Skip to content
DraconiticResearch
Search Sources API
186,086 studies31 sourcesUpdated 36 min ago
Peer-reviewedCC BY 4.0JACC Asia

Using AI-ECG to Stratify Long-Term Mortality Risk and Prognosis in TAVR Patients

  • Wence Shi1
  • Peirou Yan2
  • Qifeng Zhu3,4,5,6
  • Guo Pu7
  • Xianbao Liu3,4,5,6
  • Cheng Li3,4,5,6
  • Moyang Wang1
  • Guannan Niu1
  • Zhenyan Zhao1
  • Zheng Zhou1
  • Dejing Feng1
  • Yongjian Wu1
2 more authors
  • Jian'an Wang3,4,5,6
  • Hongliang Zhang1
7 affiliations
  1. 1Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Disease, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
  2. 2State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Tianjin, China
  3. 3Department of Cardiology, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China
  4. 4State Key Laboratory of Transvascular Implantation Devices, Hangzhou, China
  5. 5Heart Regeneration and Repair Key Laboratory of Zhejiang Province, Hangzhou, China
  6. 6Transvascular Implantation Devices Research Institute, Hangzhou, China
  7. 7Peking University, Beijing, China
Read full textDOICite

Abstract

Background: Long-term mortality remains unsatisfactorily high after transcatheter aortic valve replacement (TAVR). Conventional risk models are limited in capturing subclinical electrophysiological alterations associated with poor prognosis, which can be identified on routine preoperative electrocardiograms.

Objectives: The authors aim to develop and validate an artificial intelligence–enhanced electrocardiogram (AI-ECG) model for predicting long-term mortality in post-TAVR patients.

Methods: A total of 711 patients with severe aortic stenosis undergoing TAVR were enrolled from 2 centers. Patients from one center were divided into training and internal validation sets (7:3), and participants from another center served as the external validation cohort. Preoperative electrocardiogram images were analyzed using a Residual Network-18 model to generate mortality risk stratification. The primary endpoint was 3-year all-cause death.

Results: The AI-ECG model demonstrated comparable discrimination between the internal and external patient cohorts, with areas under the receiver operating characteristics curve of 0.767 (95% CI: 0.657-0.877) vs 0.712 (95% CI: 0.627-0.795) (P for DeLong test = 0.428). High-risk patients (15.5% [39 of 251]) exhibited a 61.5% (24 of 39, 95% CI: 42.8%-74.1%) 3-year mortality rate vs 16.5% (35 of 212, 95% CI: 11.4%-21.4%) in low-risk patients (84.5% [212 of 251]) (log-rank P < 0.001). Adjusted for comorbidities, high-risk classification independently predicted mortality (adjusted HR: 3.49; 95% CI: 1.96-6.22). Subgroup analysis did not reveal significant interaction effects of the AI-ECG model across different patient populations. Decision curve analysis confirmed clinical net benefit across threshold probabilities (0.05-0.60).

Conclusions: The AI-ECG model provides noninvasive and accurate long-term risk stratification for TAVR patients, with promising clinical application value for individualized follow-up management.

Related

  1. Evaluation of Clinical SYNTAX Score in Predicting New-Onset Atrial Fibrillation and Long-Term Prognosis in Patients Hospitalized with Non-ST Segment Elevation Myocardial Infarction
    Zubeyir Bulat, Mehmet Emin Gokce, Sukru Arslan +7
    Journal of cardiovascular development and diseasePeer-reviewedCC BYFull textCardiovascular medicineEurope PMC
  2. Dynamic serum chloride trajectories predict short- and long-term mortality in patients with malignancies: a retrospective cohort study with external validation
    Ruming Zhao, Shaojun Yang
    Frontiers in oncologyPeer-reviewedCC BYFull textOncologyEurope PMC
  3. Machine Learning-Based Prediction of Long-Term Mortality in Patients with Implantable Cardioverter Defibrillators
    Lei Pan, Zilong Xiao, Ziqing Yu +8
    Journal of cardiovascular development and diseasePeer-reviewedCC BYFull textCardiovascular medicineEurope PMC
  4. Impact of Laparoscopic Liver Resection on Long‐Term Outcomes and Non‐Liver‐Related Mortality in Elderly Patients With Primary Hepatocellular Carcinoma: A Multicenter Propensity Score‐Matched Analysis
    Yukio Tokumitsu, Hidenori Takahashi, Yuki Nakagami +17
    Annals of gastroenterological surgeryPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  5. Long-term prognosis and postoperative liver atrophy after gastrectomy in patients with gastric cancer and liver cirrhosis
    Atsushi Yasuda, Masuhiro Terada, Naoko Konami +10
    Surgery TodayPeer-reviewedCC BY 4.0Full textGeneral medicinePMC

