Diagnosing Spinal Abnormalities Using Machine Learning: A Data-Driven Approach

Abstract

Low back pain is a predominant condition which can affects people from different diaspora. The goal of this work is to use machine learning approach to forecast spinal abnormalities. Extratreesclassifier is utilized as a data preprocessing stage to choose the dataset's most prominent features. On a dataset of 310 samples, spinal anomalies are diagnosed using machine learning algorithms like the Support Vector Machine (SVM) and the multilayer perceptron (MLP). The purpose of this study is to determine the most crucial factors that produce backbone abnormalities and to predict them using supervised machine learning techniques. The classification of normal and abnormal spinal patients is investigated in terms of various aspects, including testing and training accuracy, precision, and recall. The observed accuracies for SVM and MLP with 80% training data are 92% and 90%, respectively. The result shows that these models can achieve high accuracy in predicting spinal abnormalities, with the SVM model performing the better. The result suggest that this approach has the potential to significantly improve the efficiency and accuracy of spinal abnormality diagnosis, leading to better patient outcomes.