Application of machine learning models to classify Parkinson disease patients using accelerometer - Early detection study

Aug 4, 2026

Upload by Eden

Parkinson’s disease (PD) significantly impacts mobility, making early detection essential for better treatment outcomes. This study applies advanced machine learning to accelerometer data from motion-tracking sensors that capture movement behaviors and related PD symptoms. Using algorithms including support vector machines, neural networks, and random forest, the research builds an integrated ensemble model to reconcile conflicting predictions from individual classifiers and reduce uncertainty. The dataset comes from the University of Zaragoza Hospital and includes diagnosed and undiagnosed participants, enabling classification between PD and non-PD groups. Results show improved performance, with the best ensemble reaching 65.69% accuracy, 73.5% specificity, and 71.17% precision.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Introduction

Background

INTERNATIONAL JOURNAL OF SCIENCE FOR GLOBAL SUSTAINABILITY (A PUBLICATION OF FACULTY OF SCIENCE, FEDERAL UNIVERSITY GUSAU, NIGERIA) | Application of machine learning models to classify
Parkinson disease patients using accelerometer 1Ameenu Abdulhameed Rabiu, 2Ismail Ahmad Ibrahim, 3Buhari Bashir and 4 Salihu Abdullahi Audu
1No. 70 Kundilar Gandu, Zoo Road Housing Estate, Kano.
2No. 13 Dutsinma Street Tudun Wada, Kaduna.
3No. 8 Funtua Crescent K/Kaura New Layout, Katsina.
4Department of Computer Science, Nasarawa State University, Nigeria
Corresponding Author’[s Email:](s Email: abdulgiz@nsuk.edu.ng)[ ](s Email: abdulgiz@nsuk.edu.ng)[abdulgiz@nsuk.edu.ng](s Email: abdulgiz@nsuk.edu.ng)
Received on: April, 2025 Revised and Accepted on: May, 2025 Published on: July, 2025 | | --- | | ABSTRACT
Parkinson’s disease (PD) greatly affects mobility, emphasizing the critical need for early detection to optimize treatment outcomes. This study explores the application of advanced machine learning techniques to analyse data collected from specialized motion tracking sensors known as accelerometers. These sensors monitor individual’s movements and symptoms associated with Parkinson’s disease, with a primary focus on comprehending the unique movement patterns and related symptoms prevalent in those affected by this condition. This research leverages the capabilities of machine learning, employing diverse algorithms such as support vector machines, neural networks, and random forest. Through an integrated approach, the study aims to construct a robust ensemble model capable of synthesizing insights from these techniques. The dataset utilized originates from the University of Zaragoza Hospital, encompassing a diverse range of participants, including individuals both diagnosed and undiagnosed with Parkinson’s disease. This diversity ensures a comprehensive exploration of various movement patterns and symptoms among heterogeneous individuals. The primary objective revolves around precise differentiation between individuals affected by Parkinson’s disease and those who are not. To achieve this, the study adopts an ensemble model strategically designed to reconcile conflicting predictions from individual classifiers. This methodological approach seeks consensus by aggregating multiple classifier opinions, thereby minimizing uncertainties arising from divergent predictions. The outcomes of this study are particularly significant, with the ensemble model demonstrating superior performance over traditional machine learning models. The bestperforming ensemble model, as identified through comparative analysis, achieved an impressive accuracy of 65.69%, specificity of 73.5%, and precision of 71.17% . These metrics underscore the potential of ensemble classifiers in enhancing diagnostic precision, thereby contributing to the early detection and continuous monitoring of parkinson disease.
Keywords: Parkinson disease, advanced machine learning, support vector machines, neural networks, random forest | 1.0 INTRODUCTION 1.1 Background Parkinson’s Disease (PD) is a neurodegenerative disorder that significantly affects millions of people worldwide. It is characterized by a gradual decline in motor functions, evidenced by symptoms such as tremors, stiffness, and slowed movement, which greatly affect an individual’s quality of life. Beyond these motor symptoms, PD can also lead to cognitive impairments and mood disorders, adding layers of complexity to its diagnosis and treatment. The variation in symptom manifestation and response to treatment among patients further complicates the clinical approach to PD. Traditionally, PD diagnosis relies on clinical evaluations, including medical history and neurological exams. While these methods are invaluable, their subjective nature can lead to inconsistent diagnoses. This paper is inspired by the promising capabilities of machine learning, particularly its application to objective da

FAQs

What is the main goal of this study on Parkinson’s disease?

The study aims to accurately differentiate individuals with Parkinson’s disease from those without using accelerometer-based movement data and machine learning models.

Which machine learning algorithms are used in the research?

The research employs support vector machines, neural networks, and random forest, and integrates them through an ensemble approach.

Why does the paper emphasize ensemble classifiers?

Ensemble classifiers combine opinions from multiple individual models to reach consensus, improving robustness and reducing uncertainties from conflicting predictions.

Aug 4, 2026

Upload by Eden