Sign in Subscribe
Algorithms

Early Diagnosis of Coronary Heart Disease Using Machine Learning and Deep Learning Techniques

Strategic Insights

— 2 min read

A new study on heart disease has revealed the potential of Machine Learning (ML) and Deep Learning (DL) techniques in early diagnosis of Coronary Heart Disease (CHD), one of the primary causes of cardiovascular morbidity and mortality worldwide. The researchers from Erzurum Technical University applied various ML and DL algorithms to two distinct datasets, including the comprehensive Framingham dataset and the UCI Heart Disease dataset. They implemented data preprocessing techniques such as Hotdecking, Synthetic Minority Oversampling Technique (SMOTE), and normalization to enhance data quality. Model performance was evaluated using a range of metrics, including accuracy, precision, recall, F1-score, and area under the curve (AUC).

Key Takeaways:

  • The study found that the Support Machine Vector (SVM) model achieved the highest accuracy of 92.42% on the UCI dataset, while the Extreme Gradient Boosting (XGBclassifier) model attained the highest accuracy of 90.97% on the Framingham dataset, surpassing the performance reported in existing literature.
  • The researchers demonstrated the potential of ML and DL methods for the early diagnosis of CHD and emphasized the importance of dataset selection on model performance.
  • The use of various ML and DL algorithms, including Multilayer Perceptron (MLP), Artificial Neural Networks (ANN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Support Machine Vector (SVM), Logistic Regression (LR), Decision Tree (DT), k-Nearest Neighbor (kNN), Categorical Naive Bayes (CategoricalNB), and Extreme Gradient Boosting (XGBclassifier), was found to be effective in early diagnosis of CHD.
  • The study highlights the significance of data-driven strategies in advancing healthcare for the early detection and management of CHD and similar cardiovascular diseases.
  • The authors, including Seda Demir, Harun Selvitopi, and Zulkuf Selvitopi, emphasize the importance of further research in this area to develop more accurate and effective diagnosis tools.

Statistics:

  • Accuracy of SVM model on UCI dataset: 92.42%
  • Accuracy of XGBclassifier model on Framingham dataset: 90.97%
  • Number of datasets used: 2 (Framingham and UCI Heart Disease datasets)
  • Number of ML and DL algorithms used: 11
  • Range of metrics used to evaluate model performance: accuracy, precision, recall, F1-score, and area under the curve (AUC)

Sources:

  • "An early and accurate diagnosis and detection of the coronary heart disease using deep learning and machine learning algorithms." Journal of Big Data, 2025,12(1):1-32. (Journal of Big Data - https://journalofbigdata.springeropen.com)
  • NewsRx. Erzurum Technical University Researchers Describe New Findings in Heart Disease (An early and accurate diagnosis and detection of the coronary heart disease using deep learning and machine learning algorithms). Cardiovascular Week. October 20, 2025; p 16.

Read more