Disc Herniation Diagnosis and Binary Classification of Spinal Cord Injury using Ensemble Machine Learning Vote Algorithms

Abstract

Spinal cord injury (SCI) is a complex neurological disorder that often results in a reduced quality of life and considerable functional impairment. Early and accurate detection and classification of SCI cases into injury and non-injury categories is essential for clinical decision-making, rehabilitation and treatment planning. The majority of conventional diagnostic methods rely on medical imaging and expert interpretation, which can be time-consuming and prone to inter-observer variability. To address this challenge, paper provides a binary classification framework for spinal cord injury by combining ensemble machine learning with voting methods. A hard and soft voting ensemble comprises a range of base classifiers, including k-Nearest Neighbors, Support Vector Machines, Probabilistic Neural Networks and Naïve Bayes, to improve prediction accuracy and robustness. In terms of accuracy, precision, recall and F1-score, the ensemble technique outperforms individual models, according to the evaluation of the proposed system on benchmark medical datasets. The results show that ensemble learning with classification accuracy of 96.67% has the potential to be a reliable technique for automated SCI classification, which could help develop intelligent clinical support systems and improve diagnostic processes.