TabNet to Identify Risks in Chronic Kidney Disease Using GAN's Synthetic Data

The objective of this study was to develop a system for chronic kidney disease (CKD) and to identify relevant prognostic features using a clinical dataset. Accurate classification and major risk factors in chronic kidney disease lead to better prognosis and assist nephrologists. Due to privacy and other factors, the data source is not balanced to trail any models. Therefore, it is difficult to achieve consistent accuracy with an imbalanced dataset, and there will be a variance in results with different machine learning models. In the proposed study, GAN's generated synthesised dataset, which is very close to the original dataset, is used. A hybrid synthesised dataset consists of the original dataset along with the synthesised data generated with the GAN model. The proposed model also includes the most important risk variables for CKD. The metrics used in the study include F1-score, accuracy, and from the plot, it shows that the TabNet with GAN's synthetic data is more consistent and more accurate than the traditional machine learning techniques with imbalanced dataset. The proposed model iterated for 150 times to get the variance, which is much less than in proposed techniques with hybrid preprocessed datasets. The proposed work significantly increased the classification accuracy of chronic kidney disease. These models and parameters show how important health status data is for predicting the risk of and development of kidney disease.