Analyzing the Application of SMOTE on Machine Learning Classifiers

Rattan, Vikas; Mittal, Ruchi; Singh, Jaiteg; Malik, Varun

doi:10.1109/esci50559.2021.9396962

Cited by 12 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accurate identification of CAD and non-CAD instances may be impacted by the unbalanced distribution of the instances in the two classes. Here, an oversampling method is applied, namely SMOTE [ 49 ], which is based on the K-Nearest Neighbors (KNN) [ 50 ] classifier with

and creates synthetic data [ 51 ] on the minority class (see Algorithm 1). The instances in the CAD class are oversampled, such that the subjects in the two classes are uniformly distributed.…”

Section: Methodsmentioning

confidence: 99%

Long-Term Coronary Artery Disease Risk Prediction with Machine Learning Models

Trigka

Δρίτσας

2023

Sensors

View full text Add to dashboard Cite

The heart is the most vital organ of the human body; thus, its improper functioning has a significant impact on human life. Coronary artery disease (CAD) is a disease of the coronary arteries through which the heart is nourished and oxygenated. It is due to the formation of atherosclerotic plaques on the wall of the epicardial coronary arteries, resulting in the narrowing of their lumen and the obstruction of blood flow through them. Coronary artery disease can be delayed or even prevented with lifestyle changes and medical intervention. Long-term risk prediction of coronary artery disease will be the area of interest in this work. In this specific research paper, we experimented with various machine learning (ML) models after the use or non-use of the synthetic minority oversampling technique (SMOTE), evaluating and comparing them in terms of accuracy, precision, recall and an area under the curve (AUC). The results showed that the stacking ensemble model after the SMOTE with 10-fold cross-validation prevailed over the other models, achieving an accuracy of 90.9 %, a precision of 96.7%, a recall of 87.6% and an AUC equal to 96.1%.

show abstract

and creates synthetic data [ 51 ] on the minority class (see Algorithm 1). The instances in the CAD class are oversampled, such that the subjects in the two classes are uniformly distributed.…”

Section: Methodsmentioning

confidence: 99%

Long-Term Coronary Artery Disease Risk Prediction with Machine Learning Models

Trigka

Δρίτσας

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Since the efficiency of ML models and, thus, the accurate identification of CVD and non-CVD instances may be impacted by the unbalanced distribution of the instances in the two classes, an oversampling method is applied. In particular, SMOTE (Synthetic Minority Oversampling Technique) [ 52 ] was applied, which, based on a 5-NN classifier, creates synthetic data [ 53 ] on the minority class. The instances in the CVD class are oversampled such that the subjects in the two classes are uniformly distributed.…”

Section: Methodsmentioning

confidence: 99%

Efficient Data-Driven Machine Learning Models for Cardiovascular Diseases Risk Prediction

Δρίτσας

Trigka

2023

Sensors

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) are now the leading cause of death, as the quality of life and human habits have changed significantly. CVDs are accompanied by various complications, including all pathological changes involving the heart and/or blood vessels. The list of pathological changes includes hypertension, coronary heart disease, heart failure, angina, myocardial infarction and stroke. Hence, prevention and early diagnosis could limit the onset or progression of the disease. Nowadays, machine learning (ML) techniques have gained a significant role in disease prediction and are an essential tool in medicine. In this study, a supervised ML-based methodology is presented through which we aim to design efficient prediction models for CVD manifestation, highlighting the SMOTE technique’s superiority. Detailed analysis and understanding of risk factors are shown to explore their importance and contribution to CVD prediction. These factors are fed as input features to a plethora of ML models, which are trained and tested to identify the most appropriate for our objective under a binary classification problem with a uniform class probability distribution. Various ML models were evaluated after the use or non-use of Synthetic Minority Oversampling Technique (SMOTE), and comparing them in terms of Accuracy, Recall, Precision and an Area Under the Curve (AUC). The experiment results showed that the Stacking ensemble model after SMOTE with 10-fold cross-validation prevailed over the other ones achieving an Accuracy of 87.8%, Recall of 88.3%, Precision of 88% and an AUC equal to 98.2%.

show abstract