Genomics at the Nexus of AI, Computer Vision, and Machine Learning

18A Comprehensive Approach for Enhancing Kidney Disease Detection Using Random Forest and Gradient Boosting

Mandeep Kumar^1*, Neerav Khare¹, Soumya Mani², Monika Bhakta³ and Gaurab Saha⁴

¹Department of Law, Sharda University, Greater Noida, India

²Delhi High Court, Delhi, India

³Department of Law, Sangam University, Bhilwara, Rajasthan, India

⁴Department of Law, JIMS College, Greater Noida, India

Abstract

Kidney disease poses a significant global health challenge, necessitating the development of robust and accurate diagnostic tools for early detection. This research proposes a comprehensive approach to enhance kidney disease detection by leveraging advanced machine learning techniques, specifically random forest and gradient boosting algorithms. The study utilizes a diverse dataset, i.e., CKD (chronic kidney disease), comprising clinical, demographic, and laboratory parameters to train and validate the models. Random forest, known for its ensemble learning capability and ability to handle diverse data types, is employed for feature selection and classification. Gradient boosting, a robust boosting algorithm, is integrated to refine the predictive performance further. The research focuses on balancing sensitivity and specificity to identify individuals at risk of kidney disease early while minimizing false positives. The models are fine-tuned through hyperparameter optimization and cross-validation to maximize their generalizability across different populations. Furthermore, ...