Machine Learning Performance Analysis to Predict Stroke Based on Imbalanced Medical Dataset

Cerebral stroke, the second most substantial cause of death universally, has been a primary public health concern over the last few years. With the help of machine learning techniques, early detection of various stroke alerts is accessible, which can efficiently prevent or diminish the stroke. Medical datasets, however, are frequently unbalanced in their class label, with a tendency to poorly predict minority classes. In this paper, the potential risk factors for stroke are investigated. Moreover, four distinctive approaches are applied to improve the classification of the minority class in the imbalanced stroke dataset, which are the ensemble weight voting classifier, the Synthetic Minority Over-sampling Technique (SMOTE), Principal Component Analysis with K-Means Clustering (PCA-Kmeans), Focal Loss with the Deep Neural Network (DNN) and compare their performance. Through the analysis results, SMOTE and PCA-Kmeans with DNN-Focal Loss work best for the limited size of a large severe imbalanced dataset (e.g., Stroke dataset), which is 2-4 times outperform Kaggle’s work.