A study on machine learning-based prediction of cerebellar ataxia using gait analysis and accelerometer data

Chaitra K J 1, *, Subramanya Bhat 2 and Sreenivasa B R 3

1 Department of Information Science and Engineering, Bapuji Institute of Engineering and Technology, Davangere and Research Scholar, Srinivas University, Mukka, Mangalore-574146, India.
2 Department of Computer Science and Engineering, Srinivas University, Mukka, Mangalore-574146, India.
3 Department of Computer Science and Design, Bapuji Institute of Engineering and Technology, Davanagere- 577002, India.
 
Review
International Journal of Science and Research Archive, 2024, 12(02), 873–882.
Article DOI: 10.30574/ijsra.2024.12.2.1331
Publication history: 
Received on 09 June 2024; revised on 16 July 2024; accepted on 19 July 2024
 
Abstract: 
In the neurological field, predicting Cerebellar Ataxia (CA) is based on analyzing gait values of human actions. Analyzing Gait (AoG) can potentially guide effective treatment strategies. This study aimed to create a machine-learning model for predicting AoG using gait patterns indicative of pre-AoG conditions. During the execution of designed walking tasks to provokeAoG, accelerometers were attached to the lower back of 21 subjects as they performed 12 different walking positions to collect acceleration impulses. The participants engaged in walking exercises for one minute at 12 different walking speeds on a split-belt treadmill, ranging from 0.6 to 1.7 m/s in 0.1 m/s increments. The speed sequence was randomized and concealed from the subjects to minimize fatigue effects. Prior research studies have surveyed machine-learning algorithms such as support vector machine (SVM) and k-nearest neighbors (KNN). These algorithms demonstrate strong performance, especially when the dataset is trivial, and the classification is binary. SVM, KNN, decision trees, and XGBoost algorithms were utilized in the proposed study on the CA dataset. Our findings revealed that the AdaBoost algorithm, with its high precision, offers a more precise categorisation of the severity of CA disease, instilling confidence in the study's findings.
 
Keywords: 
Medical imaging; Deep learning; Object detection; Classification; Cervical spine fracture; Convolutional Neural Network (CNN)
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0