학술논문

Prediction of CKDu using KDQOL score, Ankle Swelling and Risk Factor Analysis using Neural Networks
Document Type
Conference
Source
2020 2nd International Conference on Advancements in Computing (ICAC) Advancements in Computing (ICAC),2020 2nd International Conference on. 1:91-96 Dec, 2020
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Robotics and Control Systems
Signal Processing and Analysis
Sensitivity
Filtration
Machine learning
Convolutional neural networks
Kidney
Diseases
Testing
Chronic Kidney Disease
Glomerular Filtration Rate
KDQOL
Creatinine Level
Language
Abstract
Chronic Kidney disease (Chronic Kidney Disease (CKD)) is a type of kidney disease where gradual loss of kidney function occurs over a period of months to years. But, when CKD cannot identify a manner or causation of the disease or set of causes it is known as Chronic Kidney disease with unknown etiology (CKDu). There are several factors to be considered when analyzing the main causes for CKDu such as socio-economic, environmental, meteorological and health aspects in relation to the CKDu in Sri Lanka. In this research work, identification of CKDu has been done using the relationship of the Kidney Disease Quality of Life (KDQOL) score, ankle swelling with the serum creatinine level of blood and considering risk factors. This research has been done using three major branches of Artificial Intelligence namely neural networks, convolutional neural networks and machine learning. The relationship between the mentioned factors and CKDu has been identified. The sensitivity of 77.27% and a specificity of 89.28% have been marked for the detection of CKDu related to ankle swellin.