Related Experiment Video
Updated: May 5, 2026
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
A hybridization of XGBoost machine learning model by Optuna hyperparameter tuning suite for cardiovascular disease
1Department of Electrical and Instrumentation Engineering,Sant Longowal Institute of Engineering and Technology, Longowal, Sangrur, Punjab, India.
Insights
This study introduces a hybrid XGBoost Classifier for heart disease (HD) prediction, achieving 95.45% accuracy by optimizing data preprocessing and model parameters. The framework offers efficient and accurate diagnosis for improved cardiac patient care.
Area of Science:
- Cardiology
- Machine Learning
- Data Science
Background:
- Heart disease (HD) is a leading cause of mortality worldwide, with over 31% of annual deaths attributed to it.
- Early diagnosis of HD is challenging due to complex and large medical datasets.
- Existing diagnostic methods require improvement for timely and accurate detection.
Purpose of the Study:
- To develop a novel hybrid XGBoost Classifier framework for enhanced heart disease prediction.
- To address the challenges in early HD diagnosis through advanced data processing and model optimization.
- To improve the accuracy and efficiency of heart disease diagnosis for better patient outcomes.
Main Methods:
- A hybrid XGBoost Classifier was developed, incorporating outlier removal using z-score and IQR methods.
- Hyperparameter tuning was performed using the Optuna framework for optimal model configuration.
- The model's performance was evaluated using various train-test ratios (70:30, 80:20, 90:10) on the Cleveland HD dataset, with and without outlier handling.
Main Results:
- The proposed hybrid model achieved superior performance metrics without outliers, particularly at a 90:10 train-test ratio.
- Key performance indicators included 95.45% accuracy, 92.86% sensitivity, 100% precision, and 100% specificity.
- The model demonstrated high efficiency with minimal training and testing times, validated by Stratify K-Fold Cross-Validation.
Conclusions:
- Data preprocessing, optimal train-test ratios, and hyperparameter optimization are crucial for accurate HD prediction.
- The developed framework presents a promising approach for efficient and accurate heart disease diagnosis.
- This advancement holds potential benefits for cardiac patient healthcare and clinical decision-making.
Background:
Over the last few decades: heart disease (HD) has emerged as one of the deadliest diseases in the world. Approximately more than 31 % of the population dies from HD each year. The Diagnosis of HD in an earlier stage is a cognitively challenging task due to the vast and complex availability of medical datasets. Many tests are available for the diagnosis of HD, such as ECG, etc.; but the proper diagnosis of the disease is still a great challenge.
Methods:
Motivated by existing challenges and the significance of HD, the authors developed a novel hybrid XGBoost Classifier framework for HD prediction that incorporates outlier removal and optimized hyperparameter tuning. In this approach, outliers were handled using z-score and interquartile range (IQR) methods, and hyperparameters were optimized using the "Optuna" framework. Additionally, the impact of different train-test ratios (70,30, 80:20, and 90:10) on model performance was evaluated using Cleveland HD dataset, both with and without outliers.
Results:
The proposed hybrid model achieved the finest performance metrics without outliers on a 90:10 train-test ratio with an accuracy of 95.45 %, sensitivity of 92.86 %, precision of 100 %, specificity of 100 %, f1-score 96.3 %, training time 0.8 × 10-16 s and testing time 0.1 × 10-17 s. It was validated by Stratify K-Fold Cross-Validation.
Conclusions:
This study highlights the importance of data preprocessing, appropriate train-test ratios, and hyperparameter optimization in HD prediction. The proposed framework provides a promising solution for accurate and efficient HD diagnosis, offering potential benefits for cardiac patient healthcare and decision-making.
