Diagnosis of Parkinson's Disease using Principal Component Analysis and Machine Learning algorithms with Vocal Features

Rao, D. Venkata; Sucharitha, Y; Venkatesh, D; Mahamthy, K; Yasin, SK MD

doi:10.1109/icscds53736.2022.9760962

Cited by 14 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consistent with the literature (16, 32,33,42), our ndings a rm the superior performance of SVM models, aligning with the trends in PD diagnosis using voice analysis. Only a few studies showed different results (43) (44). Our model's accuracy and F1 scores for SVM, GB, and RF are comparable or superior to those reported in more extensive studies (38,45).…”

Section: Discussionsupporting

confidence: 63%

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comprehensive Study Across Diverse Datasets

Neto

2023

SSRN Journal

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 63%

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comprehensive Study Across Diverse Datasets

Neto

2023

SSRN Journal

View full text Add to dashboard Cite

“…To compact and eliminate irrelevant features, a dimensionality reduction technique called principal component analysis (PCA) was applied (Jollife and Cadima 2016). An algorithm for diagnosing PD based on PCA and machine learning algorithms using vocal features reported 95% of accuracy (Rao et al 2022). Further, the synthetic minority oversampling technique (SMOTE) (Alberto Fernández et al 2018) resampling was employed to balance the class distribution and broaden the sample range.…”

Section: Introductionmentioning

confidence: 99%

Voice Biomarkers for Parkinson's Disease Prediction Using Machine Learning Models with Improved Feature Reduction Techniques

Dhulipalla

Battineni

Ruocco

et al. 2023

JDSIS

View full text Add to dashboard Cite

As a chronic and life-threatening disease, Parkinson's disease (PD) causes people to become rigid, 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) was 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 analyse patient voice recordings to determine the disease severity.

show abstract

“…As for the parameters tested, for the DNN, we explored the number of neurons in the rst dense layer (16,32,64), learning rates (0.001, 0.01, 0.05), dropout rates (0.1, 0.3, 0.5), batch sizes (8,16,32), epochs (30,70), activation functions (sigmoid, tanh, relu, and swish) and optimizers (Adaptive Moment Estimation (Adam), Stochastic Gradient Descent and Adamax, a variant of Adam based on the in nity norm). For the GB classi er, we adjusted several hyperparameters: learning rate (0.1, 0.2, 0.3), max depth (5), max features (sqrt, log2), min samples leaf (10, 20), min samples split (20,30), n_estimators (200, 300), and subsample (0.8, 0.9).…”

Section: Machine Learning Analysismentioning

confidence: 99%

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comparative Study Across Three Datasets

Neto

2024

Preprint

View full text Add to dashboard Cite

Objective: This study evaluates the efficacy of voice analysis combined with machine learning (ML) techniques in enabling early, noninvasive diagnosis of Parkinson's Disease (PD). Methods: Voice data, phonation of the vowel 'a', from three distinct datasets (two from the UCI ML Repository and one from figshare) for a total of 432 participants (278 PD patients) were analyzed. We employed four ML models - Artificial Neural Networks (ANN), Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM) - alongside two ensemble methods (soft voting classifier - EVC and stacking method - ESM). The models underwent 50 iterations of evaluation, involving various data splits and 10-fold cross-validation. Comparative analysis was done using one-way ANOVA followed by Bonferroni post-hoc corrections. Results: The ESM, SVM, and GB models emerged as the top performers, demonstrating superior performance across metrics including accuracy, sensitivity, specificity, precision, F1 score, and ROC AUC. Despite data heterogeneity and variable selection limitations, the models showed high values for all metrics. Conclusion: Machine learning integration with voice analysis, mainly through ESM, SVM, and GB, is promising for early PD diagnosis. Using multi-source data and a large sample size enhances our findings' validity, reliability, and generalizability. Significance: This study underscores the potential of noninvasive voice analysis combined with advanced ML to revolutionize early PD detection and pave the way for cost-effective, scalable diagnostic tools.

show abstract

Diagnosis of Parkinson's Disease using Principal Component Analysis and Machine Learning algorithms with Vocal Features

Cited by 14 publications

References 8 publications

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comprehensive Study Across Diverse Datasets

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comprehensive Study Across Diverse Datasets

Voice Biomarkers for Parkinson's Disease Prediction Using Machine Learning Models with Improved Feature Reduction Techniques

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comparative Study Across Three Datasets

Contact Info

Product

Resources

About