Deep Learning Approach to Parkinson's Disease Detection Using Voice Recordings and Convolutional Neural Network Dedicated to Image Classification

A machine learning approach for vocal fold segmentation and disorder classification based on ensemble method

In the healthcare domain, the essential task is to understand and classify diseases affecting the vocal folds (VFs). The accurate identification of VF disease is the key issue in this domain. Integrating VF segmentation and disease classification into a single system is challenging but important for precise diagnostics. Our study addresses this challenge by combining VF illness categorization and VF segmentation into a single integrated system. We utilized two effective ensemble machine learning methods: ensemble EfficientNetV2L-LGBM and ensemble UNet-BiGRU. We utilized the EfficientNetV2L-LGBM model for classification, achieving a training accuracy of 98.88%, validation accuracy of 97.73%, and test accuracy of 97.88%. These exceptional outcomes highlight the system's ability to classify different VF illnesses precisely. In addition, we utilized the UNet-BiGRU model for segmentation, which attained a training accuracy of 92.55%, a validation accuracy of 89.87%, and a significant test accuracy of 91.47%. In the segmentation task, we examined some methods to improve our ability to divide data into segments, resulting in a testing accuracy score of 91.99% and an Intersection over Union (IOU) of 87.46%. These measures demonstrate skill of the model in accurately defining and separating VF. Our system's classification and segmentation results confirm its capacity to effectively identify and segment VF disorders, representing a significant advancement in enhancing diagnostic accuracy and healthcare in this specialized field. This study emphasizes the potential of machine learning to transform the medical field's capacity to categorize VF and segment VF, providing clinicians with a vital instrument to mitigate the profound impact of the condition. Implementing this innovative approach is expected to enhance medical procedures and provide a sense of optimism to those globally affected by VF disease.

AI Detection of Glottic Neoplasm Using Voice Signals, Demographics, and Structured Medical Records

OBJECTIVE

This study investigated whether artificial intelligence (AI) models combining voice signals, demographics, and structured medical records can detect glottic neoplasm from benign voice disorders.

METHODS

We used a primary dataset containing 2-3 s of vowel "ah", demographics, and 26 items of structured medical records (e.g., symptoms, comorbidity, smoking and alcohol consumption, vocal demand) from 60 patients with pathology-proved glottic neoplasm (i.e., squamous cell carcinoma, carcinoma in situ, and dysplasia) and 1940 patients with benign voice disorders. The validation dataset comprised data from 23 patients with glottic neoplasm and 1331 patients with benign disorders. The AI model combined convolutional neural networks, gated recurrent units, and attention layers. We used 10-fold cross-validation (training-validation-testing: 8-1-1) and preserved the percentage between neoplasm and benign disorders in each fold.

RESULTS

Results from the AI model using voice signals reached an area under the ROC curve (AUC) value of 0.631, and additional demographics increased this to 0.807. The highest AUC of 0.878 was achieved when combining voice, demographics, and medical records (sensitivity: 0.783, specificity: 0.816, accuracy: 0.815). External validation yielded an AUC value of 0.785 (voice plus demographics; sensitivity: 0.739, specificity: 0.745, accuracy: 0.745). Subanalysis showed that AI had higher sensitivity but lower specificity than human assessment (p < 0.01). The accuracy of AI detection with additional medical records was comparable with human assessment (82% vs. 83%, p = 0.78).

CONCLUSIONS

Voice signal alone was insufficient for AI differentiation between glottic neoplasm and benign voice disorders, but additional demographics and medical records notably improved AI performance and approximated the prediction accuracy of humans.

LEVEL OF EVIDENCE

NA Laryngoscope, 2024.

Leveraging Deep Learning for Fine-Grained Categorization of Parkinson's Disease Progression Levels through Analysis of Vocal Acoustic Patterns

Speech impairments often emerge as one of the primary indicators of Parkinson's disease (PD), albeit not readily apparent in its early stages. While previous studies focused predominantly on binary PD detection, this research explored the use of deep learning models to automatically classify sustained vowel recordings into healthy controls, mild PD, or severe PD based on motor symptom severity scores. Popular convolutional neural network (CNN) architectures, VGG and ResNet, as well as vision transformers, Swin, were fine-tuned on log mel spectrogram image representations of the segmented voice data. Furthermore, the research investigated the effects of audio segment lengths and specific vowel sounds on the performance of these models. The findings indicated that implementing longer segments yielded better performance. The models showed strong capability in distinguishing PD from healthy subjects, achieving over 95% precision. However, reliably discriminating between mild and severe PD cases remained challenging. The VGG16 achieved the best overall classification performance with 91.8% accuracy and the largest area under the ROC curve. Furthermore, focusing analysis on the vowel /u/ could further improve accuracy to 96%. Applying visualization techniques like Grad-CAM also highlighted how CNN models focused on localized spectrogram regions while transformers attended to more widespread patterns. Overall, this work showed the potential of deep learning for non-invasive screening and monitoring of PD progression from voice recordings, but larger multi-class labeled datasets are needed to further improve severity classification.

