Innovations in Public Health Services: Leveraging Data Science for Kidney Health Assessment

Abstract

Improvements in Public Health Services use advanced analytical methods to address kidney-related illnesses early through extensive data research and to enhance public health outcomes. The difficulty would be an extreme dependence on data, which could distort physical condition assessment by ignore kidney patient aspect like existence and socioeconomic conditions. To overcome this problem, use the machine learning (ML) approach in the proposed method. Differential Evolution optimization with Upgraded logistic regression (DEO-ULR) utilizedfor the kidney health evaluation. A diagnosis of CKD has comprehensive health information dataset available in open source Kaggle website. The gathered data is preprocessed using Min-Max normalization and employed feature selectedutilizing Recursive Feature Elimination (RFE). The suggested method is also compared the other traditional algorithms, and this study is experiment with in the Python platform. The findings show the suggested technique achieve enhanced performance in accuracy, precision, F1-Score and recall. The study demonstrates the probable of data science in improvingpublic health for kidney health assessment through advanced analytics, resulting in more precise diagnoses, efficient treatment strategies, and earlier detection for patients.