Diagnosis of vertebral column pathologies using concatenated resampling with machine learning algorithms

Abstract

Medical diagnosis through the classification of biomedical attributes is one of the exponentially growing fields in bioinformatics. Although a large number of approaches have been presented in the past, wide use and superior performance of the machine learning (ML) methods in medical diagnosis necessitates significant consideration for automatic diagnostic methods. This study proposes a novel approach called concatenated resampling (CR) to increase the efficacy of traditional ML algorithms. The performance is analyzed leveraging four ML approaches like tree-based ensemble approaches, and linear machine learning approach for automatic diagnosis of inter-vertebral pathologies with increased. Besides, undersampling, over-sampling, and proposed CR techniques have been applied to unbalanced training dataset to analyze the impact of these techniques on the accuracy of each of the classification model. Extensive experiments have been conducted to make comparisons among different classification models using several metrics including accuracy, precision, recall, and F1 score. Comparative analysis has been performed on the experimental results to identify the best performing classifier along with the application of the re-sampling technique. The results show that the extra tree classifier achieves an accuracy of 0.99 in association with the proposed CR technique.

Using deep transfer learning to detect scoliosis and spondylolisthesis from x-ray images

“…Table 10 shows a comparison to the related work in the literature in terms of performance. Although the related literature produced high accuracy values, these approaches [ 1 , 12 , 17 ] require extensive and error-prone measurement of the biomechanical parameters that indicated the specific disease case, which is not required by our approach. To our knowledge, no other study has included deep learning in the classification of scoliosis vs spondylolisthesis vs normal X-ray images.…”

“…The research landscape using machine learning (ML) and artificial intelligence (AI) followed a similar path to that of the medical literature by designing algorithms that can automatically extract the aforementioned biomechanical markers of disease from medical images [ 8 – 11 ], which can be utilized by the specialists for diagnosis. Furthermore, these parameters can be utilized as features for AI-based diagnosis by classifying images into healthy and different disease classes [ 1 , 12 , 13 ]. However, the accuracy of such methods is either low [ 14 – 16 ] or highly dependent on the accuracy of measurement of the biomechanical parameters [ 1 , 12 , 17 ].…”

“…Furthermore, these parameters can be utilized as features for AI-based diagnosis by classifying images into healthy and different disease classes [ 1 , 12 , 13 ]. However, the accuracy of such methods is either low [ 14 – 16 ] or highly dependent on the accuracy of measurement of the biomechanical parameters [ 1 , 12 , 17 ]. In contrast, the work in this paper does not require any explicit measurements of any parameters.…”

“…They achieved an 85.9% maximum accuracy. This methodology of processing X-ray images to extract disease features and using various classical (i.e., non-deep) machine learning algorithms (e.g., multilayer perceptron) and processing techniques (e.g., clustering) was taken by several related works [ 1 , 12 , 25 , 26 ]. However, such explicit extraction of measurements and features may complicate usability and can be error prone [ 27 ].…”

Vector mosquito image classification using novel RIFS feature selection and machine learning models for disease epidemiology

“…Feature selection is the process of finding the most appropriate features of a given dataset ( Reshi, 2021 ). It is beneficial for the improvement of classification accuracy as well as computational speed.…”