Automatic evaluation of the Nine-Hole Peg Test in multiple sclerosis patients using machine learning models

• Published in: Biomedical signal processing and control Vol. 92; p. 106128
• Main Authors: Balaceanu, A., Puertas, I., Alonso de Leciñana, M., Tallón, A., Gutiérrez-Tenorio, Á., Vargas, P., Torres, G., Gutiérrez, Á.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-06-2024
• Subjects: Convolutional neural network; Deep learning; DeepLabCut; Machine learning; Multiple sclerosis; Nine-Hole Peg Test; Deep learning; Multiple sclerosis; Nine-Hole Peg Test; DeepLabCut; Convolutional neural network; Machine learning
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2024.106128

Neurological damage in Multiple Sclerosis (MS) affects the motor, sensory, visual, cognitive and sphincteric systems, resulting in different degrees of disability. Upper limb dysfunction is a core deficit affecting MS patients. However, since upper limb function impairment is not properly recorded in the Expanded Disability Status Scale (EDSS) for MS, other tests have been developed in the last decades. The Nine Hole Peg Test (9HPT) is widely considered a gold standard metric for manual dexterity. Unfortunately, its quantification strongly depends on the subjectivity of each clinician.
The aim of this work is to standardize the measurement process of the 9HPT. Instead of a human interpretation of the time needed to complete the exercise, this paper aims to objectively extract multiple kinematic information of the subject’s hand (period, velocity, time). This information is used to detect the presence and the state of the disease more accurately and classify the patients automatically. The manuscript describes a developed framework to automate and objectivize the 9HPT. The framework evaluates the performance of different Machine Learning models and Artificial Neural Networks on MS diagnosis. The built system analyzes videos of subjects performing the 9HPT, extracts the hand’s pose using Convolutional Neural Networks, acquires the hand’s kinematic features and classifies the severity of the disease using Machine Learning algorithms. For the framework validation, two classification approaches are proposed. The first one is a binary classification problem, separating the subjects between control and patients. The second one is a multiclass classification problem, where the patients are separated into three different classes based on the severity assessed by the clinicians. A technical validation has been implemented with an accuracy of up 96.67% for the binary classification and 92.22% for the multiclass classification.