Enhancing Healthcare Delivery with Cloud Computing Using CNN-RNN Models for Kidney Disease Diagnosis and Management
Year: 2025
Type: article
Abstract: Chronic Kidney Disease (CKD) is a chronic disease that must be diagnosed early to avoid kidney failure. This research proposes a hybrid model using Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to predict CKD from different patient medical information. The proposed model is instantiated on cloud resources for elastic storage and secure management of data with HIPAA-standard encryption for privacy. Comparison in terms of performance of the current cloud-based approach and the proposed CNN-RNN model reveals colossal improvement. The proposed approach optimizes critical measurements: latency from 200 ms to 110 ms, throughput from 1000 Mbps to 1150 Mbps, and processing time from 2 seconds to 1 second. Additionally, it has 100% fault tolerance and 99% data retention, outperforming the current cloud-based systems in every regard. The new CNN-RNN method is more effective compared to the current methods using performance indicators of a highest accuracy of 99%, precision of 95%, recall of 96%, and F1-score of 94%. The results show that the hybrid model is the most effective and precise method of diagnosing CKD.
Authors: Poovendran Alagarsundaram, Surendar Rama Sitaraman, Kalyan Gattupalli, Harikumar Nagarajan, Venkata Surya Bhavana Harish Gollavilli, Jayanth.S Jayanth.S
Institution: Jupiter (United States)
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4408678561