Back

Quantifying myocardial repolarization instability using wearable radar-based non-contact estimation of the JT variability index

Riaz, Z.; Pella, S. I.; Tom, N.; Halaki, M.; Esgin, T.; Ugander, M.; Yuce, M.

2025-12-04 cardiovascular medicine
10.64898/2025.12.02.25341506 medRxiv
Show abstract

Background and AimsMyocardial repolarization instability measured by electrocardiography (ECG) as the QT variability index (QTVI) predicts arrhythmic risk. We aimed to introduce and validate a non-contact wearable radar-based method for assessing myocardial repolarization instability. MethodsQTVI by ECG (normalized QT variability to normalized heart rate variability) was compared to the analogous J-point-to-T-end variability index (JTVI) by ECG. Simultaneous 2-minute ECG and wearable radar recordings were analysed using an intelligent algorithm to extract mechanical correlates of the J-point and Tend from radar-derived cardiac motion signals, and compared to JTVI by ECG. ResultsBased on a selection of publicly available datasets of 9 patients with atrial fibrillation, 11 patients with sinus rhythm and 20 healthy people (n=40, 23% with atrial fibrillation, mean{+/-}SD heart rate 85{+/-}12 beats/min, QTVI -0.36{+/-}0.75, JTVI -0.10{+/-}0.75), the SD of JT and QT intervals strongly agreed (R{superscript 2}>0.99, bias -0.4{+/-}1.5 ms, 1.1{+/-}3.9%), and JTVI and QTVI correlated closely (R{superscript 2}=0.98, QTVI=1.0*JTVI-0.26, bias -0.26{+/-}0.11). Among a separate group of healthy volunteers (n=20, age 43{+/-}11 years, 25% female, heart rate 66{+/-}14 beats/min, JTVI - 0.52{+/-}0.51), there was excellent agreement for ECG-derived and radar-estimated SD of JT (R{superscript 2}=0.88, bias 0.1{+/-}4.9 ms, 6.4{+/-}2.7 %), SD of beat-to-beat interval (SDNN) (R{superscript 2}=0.93, bias 16.0{+/-}22.1 ms, 9.5{+/-}4.9 %), and JTVI (R{superscript 2}=0.99, bias 0.00{+/-}0.05, 0.0{+/-}6.5 %). ConclusionQTVI and JTVI adjusted for a small bias are effectively interchangeable for quantifying myocardial repolarization instability, and JTVI can be accurately and precisely estimated using radar sensors. This illustrates the feasibility for non-contact wearable radar-based monitoring of arrhythmic risk, with particular applicability to culturally sensitive populations.

Matching journals

The top 8 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.