Back

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

Sengupta, P. P.; Jamthikar, A. D.; Yanamala, N.; Maganti, K.; Titus, J.; Bhavnani, S.; Sengupta, S.

2025-12-30 cardiovascular medicine
10.64898/2025.12.24.25342991 medRxiv
Show abstract

Non-ST-segment elevation acute coronary syndrome (NSTE-ACS) is conventionally diagnosed using electrocardiography and serial blood biomarker measurements. We investigated a non-invasive, bloodless, and electrode-free diagnostic strategy using a wrist-worn infrared spectrophotometric biosensor (Infrasensor). In a prospective, multicenter study of 595 patients with suspected NSTE-ACS enrolled across 13 sites in two countries, participants were stratified into five analytical cohorts. With 200 multi-ethnic controls and a leave-one-cohort-out external validation, a machine learning model detected high-grade coronary obstruction with an area under the receiver operating characteristic curve (AUC) of 0.87 (95% CI: 0.84-0.90), 90% specificity, and 84% positive predictive value--surpassing standard risk scores. A secondary model predicted freedom from NSTE-ACS and adverse outcomes over 30 days with an AUC of 0.89 (95% CI: 0.87-0.92), 99% sensitivity, and 96% negative predictive value. These findings demonstrate the potential of the Infrasensor as a rapid, scalable point-of-care tool for early risk stratification in NSTE-ACS.

Published in Life · training set

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.