Anomaly Detection in Human Disease: A Hybrid Approach Using GWO-SVM for Gene Selection

Abstract

The goal is to facilitate early disease detection. A Grey Wolf Optimizer (GWO) was implemented in the proposed method, a meta-heuristic algorithm known for its efficiency in reducing computational time for high-dimensional data. This optimization technique simplifies the problem by breaking it into manageable subsets. Following this, a filter approach, such as analysis of variance (ANOVA), was used to select informative genes from the reduced data. A Support Vector Machine (SVM) was also used as a classifier to select genes that efficiently categorize anomalous cases, serving as a fitness function—this combined approach, referred to as GWO-SVM, and aimed to reduce computational time while improving accuracy. The experimental results demonstrated that the proposed method achieved an accuracy rate of 96.46% in predicting disease detection, representing a significant improvement compared to previous methods. These findings underscore the potential of the GWO-SVM approach in advancing anomaly detection in human diseases.