An automated clinical decision support system for predicting cardiovascular disease using ensemble learning approach

Cardiovascular disease remains a serious public health problem internationally, responsible for a considerable number of fatalities. Early and correct detection of cardiovascular illness is crucial for optimal care and control of the condition. In this paper, we present an ensemble learning technique that includes voting classifiers to increase the reliability of cardiovascular disease diagnosis. We obtained a set of data from five cardiology databases, which included the Cleveland, Hungary, Switzerland, Long Beach VA and Statlog (Heart) datasets, which supplied us with a total of 1189 entries. We employed a feature engineering approach to extract relevant features from the dataset, enabling us to acquire vital information to enhance our model's performance. We trained and evaluated several machine learning algorithms, such as Random Forests, MLP, K-Nearest Neighbors, Extra Trees, XGBoost, Support Vector Machines, AdaBoost, Decision Trees, Linear Discriminant Analysis, and Gradient Boosting, and then incorporated these models using voting classifiers to produce more reliable and accurate models. Our findings reveal that the proposed ensemble learning process outperforms standalone models and conventional ensemble approaches, obtaining an accuracy rate of 91.4%. Our technique is likely to benefit clinicians in the early diagnosis of heart problems and improve patient outcomes. This work has major significance for the area of cardiology, indicating the possibility for machine learning approaches to boost both the reliability and accuracy of heart disease identification. The recommended ensemble learning technique may be adopted in hospitals to enhance patient care and eventually lessen the worldwide impact of cardiovascular disease. Further study is required to investigate the uses of predictive modeling in cardiology and other medical domains.

show abstract

A differentially private distributed collaborative XGBoost method

Li,

et al. 2024

era

View full text Add to dashboard Cite

<abstract> <p>With the rapid progress of artificial intelligence (AI) technology in medical scenarios, it becomes a trend for medical services to adopt various AI algorithms for auxiliary diagnosis and health care of patients. However, medical data is often sensitive and possibly owned by multiple participants without the willingness of data sharing. To solve this problem under the vertical partition scenario of medical data, a differentially private distributed collaborative XGBoost method named DP-DCXGBoost was proposed and applied for disease classification in the paper. Initially, a reputation-based participant selection algorithm was designed, which evaluated the contribution of participants to the global model and used it for reputation calculation to select proper participants. Then, in the collaborative training phase, the proposed method utilized the local vertical dataset of each participant to calculate feature buckets and splitting gains in order to collaboratively construct a differentially private global XGBoost classification model. Finally, the experimental analysis for two real disease datasets showed that the proposed method had good classification accuracy on the basis of preserving participants' data privacy.</p> </abstract>

show abstract

An automated clinical decision support system for predicting cardiovascular disease using ensemble learning approach

Cited by 4 publications

References 36 publications

Efficient Way of Heart Disease Prediction and Analysis using different Ensemble Algorithm: A Comparative Study

Efficient Way of Heart Disease Prediction and Analysis using different Ensemble Algorithm: A Comparative Study

Ensemble Learning for Heart Disease Diagnosis: AVoting Classifier Approach

A differentially private distributed collaborative XGBoost method

Contact Info

Product

Resources

About