A Deep Learning-Based Predictive Approach for Early Detection of Chronic Kidney Disease Using Machine Learning Technique

View at publisher Summarise with VIRAT
Authors: J Adilakshmi, Sadargari Viharika, Katukojwala Shiva Sai, Addepalli Karthikeya, Vadla Harshitha, Suryadevara Purandhar
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Chronic Kidney Disease has emerged as a significant public-health problem in up to$\text{1 0} - \text{1 5} \%$of the population around the world. Because it slowly develops and early signs may not be present, many patients are diagnosed when the disease has already progressed. Historically, the assessment of CKD is dependent on labor-intensive review of laboratory results - an approach that might miss subtle early markers of the disease. In this paper, explore the possibility of using machine learning for early detection of CKD. Here introduce an Artificial Neural Network model and we train our model using the UCI CKD dataset in order to capture complex patterns and nonlinear dependencies among multiple clinical features. When the model was evaluated using standard performance measure (accuracy, precision response, and F1-score),observed that ANN model worked better than conventional classification methods. These results showed that ANN model had the ability to improve early CKD diagnosis, so that medical staff could make intervention in time and reduce burden on society caused by early missed diagnosis of disease. This approach supports early clinical decision-making and timely medical intervention by reducing the risk of delayed diagnosis. Overall, the proposed model contributes to efficient and reliable CKD prediction in healthcare systems.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Chronic Kidney Disease and Diabetes Data Mining and Machine Learning Applications

Publication details

Journal / source
International Conference on Sentiment Analysis and Deep Learning (ICSADL)
Pages
614–620
Publication date
18 February 2026
Language
EN