Voice Biomarkers for Parkinson's Disease Prediction Using Machine Learning Models with Improved Feature Reduction Techniques
Journal Title: Journal of Data Science and Intelligent Systems - Year 2023, Vol 1, Issue 2
Abstract
As a chronic and life-threatening disease, Parkinson’s disease (PD) causes people to become rigid and inactive and have shaky voices. There is an argument that current PD detection techniques are ineffective due to their high latency and low accuracy. To enhance the accuracy of PD identification, voice recordings were used as biomarkers in conjunction with the synthetic minority oversampling technique (SMOTE). Three machine learning (ML) models namely support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF) were adopted to calculate the prediction accuracy. By applying an unsupervised dimensional reduction method, the generated model eliminates redundant data and speeds up training and testing. Model performance is estimated with three parameters, including accuracy, F1 score, and area under the curve (AUC) values. Experimental outcomes suggested that the RF model outperforms other models with 97.4% of classification accuracy. This type of research aims to analyze patient voice recordings to determine the disease severity.
Authors and Affiliations
Nalini Chintalapudi, Venkata Rao Dhulipalla, Gopi Battineni, Ciro Rucco, Francesco Amenta
Keywords
Related Articles
- EP ID EP724853
- DOI 10.47852/bonviewJDSIS3202831
- Views 63
- Downloads 0
Federated-Based Deep Reinforcement Learning (Fed-DRL) for Energy Management in a Distributive Wireless Network
Studies on developing future generation wireless systems are expected to support increased infrastructure development and device subscriptions with densely deployed base stations (BSs). Economically, decreasing BS energy...
Dynamic Neural Network Architecture Design for Predicting Remaining Useful Life of Dynamic Processes
The prediction of remaining useful life is critical in predictive health management. This is done to reduce the expenses associated with operation and maintenance by avoiding errors and failures in dynamic processes. Rec...
Data Science and Applications
This paper investigates the significance of data science as an indispensable instrument for decision-making across multiple domains. The study examines the history, concepts, methods, and applications of data science, as...
Intra-annual National Statistical Accounts Based on Machine Learning Algorithm
The methods used for forecasting financial series are based on the concept that a pattern can be identified in the data and distinguished from randomness by smoothing past values. This smoothing process eliminates random...
A Study of the Effects of the Shape Parameter and Type of Data Points Locations on the Accuracy of the Hermite-Based Symmetric Approach Using Positive Definite Radial Kernels
Theoretical approximation ideas served as the driving force behind the research. one can see that the shape parameter's behavior is driven by the kind of problem and the analytical standards that are applied. the primary...