A modified weighted mean of vectors optimizer for Chronic Kidney disease classification

Essam H Houssein; Awny Sayed

doi:10.1016/j.compbiomed.2023.106691

A modified weighted mean of vectors optimizer for Chronic Kidney disease classification

Comput Biol Med. 2023 Mar:155:106691. doi: 10.1016/j.compbiomed.2023.106691. Epub 2023 Feb 16.

Authors

Essam H Houssein¹, Awny Sayed²

Affiliations

¹ Faculty of Computers and Information, Minia University, Minia, Egypt. Electronic address: essam.halim@mu.edu.eg.
² Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia. Electronic address: asayyed@kau.edu.sa.

PMID: 36805229
DOI: 10.1016/j.compbiomed.2023.106691

Abstract

Chronic kidney Disease (CKD), also known as chronic renal disease, is an illness that affects the majority of adults and is defined by a progressive decrease in kidney function over time, particularly in those with diabetes and high blood pressure. Metaheuristic (MH) algorithms based machine learning classifiers have become reliable for medical treatment. The weIghted meaN oF vectOrs (INFO) is a recently developed MH but suffers from a fall into local optimal and slow convergence speed. Therefore, to improve INFO, a modified INFO (mINFO) with two enhancement strategies has been developed. The developed variant utilizes the Opposition-Based Learning (OBL) to improve the local search ability to avoid trapping into the local optimum, and the Dynamic Candidate Solution (DCS) is used to overcome the premature convergence problem in INFO and achieve the appropriate balance between exploration and exploitation ability. The performance of the proposed mINFO based on the k-Nearest Neighbor (kNN) classifier is evaluated on the complex CEC'22 test suite and applied to predict Chronic Kidney Disease (CKD) on datasets extracted from UCI. The statistical results revealed the superiority of mINFO compared with several well-known MH algorithms, including the Harris Hawks Optimization (HHO), the Hunger Games Search (HGS) algorithm, the Moth-Flame Optimization (MFO) algorithm, the Whale Optimization Algorithm (WOA), the Sine Cosine Algorithm (SCA), the Gradient-Based Optimizer (GBO), and the original INFO algorithm. According to our knowledge, this paper is the first of its sort to try employing the proposed mINFO for solving the CEC'22 test suite. Furthermore, the experimental results of mINFO-kNN for classifying two CKD datasets demonstrated its superiority with an overall classification accuracy of 93.17% on two CKD datasets over other competitors.

Keywords: Chronic Kidney Disease; Classification; Dynamic candidate solution; Opposition-based learning; Weighted mean of vectors algorithm.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Cluster Analysis
Humans
Hypertension*
Machine Learning
Renal Insufficiency, Chronic*