Predicting Parkinson’s Disease Using Machine Learning with Voice Parameters and Handwriting Images

Sep 17, 2026

Uploaded by Ophelia

Most studies have not addressed geriatric diseases despite rapid medical advances. Parkinson’s disease is a neurodegenerative disorder that gradually worsens, affecting movement and motor control while limiting daily activities. Over 95% of patients report voice impairment and micrographic disability. This work uses machine learning with modern image processing to predict PD, combining Random Forest and K-nearest Neighbour, achieving 95% accuracy using UCI voice parameters data and Kaggle handwriting images.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Keywords

Introduction

Methodology

Description of Dataset for Voice Parameters

Description of Dataset for Handwriting Images

Deployment

Predicting Parkinson’s Disease Using Machine Learning with Voice Parameters and Handwriting Images Pruthvi H C 1*, UshaSree R 1*, Harprith Kaur2 1Dayananda Sagar Academy of Technology & Management, Karnataka, India 2Faculty of Data Science and Information Technology, INTI International University, Malaysia *[Email:](Email: pruthvi.shetty38@gmail.com)[ pruthvi.shetty38@gmail.com](Email: pruthvi.shetty38@gmail.com), [ushasree19832000@gmail.com](ushasree19832000@gmail.com) Abstract Most studies have failed to focus on geriatric diseases in the present era of quick advancement in medical science. Diseases like Parkinson’s display their symptoms at a later stage and make a complete recovery almost doubtful. Parkinson’s disease is a neurodegenerative disorder that affects movement and motor control systems. It is named after Dr. James Parkinson, the first person affected by this disease. Parkinson’s slowly worsens over time, leading to a variety of syndromes that can impact a person’s daily life activities. More than 95% of Parkinson’s Disease (PD) patients stated that they have exhibited voice impairment and micrographic disability. This model takes advantage of both advanced machine learning algorithms and modern image processing techniques, resulting in effective and efficient prediction PD. To further enhance the accuracy of the model, we have incorporated additional algorithms such as Random Forest and K-nearest Neighbour. Random forest classifier has a detection accuracy of 92%and sensitivity of 0.95% . The performance has been assessed with a reliable dataset from the University of California Irvine Machine Learning repository for voice parameters and a dataset from Kaggle for Handwriting images which includes wavy images and spiral images. Our proposed model has achieved the highest accuracy of 95% which outperformed the previous model or experiment on the same dataset. Keywords Parkinson's Disease, ML Models, Advanced Detection Approach, Enhanced Feature Introduction Parkinson’s disease is a common neurological disorder affecting muscle movement in the body. It affects movements, voice, and posture leading to tremors, muscle rigidity, and bradykinesia. This may lead to a variety of problems, including difficulty in concentrating and completing tasks, movement disorders, and sleep problems. Dopamine deficiency syndrome can be associated with depression, anxiety, and other mental health issues. While the progress of the syndrome may vary from patient to patient, balance problems and quivering are the most prevalent side effects of dopaminergic neuron death. Unfortunately, there is no cure or medicine for PD, hence Patients with Parkinson’s depend on early detection and tailored treatments to slow the progress of the disease. These signs include hoarseness, a sore throat, and changes in the voice. If the signs worsen, other symptoms such as difficulty breathing and pain when swallowing can manifest. It is important to seek immediate medical attention if any of these symptoms appear. This makes it easier to diagnose and treat patients who are geographically isolated or lack access to healthcare. Vocal impairment can also be monitored remotely over some time, enabling doctors to track progress and adjust treatments as needed medicine. Patients need not travel physically to a doctor instead; they can record audio using phones and perform a simple test at home. Common voice modulation symptoms include hoarseness and persistent depressive disorder. Because of its complex nature, there is no recovery from Parkinson’s till today. However, early detection followed by the right medication can reduce the tremors and imbalance symptoms in patients, enabling them to lead a normal life. This paper focuses on early detection through voice parameters and handwriting images using ML models. Our model results show that the Random Forest classifier model has an accuracy of 92% when trained on 22 attributes of the MDVP au

FAQs

Why is early detection important for Parkinson’s disease?

Parkinson’s progresses over time and there is no cure, so early detection enables timely, tailored treatments that can reduce tremors and imbalance symptoms and help patients maintain a more normal life.

Which data sources are used for the voice and handwriting parts of the model?

Voice parameters are evaluated using a dataset from the University of California Irvine Machine Learning repository, while handwriting images are taken from Kaggle, including spiral and wavy patterns.

What machine learning methods improve prediction performance in this approach?

The study incorporates Random Forest and K-nearest Neighbour, and reports that the Random Forest classifier reaches 92% accuracy on voice features and the overall proposed model reaches up to 95% accuracy on the stated datasets.

Sep 17, 2026

Uploaded by Ophelia