Thomson Multitaper MFCC and PLP voice features for early detection of Parkinson disease

Vocal Feature Changes for Monitoring Parkinson's Disease Progression-A Systematic Review

Background: Parkinson's disease has a significant impact on vocal characteristics and speech patterns, making them potential biomarkers for monitoring disease progression. To effectively utilise these biomarkers, it is essential to understand how they evolve over time as this degenerative disease progresses. Objectives: This review aims to identify the most used vocal features in Parkinson's disease monitoring and to track the temporal changes observed in each feature. Methods: An online database search was conducted to identify studies on voice and speech changes associated with Parkinson's disease progression. The analysis examined the features and their temporal changes to identify potential feature classes and trends. Results: Eighteen features were identified and categorised into three main aspects of speech: articulation, phonation and prosody. While twelve of these features exhibited measurable variations in Parkinsonian voices compared to those of healthy individuals, insights into long-term changes were limited. Conclusions: Vocal features can effectively discriminate Parkinsonian voices and may be used to monitor changes through disease progression. These changes remain underexplored and necessitate more evidence from long-term studies. The additional evidence could provide clinical insights into the disease and enhance the effectiveness of automated voice-based monitoring.

Pre-trained convolutional neural networks identify Parkinson's disease from spectrogram images of voice samples

Machine learning approaches including deep learning models have shown promising performance in the automatic detection of Parkinson's disease. These approaches rely on different types of data with voice recordings being the most used due to the convenient and non-invasive nature of data acquisition. Our group has successfully developed a novel approach that uses convolutional neural network with transfer learning to analyze spectrogram images of the sustained vowel /a/ to identify people with Parkinson's disease. We tested this approach by collecting a dataset of voice recordings via analog telephone lines, which support limited bandwidth. The convolutional neural network with transfer learning approach showed superior performance against conventional machine learning methods that collapse measurements across time to generate feature vectors. This study builds upon our prior results and presents two novel contributions: First, we tested the performance of our approach on a larger voice dataset recorded using smartphones with wide bandwidth. Our results show comparable performance between two datasets generated using different recording platforms despite the differences in most important features resulting from the limited bandwidth of analog telephonic lines. Second, we compared the classification performance achieved using linear-scale and mel-scale spectrogram images and showed a small but statistically significant gain using mel-scale spectrograms.

Pre-trained Convolutional Neural Networks Identify Parkinson's Disease from Spectrogram Images of Voice Samples

Machine learning approaches including deep learning models have shown promising performance in the automatic detection of Parkinson's disease. These approaches rely on different types of data with voice recordings being the most used due to the convenient and non-invasive nature of data acquisition. Our group has successfully developed a novel approach that uses convolutional neural network with transfer learning to analyze spectrogram images of the sustained vowel /a/ to identify people with Parkinson's disease. We tested this approach by collecting a dataset of voice recordings via telephone lines, which have limited bandwidth. This study builds upon our prior results in two major ways: First, we tested the performance of our approach on a larger voice dataset recorded using smartphones with wide bandwidth. Our results show comparable performance between two datasets generated using different recording platforms where we report differences in most important features resulting from the limited bandwidth of telephonic lines. Second, we compared the classification performance achieved using linear-scale and mel-scale spectrogram images and showed a small but statistically significant gain using mel-scale spectrograms. The convolutional neural network with transfer learning approach showed superior performance against conventional machine learning methods that collapse measurements across time to generate feature vectors.

Automated Detection of Parkinson's Disease Based on Multiple Types of Sustained Phonations Using Linear Discriminant Analysis and Genetically Optimized Neural Network

Objective: Parkinson’s disease (PD) is a serious neurodegenerative disorder. It is reported that most of PD patients have voice impairments. But these voice impairments are not perceptible to common listeners. Therefore, different machine learning methods have been developed for automated PD detection. However, these methods either lack generalization and clinically significant classification performance or face the problem of subject overlap. Methods: To overcome the problems discussed above, we attempt to develop a hybrid intelligent system that can automatically perform acoustic analysis of voice signals in order to detect PD. The proposed intelligent system uses linear discriminant analysis (LDA) for dimensionality reduction and genetic algorithm (GA) for hyperparameters optimization of neural network (NN) which is used as a predictive model. Moreover, to avoid subject overlap, we use leave one subject out (LOSO) validation. Results: The proposed method namely LDA-NN-GA is evaluated in numerical experiments on multiple types of sustained phonations data in terms of accuracy, sensitivity, specificity, and Matthew correlation coefficient. It achieves classification accuracy of 95% on training database and 100% on testing database using all the extracted features. However, as the dataset is imbalanced in terms of gender, thus, to obtain unbiased results, we eliminated the gender dependent features and obtained accuracy of 80% for training database and 82.14% for testing database, which seems to be more unbiased results. Conclusion: Compared with the previous machine learning methods, the proposed LDA-NN-GA method shows better performance and lower complexity. Clinical Impact: The experimental results suggest that the proposed automated diagnostic system has the potential to classify PD patients from healthy subjects. Additionally, in future the proposed method can also be exploited for prodromal and differential diagnosis, which are considered challenging tasks.