October 16, 2021Journal Of Big Data76 citationsOpen Access

Machine learning-based identification of patients with a cardiovascular defect

Q: What is the clinical evidence from this study?

Study design: Other. Population: Cardiovascular disease (n=4240). Intervention: Stacking machine learning algorithm with MICE data imputation vs. Base machine learning algorithms (XGBoost, AdaBoost, Gradient Boost, Extra Trees, LightGbm, SGDC, Nu SVM). Primary outcome: Prediction accuracy for cardiovascular disease.

NLNabaouia LouridiMohammed V University SDSamira DouziMohammed V University BOBouabid El OuahidiMohammed V University

Key Result

A stacking machine learning algorithm combined with MICE data imputation achieved a prediction accuracy of 95.83% on the UCI heart disease dataset and 90.24% on the Framingham dataset.

Structured PICO

Population

Patient records from the UCI Heart Disease dataset and the Framingham dataset (4,240 records) were used to train and evaluate machine learning models for predicting cardiovascular disease.

Intervention

Stacking machine learning algorithm combined with MICE imputation for missing data and SMOTE for imbalanced data

Comparator

Other machine learning algorithms (XGBoost, AdaBoost, Gradient Boost, Extra Trees, LightGbm, SGDC, Nu svc) and previous works

Outcome

Model performance metrics including accuracy, specificity, precision, recall, F-measure, and AUC

A stacking machine learning approach utilizing MICE imputation and SMOTE oversampling achieved high accuracy in predicting cardiovascular disease presence in public datasets.

Limitations

The study did not consider other clinically related disorders such as diabetes in the primary model.
The model does not yet incorporate environmental factors like meteorological conditions or air quality.

Abstract

Abstract Cardiovascular diseases had been for a long time one of the essential medical problems. As indicated by the World Health Association, heart ailments are at the highest point of ten leading reasons for death. Correct and early identification is a vital step in rehabilitation and treatment. To diagnose heart defects, it would be necessary to implement a system able to predict the existence of heart diseases. In the current article, our main motivation is to develop an effective intelligent medical system based on machine learning techniques, to aid in identifying a patient’s heart condition and guide a doctor in making an accurate diagnosis of whether or not a patient has cardiovascular diseases. Using multiple data processing techniques, we address the problem of missing data as well as the problem of imbalanced data in the publicly available UCI Heart Disease dataset and the Framingham dataset. Furthermore, we use machine learning to select the most effective algorithm for predicting cardiovascular diseases. Different metrics, such as accuracy, sensitivity, F-measure, and precision, were used to test our system, demonstrating that the proposed approach significantly outperforms other models.

问 AI

Bookmark

View Full Paper

问 AI

Bookmark

View Full Paper

Cite This Study

Louridi et al. (Sat,) conducted a other in Cardiovascular disease (n=4,240). Stacking machine learning algorithm with MICE data imputation vs. Base machine learning algorithms (XGBoost, AdaBoost, Gradient Boost, Extra Trees, LightGbm, SGDC, Nu SVM) was evaluated on Prediction accuracy for cardiovascular disease. A stacking machine learning algorithm combined with MICE data imputation achieved a prediction accuracy of 95.83% on the UCI heart disease dataset and 90.24% on the Framingham dataset.

synapsesocial.com/papers/6a211d7ba37b8f8d92968e26 https://doi.org/https://doi.org/10.1186/s40537-021-00524-9