Preprint / Version 1

The Potential of using Neural Networks in the diagnosis of Cardiovascular Disease


  • Salil Belgal Independent researcher(but done Polygence pod)



Convolutional neural networks, Cardiovascular disease, Recurrent neural networks


Cardiovascular diseases are the leading cause of death globally. Early detection and prognosis of these diseases is vital, which is why scientists have turned over to new technologies such as neural networks to speed up the long manual process of identifying key features from both cardiac imaging data and cardiac time-series data that can help doctors predict and diagnose cardiovascular risk. This paper specifically looked at the effectiveness of Convolutional neural networks (CNNs) in analyzing echocardiograms and the effectiveness of Recurrent neural networks (RNNs) in analyzing electrocardiograms and patient records. This paper also explains the basics on how both types of networks are structured, trained, and evaluated. These basics help to understand the existing studies that this paper analyzes to evaluate the effectiveness of both CNNs and RNNs in the cardiovascular healthcare field. The key statistics from the studies suggest that both RNNs and CNNs have great capabilities in helping doctors find key features and predict cardiovascular risk from both cardiac imaging and time-series data.


World Health Organization. (2021). Cardiovascular diseases.

IBM. (n.d.). What are neural networks?

Kim, J. O., Jeong, Y.-S., Kim, J. H., Lee, J.-W., Park, D., & Kim, H.-S. (2021). Machine Learning-Based Cardiovascular Disease Prediction Model: A Cohort Study on the Korean National Health Insurance Service Health Screening Database. Diagnostics, 11(6), 943.

IBM. (n.d.). What are recurrent neural networks?

Laskowski, N. (2021). What are recurrent neural networks? TechTarget.,predict%20the%20next%20likely%20scenario

Awati, R. (2023). Convolutional neural network (CNN). TechTarget.

Stewart, M. (2019). Simple Introduction to Convolutional Neural Networks. Towards Data Science.

Shah, S. (2022). Convolutional Neural Network: An Overview. Analytics Vidhya.,called%20the%20weights%20of%20CNN.&text=A%20feature%20map%20is%20a,inputs%20with%20the%20same%20weights

Roy, R. (2022). Neural Networks: Forward Pass and Backpropagation. Towards Data Science.

Arie, L. G. (2021). Neural Network Backpropagation made easy. Towards Data Science.

Nabi, J. (2019). Recurrent Neural Networks (RNNs). Towards Data Science.

Brownlee, J. (2020). A Gentle Introduction to Backpropagation Through Time. Machine Learning Mastery.

Patil, S. (2023). Vanishing Gradient Problem in RNNs. Medium.

Dilmegani, C. (2022). Machine Learning Accuracy: True-False Positive/Negative. AIMultiple.

Mankad, S. (2020). A Tour of Evaluation Metrics for Machine Learning. Analytics Vidhya.

Kharwal, A. (2021). R2 Score in Machine Learning. The Clever Programmer.

Mayo Clinic Staff. (2022). Electrocardiogram (ECG or EKG). Mayo Clinic.

Singh, S., Pandey, S. K., Pawar, U., & Janghel, R. R. (2018). Classification of ECG Arrhythmia using Recurrent Neural Networks. Procedia Computer Science, 132, 1290-1297.

Guo, A., Beheshti, R., Khan, Y. M., Langabeer II, J. R., Foraker, R. E. (2021). Predicting cardiovascular health trajectories in time-series electronic health records with LSTM models. BMC Medical Informatics and Decision Making, 21(1), 5.

NHS. (2022). Echocardiogram.

Ghorbani, A., Ouyang, D., Abid, A., He, B., Chen, J. H., Harrington, R. A., ... Zou, J. Y. (2020). Deep Learning interpretation of echocardiograms. npj Digital Medicine, 3, 10.

Blouin, L. (2023). AI’s mysterious “black box” problem, explained. University of Michigan-Dearborn.