.84-0.90), 90% specificity, and 84% positive predictive value.
• The model's performance surpassed standard risk scores in detecting coronary obstruction.
• A secondary model predicted 30-day freedom from NSTE-ACS and adverse outcomes with an AUC of 0.89 (95% CI: 0.87-0.92), 99% sensitivity, and 96% negative predictive value.

Conclusions:

• The Infrasensor demonstrates significant potential as a rapid, scalable point-of-care tool for early risk stratification in NSTE-ACS.
• This bloodless, electrode-free technology offers a promising alternative to conventional diagnostic methods.
• Further implementation could enhance timely diagnosis and management of NSTE-ACS patients.