A customized stacked dense network model for chronic kidney disease prediction

Abstract

Chronic kidney disease (CKD) is still a health concern, even though surgical care and treatment have improved. Recently, academics throughout the globe have been more interested in creating high-performance approaches for diagnosing, treating, and preventing kidney disease by being more knowledgeable about the aspects that the issue is concerned with, designed to provide better. Evaluation of patient records for patients may assist health care providers detects sickness earlier on. Several have tried to construct sophisticated algorithms that forecast CKD by analyzing health data, but their effectiveness needs improvement. An intelligence categorization and linear regression model are suggested in this paper. The kidney-related disorders are predicted using a customized stacked dense network model (). Compared to current models, the testing of the conceptual scheme reveals that it can predict CKD with 98.5% accuracy. Research suggests that utilizing sophisticated deep learning algorithms is advantageous for treatment decisions and may assist in the early diagnosis of CKD and its associated stages, reducing the development of kidney problems.