Research on Early Warning Model of Cardiovascular Disease Based on Computer Deep Learning

TL;DR

This paper develops a cardiovascular disease early warning model using 1D convolutional neural networks, improving prediction accuracy and curve fitting on UCI heart disease data.

Contribution

It introduces a novel 2D matrix conversion of 1D CNNs and applies advanced optimization techniques for improved early warning of cardiovascular diseases.

Findings

Prediction accuracy increased by 11.2%

Significant improvement in curve fitting

Effective application of CNNs for health risk prediction

Abstract

This project intends to study a cardiovascular disease risk early warning model based on one-dimensional convolutional neural networks. First, the missing values of 13 physiological and symptom indicators such as patient age, blood glucose, cholesterol, and chest pain were filled and Z-score was standardized. The convolutional neural network is converted into a 2D matrix, the convolution function of 1,3, and 5 is used for the first-order convolution operation, and the Max Pooling algorithm is adopted for dimension reduction. Set the learning rate and output rate. It is optimized by the Adam algorithm. The result of classification is output by a soft classifier. This study was conducted based on Statlog in the UCI database and heart disease database respectively. The empirical data indicate that the forecasting precision of this technique has been enhanced by 11.2%, relative to conventional approaches, while there is a significant improvement in the logarithmic curve fitting. The efficacy and applicability of the novel approach are corroborated through the examination employing a one-dimensional convolutional neural network.