• SPEED-TR: a self-distilled and...

Treffer: SPEED-TR: a self-distilled and pre-trained transformer model for enhanced ECG detection of tricuspid regurgitation.

Title:
SPEED-TR: a self-distilled and pre-trained transformer model for enhanced ECG detection of tricuspid regurgitation.
Authors:
Diao, Xiaolin, Xu, Wei, Cheng, Huaibing, Zhou, Ya, Liu, Yang, Huo, Yanni, Lu, Jianli, Huang, Jinghan, He, Jia, Liu, Fang, Cao, Zhihui, Zhang, Xue, Zhao, Wei, Fan, Xiaohan
Source:
NPJ Digital Medicine; 11/12/2025, Vol. 8 Issue 1, p1-12, 12p
Subject Terms:
PREDICTIVE tests, DIAGNOSTIC imaging, T-test (Statistics), RESEARCH funding, ARTIFICIAL intelligence, RETROSPECTIVE studies, DESCRIPTIVE statistics, CHI-squared test, MANN Whitney U Test, ELECTROCARDIOGRAPHY, DEEP learning, COMPUTER-aided diagnosis, TECHNOLOGY, CALIBRATION, DATA analysis software, MEDICAL screening, TRICUSPID valve diseases, SENSITIVITY & specificity (Statistics), ECHOCARDIOGRAPHY, ALGORITHMS
Database:
Complementary Index

Weitere Informationen

Tricuspid regurgitation (TR) remains underdiagnosed due to the lack of effective screening tools. We developed a self-distilled and pre-trained transformer model for detecting TR (SPEED-TR) from electrocardiography. The model was trained using 466,149 electrocardiogram-echocardiogram pairs from 291,673 patients and validated in one internal (63,925 patients) and two external cohorts (44,951 and 21,300 patients). SPEED-TR accurately detected moderate-to-severe TR in the hold-out set (AUROC 0.945, NPV 0.983; specificity 0.973) and maintained stable performance in multi-center testing sets (AUROCs 0.939–0.943; NPVs 0.978–0.988). Three thresholds enabled SPEED-TR severity grading: none (0–0.008), mild (0.008–0.255), moderate (0.255–0.755), and severe (0.755–1), achieving accuracies of 0.749 (hold-out), 0.730 (internal), 0.775 and 0.726 (external), with overall accuracy of 0.744. SPEED-TR remained robust in patients with 1 to ≥3 risk factors and 1 to ≥2 valvular diseases. SPEED-TR demonstrated potential as a screening tool and may provide reference for TR severity assessment. [ABSTRACT FROM AUTHOR]

Copyright of NPJ Digital Medicine is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)