Predicting Kidney Stone Presence from Urine Analysis: A Neural Network Approach using JNN

International Journal of Academic Information Systems Research (IJAISR) 7 (9):32-39 (2023)
  Copy   BIBTEX

Abstract

Kidney stones pose a significant health concern, and early detection can lead to timely intervention and improved patient outcomes. This research endeavours to predict the presence of kidney stones based on urine analysis, utilizing a neural network model. A dataset of 552 urine specimens, comprising six essential physical characteristics (specific gravity, pH, osmolarity, conductivity, urea concentration, and calcium concentration), was collected and prepared. Our proposed neural network architecture, featuring three layers (input, hidden, output), was trained and validated, achieving an impressive accuracy of 98.67% and an average error of 0.012. In addition to model performance, feature importance analysis was conducted to determine the most influential factors in predicting kidney stone presence. The findings underscore the significance of urea concentration, specific gravity, calcium concentration, conductivity, osmolarity, and pH as key indicators. This research contributes to the early diagnosis of kidney stones and demonstrates the potential of neural networks in medical diagnostics. The clinical implications of these findings are discussed, emphasizing the importance of timely intervention in managing kidney stone-related health issues.

Author's Profile

Samy S. Abu-Naser
North Dakota State University (PhD)

Analytics

Added to PP
2023-10-06

Downloads
423 (#44,737)

6 months
269 (#9,125)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?