Electrocardiograph Analysis for Risk Assessment of Heart Failure with Preserved Ejection Fraction: A Deep Learning Model
ESC Heart Failure · 2025
DOI: 10.1002/ehf2.15120 ↗Kurz gefasst
Fachartikel in der Zeitschrift ESC Heart Failure, 2025. Verfasst von Zheng Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, The First Hospital of Hebei Medical University, Shijiazhuang, China. Hauptthemen laut MEDLINE: Heart Failure, Deep Learning, Electrocardiography, Stroke Volume. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Hebei Province Health Commission for Medical Scientific Research.
Themen: Herzinsuffizienz
Abstract (Originalsprache)
Aims
Heart failure with preserved ejection fraction (HFpEF) requires an efficient screening method. We developed a deep learning model (DLM) to screen HFpEF risk using electrocardiograms (ECGs). Methods and results A cohort study was conducted utilising data from Cohorts A and B. A convolutional neural network-long short-term memory (CNN-LSTM) DLM was employed. HFpEF risk was determined by left ventricular end-diastolic pressure (LVEDP) and clinical symptoms. The DLM was trained by ECGs. LVEDP for each patient was collected through invasive left ventricular catheterisation. Cohort A and B comprised data from individuals at high risk for HFpEF (LVEDP > 12 mmHg) and low risk for HFpEF (LVEDP ≤ 12 mmHg). The model was trained on Cohort A and prospectively validated on Cohort B.
Results
A total of 238 patients underwent ECG and left ventricular catheterisation for model training in Cohort A, and 117 patients for validation in Cohort B. The DLM achieved 78% accuracy in assessing HFpEF risk in Cohort A, while in Cohort B, it demonstrated 78% accuracy, 71.9% specificity, and 71.7% sensitivity. In the validation Cohort B, the DLM-identified high-risk HFpEF group exhibited significantly higher prevalence of diabetes (22.03%–11.86%, P < 0.01), higher BMI indices (25.92–24.22 kg/cm2, P < 0.01), and lower usage history of calcium channel blockers (CCB) (11.76%–28.81%, P < 0.01) compared with the DLM-identified low-risk HFpEF group. Traditional HFpEF indicators, including B-type natriuretic peptide (BNP) (22–20 pg/mL, P = 0.71) and E/E′ (8.25–8.5, P = 0.66), did not exhibit significant differences between the two groups.
Conclusions
The DLM offers an accurate, cost-effective tool for HFpEF risk assessment, potentially facilitating early detection and improved clinical management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiology, The First Hospital of Hebei Medical University, Shijiazhuang, China.
- Department of Cardiology, Cangzhou Central Hospital, Cangzhou, China.
- Diagnostic Department, Faculty of Medicine, Cangzhou Medical College, Cangzhou, China.
ORCID-Profile: Chao Liu
Förderung
- Hebei Province Health Commission for Medical Scientific Research
Zitieren
APA
Gao, Z., Yang, Y., Yang, Z., Zhang, X., & Liu, C. (2025). Electrocardiograph Analysis for Risk Assessment of Heart Failure with Preserved Ejection Fraction: A Deep Learning Model. ESC Heart Failure. https://doi.org/10.1002/ehf2.15120
Vancouver
Gao Z, Yang Y, Yang Z, Zhang X, Liu C. Electrocardiograph Analysis for Risk Assessment of Heart Failure with Preserved Ejection Fraction: A Deep Learning Model. ESC Heart Failure. 2025. doi:10.1002/ehf2.15120
BibTeX
@article{Gao2025,
author = {Gao, Zheng and Yang, Yuqing and Yang, Zhiqiang and Zhang, Xinyue and Liu, Chao},
title = {Electrocardiograph Analysis for Risk Assessment of Heart Failure with Preserved Ejection Fraction: A Deep Learning Model},
journal = {ESC Heart Failure},
year = {2025},
doi = {10.1002/ehf2.15120}
}
EUVIMED