Parkinson's Disease Prediction Using Machine Learning Techniques

Parkinson's disease, a progressive neurological disorder, presents a spectrum of symptoms primarily affecting motor functions such as tremors and coordination challenges. Beyond the physical symptoms, it encroaches upon cognitive and emotional domains, often leading to depression and cognitive...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS) pp. 1 - 7
Main Authors Harry, M., Vijula, V., Princess, J. Pearly
Format Conference Proceeding
LanguageEnglish
Published IEEE 28.06.2024
Subjects
Accuracy
Convolutional Neural Network
Data models
Feature extraction
Feed Forward Neural Network
Motors
Parkinson's disease
Parkinson's Disease Detection
Predictive models
Tabnet
Training
Online AccessGet full text

Cover

More Information
Summary:Parkinson's disease, a progressive neurological disorder, presents a spectrum of symptoms primarily affecting motor functions such as tremors and coordination challenges. Beyond the physical symptoms, it encroaches upon cognitive and emotional domains, often leading to depression and cognitive decline. A recent breakthrough in diagnosis involves a voice-based model that detects subtle speech irregularities linked to Parkinson's. This innovative approach relies on a dataset comprising 24 columns capturing diverse symptoms, from motor impairments to non-motor indicators. This dataset serves as a crucial foundation for training and validating the model's accuracy. By analyzing individual symptom profiles, this multidimensional approach facilitates early detection and tailored intervention, essential for effectively managing the disease's progression. Integrating advanced technology with comprehensive clinical data represents a significant step forward in Parkinson's disease management, promising personalized care and improved outcomes for patients by addressing their unique needs and challenges. Furthermore, the integration of voice analysis adds a non-invasive dimension to Parkinson's diagnosis, potentially improving accessibility to screening methods. This approach holds promise for reaching underserved populations who may face barriers to traditional diagnostic procedures. By enhancing early detection and intervention, it offers the possibility of mitigating the disease's impact and improving overall patient outcomes.
DOI:10.1109/ICITEICS61368.2024.10625564