Cite

BibTeXRIS
BibTeX
@article{shi2026using,
  title = {{Using AI-ECG to Stratify Long-Term Mortality Risk and Prognosis in TAVR Patients}},
  author = {Wence Shi and Peirou Yan and Qifeng Zhu and Guo Pu and Xianbao Liu and Cheng Li and Moyang Wang and Guannan Niu and Zhenyan Zhao and Zheng Zhou and Dejing Feng and Yongjian Wu and Jian'an Wang and Hongliang Zhang},
  journal = {JACC Asia},
  year = {2026},
  month = aug,
  doi = {10.1016/j.jacasi.2026.05.034},
  url = {https://doi.org/10.1016/j.jacasi.2026.05.034},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Using AI-ECG to Stratify Long-Term Mortality Risk and Prognosis in TAVR Patients
AU  - Wence Shi
AU  - Peirou Yan
AU  - Qifeng Zhu
AU  - Guo Pu
AU  - Xianbao Liu
AU  - Cheng Li
AU  - Moyang Wang
AU  - Guannan Niu
AU  - Zhenyan Zhao
AU  - Zheng Zhou
AU  - Dejing Feng
AU  - Yongjian Wu
AU  - Jian'an Wang
AU  - Hongliang Zhang
PY  - 2026
DA  - 2026/08/06
JO  - JACC Asia
DO  - 10.1016/j.jacasi.2026.05.034
UR  - https://doi.org/10.1016/j.jacasi.2026.05.034
AB  - Background: Long-term mortality remains unsatisfactorily high after transcatheter aortic valve replacement (TAVR). Conventional risk models are limited in capturing subclinical electrophysiological alterations associated with poor prognosis, which can be identified on routine preoperative electrocardiograms.  Objectives: The authors aim to develop and validate an artificial intelligence–enhanced electrocardiogram (AI-ECG) model for predicting long-term mortality in post-TAVR patients.  Methods: A total of 711 patients with severe aortic stenosis undergoing TAVR were enrolled from 2 centers. Patients from one center were divided into training and internal validation sets (7:3), and participants from another center served as the external validation cohort. Preoperative electrocardiogram images were analyzed using a Residual Network-18 model to generate mortality risk stratification. The primary endpoint was 3-year all-cause death.  Results: The AI-ECG model demonstrated comparable discrimination between the internal and external patient cohorts, with areas under the receiver operating characteristics curve of 0.767 (95% CI: 0.657-0.877) vs 0.712 (95% CI: 0.627-0.795) (P for DeLong test = 0.428). High-risk patients (15.5% [39 of 251]) exhibited a 61.5% (24 of 39, 95% CI: 42.8%-74.1%) 3-year mortality rate vs 16.5% (35 of 212, 95% CI: 11.4%-21.4%) in low-risk patients (84.5% [212 of 251]) (log-rank P < 0.001). Adjusted for comorbidities, high-risk classification independently predicted mortality (adjusted HR: 3.49; 95% CI: 1.96-6.22). Subgroup analysis did not reveal significant interaction effects of the AI-ECG model across different patient populations. Decision curve analysis confirmed clinical net benefit across threshold probabilities (0.05-0.60).  Conclusions: The AI-ECG model provides noninvasive and accurate long-term risk stratification for TAVR patients, with promising clinical application value for individualized follow-up management.
SN  - 2772-3747
ER  -