Early Detection of Parkinson’s Disease using Deep Learning Models

Nautiyal, Abhijeet (2024) Early Detection of Parkinson’s Disease using Deep Learning Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (834kB) | Preview

Abstract

The study presents the efficient deep learning models such as CNN-LSTM and CNN-GRU architectures to detect Parkinson's disease (PD) at an early stage through voice data. By employing both intelligent audio as well as nonlinear indicators like jitter, shimmer, and harmonic-to-noise ratio (HNR) using Recurrence Period Density Entropy (RPDE) and Detrended Fluctuation Analysis (DFA). The experiments for evaluating the model took place among default and optimized configurations of both CNN-LSTM and CNN-GRUs, with and without early stopping. Results denote that early stopping off considerably ameliorates all metrics and optimized CNN-GRU models (conv=64, gr=75,100) are the leading ones in the tests across all metrics. The CNN-GRU model was able to accurately predict 76.47% of the test data, reaching a F1 score of 77.78% and a balance of recall of 100% and a precision of 63.64%. These results pin down the CNN-GRU model's capacity to generalize and at the same time correctly identify. This study points out the fact that deep learning in voice diagnostics has the potential to become a scalable, non-invasive, and economical solution for early Parkinson's detection. The models that are built in this study offer a firm base for further integration into telehealth systems and thus making early diagnoses and personalized interventions more effective.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Singh, Jaswinder UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry > Neurology. Diseases of the Nervous System.
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2025 15:02
Last Modified:	03 Sep 2025 15:02
URI:	https://norma.ncirl.ie/id/eprint/8758

Actions (login required)

View Item