International Journal of Science, Engineering and TechnologyAuthors: Gomathi T, Nivedita K, Sindhu M, Soundarya P
Abstract: Coronary Heart Disease (CHD) remains one of the leading causes of mortality worldwide, necessitating early and accurate prediction methods to improve patient outcomes. This paper proposes an efficient predictive framework using an improved Light Gradient Boosting Machine (LightGBM) algorithm for the early detection of CHD. The proposed model integrates advanced preprocessing techniques, including data cleaning, normalization, and feature selection, to enhance data quality and relevance. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is employed, thereby improving model robustness. Hyperparameter tuning is also performed to optimize model performance and reduce overfitting. The system is trained and evaluated using clinical datasets containing key attributes such as age, blood pressure, cholesterol levels, and lifestyle factors. Experimental results demonstrate that the improved LightGBM model achieves higher accuracy, precision, and recall compared to traditional machine learning approaches. Additionally, the model identifies significant risk factors contributing to CHD, supporting clinical decision-making. The proposed approach provides a reliable, scalable, and efficient solution for early CHD prediction, with potential applications in healthcare systems for preventive diagnosis and risk assessment. The improved LightGBM model not only enhances predictive accuracy but also reduces computational complexity, making it suitable for large-scale medical datasets. Furthermore, the interpretability of the model, achieved through feature importance analysis, enables healthcare professionals to better understand contributing risk factors and take proactive preventive measures. This approach bridges the gap between data- driven insights and clinical practice, ultimately contributing to improved patient care, early intervention, and reduced mortality associated with coronary heart disease.
