Article icon
Original research

A Predictive Model for Cardiovascular Diseases Using Data Mining Techniques

* Corresponding author

[email protected]


In many countries, heart disease is the main cause of mortality. Heart diseases are often identified by doctors based on recent clinical trial results and their prior experience treating patients who present comparable symptoms. Patients with heart disease require early diagnosis, prompt treatment or constant monitoring. The purpose of this study is to look into the numerous data mining technologies that have recently been developed for predicting heart disease. According to observations, 15 feature neural networks outperform all other data mining methodologies. Another finding from the analysis is that decision trees using genetic algorithms or feature subset selection have good accuracy. The results illustrate that the same classifier can occasionally produce precise results that change depending on the data mining approach used. According to the findings, a neural network with 15 characteristics has so far achieved a maximum efficiency of 100%. Decision Tree, on the other hand, has also done well, with 98.65% accuracy and 15 features.


Avneesh Kumar, Santosh Kumar Singh, Shruti Sinha. A Predictive Model for Cardiovascular Diseases Using Data Mining Techniques. Cardiometry; Issue 24; November 2022; p.367-372; DOI: 10.18137/cardiometry.2022.24.367372; Available from:


Cardiovascular Disease (CVD),  Cardiomyopathy,  Data mining,  Decision Tree,  Neural Network
Download PDF
Cardiometry in Telegram
Current issue
Cardiometry's library
Founders of Cardiometry
Video about Cardiometry
Club of long-livers 90+
Our partners