Multilevel Ensemble Method to Identify Risks in Chronic Kidney Disease Using Hybrid Synthetic Data

This research was conducted with the goals of developing models that have an accurate classification of chronic kidney disease (CKD) and locating significant prognostic factors within a clinical dataset. In chronic kidney disease, accurate classification and identification of major risk factors contribute to improved prognoses and provide assistance to nephrologists. The data source is not balanced enough to serve as a benchmark for any machine learning or deep learning models due to privacy concerns and other factors. As a result, it is difficult to achieve consistent accuracy with an imbalanced dataset, and there will be a variance in results with various machine learning models due to the fact that there are so many different factors involved. A multiple-level ensemble learning system was utilised in the proposed research in order to classify chronic kidney disease using a hybrid synthesised dataset. A hybrid synthesised dataset is one that contains both the original dataset as well as the synthesised data that was produced using the ADASYN method. The most important risk factors for chronic kidney disease are accounted for in the model that was proposed. The F1-score and accuracy were two of the metrics that were utilised in this research. Furthermore, the plot demonstrates that the multilevel ensemble is superior to the conventional machine learning techniques in terms of consistency and accuracy. The variance was calculated using the proposed model by iterating for a total of 150 times, which is a significant reduction when compared to multi-level ensemble techniques using hybrid preprocessed datasets. The accuracy of classifying patients with chronic kidney disease was significantly improved by using a multi-level ensemble. These models and parameters highlight the significance of current health status information in estimating the likelihood of developing kidney disease as well as its progression.