Litcius/Paper detail

Diagnosis of Chronic Kidney Disease Based on CNN and LSTM

Elif Nur Yildiz, Emine Cengil, Muhammed Yıldırım, Harun Bingöl

2023Acadlore Transactions on AI and Machine Learning10 citationsDOIOpen Access PDF

Abstract

Kidney plays an extremely important role in human health, and one of its important tasks is to purify the blood from toxic substances. Chronic Kidney Disease (CKD) means that kidney begins to lose its function gradually and show some symptoms, such as fatigue, weakness, nausea, vomiting, and frequent urination. Early diagnosis and treatment increase the likelihood of recovery from the disease. Due to high classification performance, artificial intelligence techniques have been widely used to classify disease data in the last ten years. In this study, a hybrid model based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) was proposed using a two-class data set, which automatically classified CKD. This dataset consisted of thirteen features and one output. If the features showed, CKD was diagnosed. Compared with many well-known machine learning methods, the proposed CNN-LSTM based model obtained a classification accuracy of 99.17%.

Topics & Concepts

Kidney diseaseArtificial intelligenceConvolutional neural networkComputer scienceNauseaMachine learningVomitingDiseaseMedicinePathologyInternal medicineArtificial Intelligence in Healthcare
Diagnosis of Chronic Kidney Disease Based on CNN and LSTM | Litcius