Related Experiment Video
Updated: Feb 4, 2026
Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice
Published on: February 14, 2017
A novel approach for accurate disease prediction: Application to heart and liver diseases
Satyanarayana Poojari1, B Ismail2
1Department of Applied Statistics and Data Science, Prasanna School of Public Health, Manipal Academy of Higher Education, Manipal, Karnataka, India.
Insights
A new hybrid machine learning model improves early detection of heart and liver diseases. This model combines decision tree and logistic regression for higher accuracy, outperforming existing methods on both balanced and imbalanced datasets.
Area of Science:
- Health Informatics
- Computational Biology
- Machine Learning in Healthcare
Background:
- Heart and liver diseases are leading global causes of mortality.
- Early detection is crucial for preventing complications and improving patient outcomes.
- Existing machine learning models like logistic regression (LR) and decision tree (DT) have limitations, including overfitting and high misclassification rates.
Purpose of the Study:
- To develop a hybrid classification model that combines the strengths of decision tree and logistic regression.
- To address the limitations of individual LR and DT models in predicting heart and liver diseases.
- To improve the accuracy and efficiency of predictive models in health science.
Main Methods:
- A hybrid classification model integrating decision tree and logistic regression was developed.
- Monte Carlo simulations and empirical studies were conducted for performance evaluation.
- The proposed model was compared against Logistic Regression, Decision Tree, Support Vector Machine, K-Nearest Neighbors, and Random Forest using heart and liver disease datasets.
Main Results:
- The hybrid model demonstrated superior predictive performance compared to other classification models across various sample sizes.
- Empirical data showed high predictive accuracy: 91% for heart disease and 95% for liver disease.
- The model effectively handled both balanced and imbalanced datasets without requiring specific balancing techniques.
Conclusions:
- The developed hybrid model offers enhanced prediction accuracy for heart and liver diseases, irrespective of data size or balance.
- This improved efficiency facilitates earlier disease detection and better clinical decision-making.
- The model contributes to the advancement of health systems by providing a more robust predictive tool.
Background:
Heart and liver diseases are among the leading causes of mortality globally. Their early detection can prevent complications, reduce costs, and ensure healthy lives and well-being for everyone. Machine learning-based predictive models, such as logistic regression (LR) and decision tree (DT) are commonly used in health science for prediction. Even though LR and DT are effective, they have major drawbacks. DT assigns the same class to all observations in a branch which can lead to overfitting, while LR model often produces high misclassification rates and overfit when dealing with high-dimensional data. To address these limitations, this paper proposes a hybrid classification model combining the strengths of DT and LR.
Materials And Methods:
Monte Carlo simulation and empirical study are conducted to compare the predictive performance of the proposed model with LR, DT, Support Vector Machine, K-Nearest Neighbors, and Random Forest. For the empirical study two datasets namely, heart disease prediction dataset (balanced, 303 observations, 14 variables) and Liver disease dataset (imbalanced, 583 observations, 11 variables) are used.
Results:
The simulation results indicate the hybrid model outperforms other classification models considered, across various sample sizes. These findings are consistent with the empirical data, showing predictive accuracy of 91% for heart disease and 95% for liver disease data.
Conclusion:
The developed hybrid model has enhanced prediction accuracy irrespective of sample size and effectively handles both balanced and imbalanced data, reducing the need to identify suitable balancing techniques. Improved efficiency can help with early detection, better decision-making, and improved health systems.
More Related Videos
08:41Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease
Published on: March 24, 2023
09:27Analysis of Liver Microenvironment During Early Progression of Non-Alcoholic Fatty Liver Disease-Associated Hepatocellular Carcinoma in Zebrafish
Published on: April 1, 2021
Related Concept Videos
01:26Diseases of the Liver and Gallbladder
Cirrhosis is characterized by the scarring of hepatic lobules in the liver, which are replaced by fibrous tissue, affecting the liver's normal functioning. NAFLD, on the other hand, is caused by an excessive build-up of fat in the liver, not...
01:23Rheumatic Heart Disease I: Introduction
01:17Ischemic Heart Disease: Overview
Atherosclerosis, the primary malefactor, orchestrates this dangerous condition. It manifests as the accumulation of fatty deposits, akin to insidious plaques, within arterial walls. As time elapses, these plaques metamorphose, hardening and...
01:21Rheumatic Heart Disease III: Medical Management
01:20Rheumatic Heart Disease IV: Nursing Management
01:22Effect of Hepatic Disease on Pharmacokinetics: Pathophysiologic Assessment and Liver Function Test