Deep Learning for Early Detection of Cardiovascular Diseases From Medical Imaging
Health Science Reports · 2025-10 · 8 (10)
DOI: 10.1002/hsr2.71334 ↗Kurz gefasst
Fachartikel in der Zeitschrift Health Science Reports, online erschienen am 06.10.2025. Verfasst von Sangeeta Davi und 11 weiteren Autor:innen. Beteiligte Einrichtung: Peoples University of Medical and Health Sciences For Women (PUMHSW) Nawabshah Pakistan. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background
Cardiovascular diseases (CVDs) remain a leading cause of mortality worldwide, making early detection vital for reducing morbidity and death rates. Echocardiography is a widely used, noninvasive imaging tool for diagnosing CVDs, but manual interpretation can be time‐consuming and subject to variability. This study aims to evaluate the performance of a deep learning model using echocardiogram videos for the early detection of CVDs.
Methods
We applied a convolutional neural network (CNN), based on the ResNet‐50 architecture, to the EchoNet‐Dynamic data set, which includes echocardiogram videos. Preprocessing involved resizing frames and applying augmentation techniques to enhance model robustness. The data set was split into training (80%) and testing (20%) subsets. The model was trained to classify patients based on the presence or absence of CVD using temporal video features.
Results
The CNN model achieved strong performance metrics, with an overall accuracy of 92.3%, a precision of 91.5%, a recall of 92.7%, and an F1‐score of 92.1%. The area under the receiver operating characteristic curve (AUC‐ROC) was 0.95, indicating excellent discriminatory ability. These results highlight the model's capability to detect CVDs accurately from dynamic echocardiographic imaging.
Conclusion
This study demonstrates the potential of deep learning, particularly CNN‐based models, for automating the early detection of CVDs using echocardiogram videos. The high performance of the model suggests it could contribute to faster, more accurate, and cost‐effective diagnosis in clinical practice. Future research should focus on improving model generalizability across diverse populations and enhancing interpretability for integration into clinical workflows.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Peoples University of Medical and Health Sciences For Women (PUMHSW) Nawabshah Pakistan.
- Shaheed Mohtarma Benazir Bhutto Medical College Lyari Karachi Pakistan.
- SR Sanjeevani Hospital Nepal Kalyanpur Siraha Nepal.
- Department of Internal Medicine Rama Medical College Hospital & Research Centre Pilkhuwa, Hapur Uttar Pradesh India.
ORCID-Profile: Ashvin Kumar, F N U Venjhraj, Amogh Verma
Zitieren
APA
Davi, S., Kumar, M., Hanif, Z. M., Kumar, A., Kumari, M., Ridham, F. N. U., Shaikh, A. S., Azad, I. F., Kumar, M., Suwasi, F. N. U., Venjhraj, F. N. U., & Verma, A. (2025). Deep Learning for Early Detection of Cardiovascular Diseases From Medical Imaging. Health Science Reports, 8(10). https://doi.org/10.1002/hsr2.71334
Vancouver
Davi S, Kumar M, Hanif ZM, Kumar A, Kumari M, Ridham FNU, et al. Deep Learning for Early Detection of Cardiovascular Diseases From Medical Imaging. Health Science Reports. 2025;8(10). doi:10.1002/hsr2.71334
BibTeX
@article{Davi2025,
author = {Davi, Sangeeta and Kumar, Mukesh and Hanif, Zainab Muhammad and Kumar, Ashvin and Kumari, Muskan and Ridham, F N U and Shaikh, Aiman Salam and Azad, Insiya Fatima and Kumar, Manesh and Suwasi, F N U and Venjhraj, F N U and Verma, Amogh},
title = {Deep Learning for Early Detection of Cardiovascular Diseases From Medical Imaging},
journal = {Health Science Reports},
year = {2025},
volume = {8},
number = {10},
doi = {10.1002/hsr2.71334}
}
EUVIMED