Machine learning approaches to identify significant features for the diagnosis and prognosis of chronic kidney disease

Nosin Ibna Mahbub, Md Imran Hasan, Md Martuza Ahamad, Sakifa Aktar, Mohammad Ali Moni

Research output: Book chapter/Published conference paperConference paperpeer-review

3 Citations (Scopus)

Abstract

Chronic kidney disease (CKD)is a long-term disease in which the kidneys are failed and needed dialysis or kidney transplantation in the severe stage. Thirty-seven million people in the United States have CKD, and millions more are at risk. Early diagnosis can help prevent kidney disease from progressing to kidney failure. The aim of this study is to make CKD diagnosis predictions based on symptoms or characteristics seen in a particular case, regardless of whether the stage is acute or chronic, and to classify the most important features that contribute to CKD. We illustrate machine learning methods to predict chronic kidney disease using clinical evidence and statistical tests to identify the most important reasons for CKD. Seven machine learning methods are explored including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree, Random Forest, Naive Bayes, and XGBboost classifiers to predict CKD and two statistical tests including Student's T-test and chi-squared test to identify most significant features. The results showed that the tree-based classifier performs best in the kidney diagnostic procedure with accuracy of 100%. In addition,hemoglobin, packed cell volume, specific gravity, red bloodcell countsand albumin are the most predictive biomarker for CKD.

Original languageEnglish
Title of host publication2022 International Conference on Innovations in Science, Engineering and Technology
Subtitle of host publicationICISET 2022
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages312-317
Number of pages6
ISBN (Electronic)9781665483971
ISBN (Print)9781665483988 (Print on demand)
DOIs
Publication statusPublished - 2022
Event2022 International Conference on Innovations in Science, Engineering and Technology, ICISET 2022 - International Islamic University Chittagong, Chittagong, Bangladesh
Duration: 25 Feb 202228 Feb 2022
https://ieeexplore.ieee.org/xpl/conhome/9775773/proceeding (Proceedings)
https://iciset2022.iiuc.ac.bd/ (Conference website)
https://web.archive.org/web/20220320072907/https://iciset.iiuc.ac.bd/wp-content/uploads/2021/03/Call-for-Papers-6.jpg (Call for papers)

Publication series

Name2022 International Conference on Innovations in Science, Engineering and Technology, ICISET 2022

Conference

Conference2022 International Conference on Innovations in Science, Engineering and Technology, ICISET 2022
Abbreviated titleTechnology for Sustainable Development
Country/TerritoryBangladesh
CityChittagong
Period25/02/2228/02/22
OtherInternational Conference on Innovations in Science, Engineering and Technology 2022 (ICISET 2022) is a multidisciplinary international conference organized by the Faculty of Science and Engineering (FSE) in association with the Center for Research and Publication (CRP) of International Islamic University Chittagong (IIUC). This is the third time ICISET is going to take place where the first two rounds of this immensely successful conference were held in 2016 and 2018. The objective of ICISET 2022 is to create a unique opportunity for scientists, engineers, professionals, researchers, and students to present their latest research findings and experiences in the areas of Computer Science and Engineering, Electrical Engineering, Electronics, Telecommunication Engineering, Pharmacy, Environmental Science and other relevant areas of Science, Engineering, and Technology. The vision of ICISET is to become a platform of collaboration for the researchers from home and abroad where practitioners from the industry will engage with the researchers from academia for generating innovative solutions to contemporary challenges.
Internet address

Fingerprint

Dive into the research topics of 'Machine learning approaches to identify significant features for the diagnosis and prognosis of chronic kidney disease'. Together they form a unique fingerprint.

Cite this