Data-driven diagnosis of spinal abnormalities using feature selection and machine learning algorithms

• Published in: PloS one Vol. 15; no. 2; p. e0228422
• Main Authors: Raihan-Al-Masud, Md, Mondal, M. Rubaiyat Hossain
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 06.02.2020; Public Library of Science (PLoS)
• Subjects: Abnormalities; Accuracy; Algorithms; Analysis; Back pain; Bagging; Biology and Life Sciences; Classification; Computer and Information Sciences; Data mining; Datasets; Datasets as Topic - statistics & numerical data; Diagnosis; Diagnosis, Computer-Assisted - methods; Diagnosis, Differential; Feature extraction; Humans; Image Interpretation, Computer-Assisted - methods; Information technology; Learning algorithms; Libraries; Logistic Models; Machine Learning; Medical diagnosis; Medicine and Health Sciences; Methods; Physical Sciences; Posture - physiology; Predictive Value of Tests; Principal components analysis; Recall; Regression analysis; Reproducibility of Results; Research and Analysis Methods; Spinal Diseases - diagnosis; Spinal Diseases - epidemiology; Spine - abnormalities; Spine - diagnostic imaging; Support Vector Machine; Support vector machines; Training; Taiwan; Bangladesh
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0228422

This paper focuses on the application of machine learning algorithms for predicting spinal abnormalities. As a data preprocessing step, univariate feature selection as a filter based feature selection, and principal component analysis (PCA) as a feature extraction algorithm are considered. A number of machine learning approaches namely support vector machine (SVM), logistic regression (LR), bagging ensemble methods are considered for the diagnosis of spinal abnormality. The SVM, LR, bagging SVM and bagging LR models are applied on a dataset of 310 samples publicly available in Kaggle repository. The performance of classification of abnormal and normal spinal patients is evaluated in terms of a number of factors including training and testing accuracy, recall, and miss rate. The classifier models are also evaluated by optimizing the kernel parameters, and by using the results of receiver operating characteristic (ROC) and precision-recall curves. Results indicate that when 78% data are used for training, the observed training accuracies for SVM, LR, bagging SVM and bagging LR are 86.30%, 85.47%, 86.72% and 85.06%, respectively. On the other hand, the accuracies for the test dataset for SVM, LR, bagging SVM and bagging LR are the same being 86.96%. However, bagging SVM is the most attractive as it has a higher recall value and a lower miss rate compared to others. Hence, bagging SVM is suitable for the classification of spinal patients when applied on the most five important features of spinal samples.