Predicting Chronic Kidney Disease (CKD) Using Histopathological Images and Clinical Data

Yusuff Nazzer, Haameem Shimar (2025) Predicting Chronic Kidney Disease (CKD) Using Histopathological Images and Clinical Data. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

A Chronic Kidney Disease (CKD) is a widespread and progressive health condition that frequently remains undetected until its advanced stages. Early
identification is essential to improving clinical outcomes and reducing the burden of disease. This thesis presents an intelligent diagnostic framework for early CKD prediction, leveraging two complementary deep learning models: one for medical image classification and another for the analysis of structured and unstructured clinical data. A convolutional neural network (CNN) processes kidney images to classify them into four categories—normal, kidney stone, chronic kidney disease, and tumor—thereby detecting morphological indicators relevant to CKD assessment. In parallel, a multi-task neural network ingests structured clinical parameters alongside TF-IDF–vectorized patient symptom narratives to jointly estimate CKD presence, glomerular filtration rate (GFR), and disease stage. The models operate independently, and their outputs are integrated at the application layer to provide a comprehensive diagnostic report. The system is implemented as an interactive Streamlit-based web application, enabling clinicians and patients to upload kidney images, input clinical data, and receive immediate, interpretable predictions. By combining insights from imaging and clinical data analysis, this approach offers a multifaceted assessment of CKD risk, with potential for future extension into a fully unified multimodal diagnostic system.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Simiscuka, Anderson UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence R Medicine > Healthcare Industry H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	12 Aug 2026 10:17
Last Modified:	12 Aug 2026 10:17
URI:	https://norma.ncirl.ie/id/eprint/9518

Actions (login required)

View Item