A multimodal screening system for elderly neurological diseases based on deep learning

In this paper, we propose a deep-learning-based algorithm for screening neurological diseases. We proposed various examination protocols for screening neurological diseases and collected data by video-recording persons performing these protocols. We converted video data into human landmarks that capture action information with a much smaller data dimension. We also used voice data which are also effective indicators of neurological disorders. We designed a subnetwork for each protocol to extract features from landmarks or voice and a feature aggregator that combines all the information extracted from the protocols to make a final decision. Multitask learning was applied to screen two neurological diseases. To capture meaningful information about these human landmarks and voices, we applied various pre-trained models to extract preliminary features. The spatiotemporal characteristics of landmarks are extracted using a pre-trained graph neural network, and voice features are extracted using a pre-trained time-delay neural network. These extracted high-level features are then passed onto the subnetworks and an additional feature aggregator that are simultaneously trained. We also used various data augmentation techniques to overcome the shortage of data. Using a frame-length staticizer that considers the characteristics of the data, we can capture momentary tremors without wasting information. Finally, we examine the effectiveness of different protocols and different modalities (different body parts and voice) through extensive experiments. The proposed method achieves AUC scores of 0.802 for stroke and 0.780 for Parkinson's disease, which is effective for a screening system.

Towards a Corpus (and Language)-Independent Screening of Parkinson's Disease from Voice and Speech through Domain Adaptation

End-to-end deep learning models have shown promising results for the automatic screening of Parkinson's disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These facts indicate a lack of generalisation or the presence of certain shortcuts in the decision, and also suggest the need for developing new corpus-independent models. In this respect, this work explores the use of domain adversarial training as a viable strategy to develop models that retain their discriminative capacity to detect Parkinson's disease across diverse datasets. The paper presents three deep learning architectures and their domain adversarial counterparts. The models were evaluated with sustained vowels and diadochokinetic recordings extracted from four corpora with different demographics, dialects or languages, and recording conditions. The results showed that the space distribution of the embedding features extracted by the domain adversarial networks exhibits a higher intra-class cohesion. This behaviour is supported by a decrease in the variability and inter-domain divergence computed within each class. The findings suggest that domain adversarial networks are able to learn the common characteristics present in Parkinsonian voice and speech, which are supposed to be corpus, and consequently, language independent. Overall, this effort provides evidence that domain adaptation techniques refine the existing end-to-end deep learning approaches for Parkinson's disease detection from voice and speech, achieving more generalizable models.

A Novel Artificial-Intelligence-Based Approach for Classification of Parkinson's Disease Using Complex and Large Vocal Features

Parkinson's disease (PD) affects a large proportion of elderly people. Symptoms include tremors, slow movement, rigid muscles, and trouble speaking. With the aging of the developed world's population, this number is expected to rise. The early detection of PD and avoiding its severe consequences require a precise and efficient system. Our goal is to create an accurate AI model that can identify PD using human voices. We developed a transformer-based method for detecting PD by retrieving dysphonia measures from a subject's voice recording. It is uncommon to use a neural network (NN)-based solution for tabular vocal characteristics, but it has several advantages over a tree-based approach, including compatibility with continuous learning and the network's potential to be linked with an image/voice encoder for a more accurate multi modal solution, shifting SOTA approach from tree-based to a neural network (NN) is crucial for advancing research in multimodal solutions. Our method outperforms the state of the art (SOTA), namely Gradient-Boosted Decision Trees (GBDTs), by at least 1% AUC, and the precision and recall scores are also improved. We additionally offered an XgBoost-based feature-selection method and a fully connected NN layer technique for including continuous dysphonia measures, in addition to the solution network. We also discussed numerous important discoveries relating to our suggested solution and deep learning (DL) and its application to dysphonia measures, such as how a transformer-based network is more resilient to increased depth compared to a simple MLP network. The performance of the proposed approach and conventional machine learning techniques such as MLP, SVM, and Random Forest (RF) have also been compared. A detailed performance comparison matrix has been added to this article, along with the proposed solution's space and time complexity.

Computed tomography-based COVID-19 triage through a deep neural network using mask-weighted global average pooling

Background

There is an urgent need to find an effective and accurate method for triaging coronavirus disease 2019 (COVID-19) patients from millions or billions of people. Therefore, this study aimed to develop a novel deep-learning approach for COVID-19 triage based on chest computed tomography (CT) images, including normal, pneumonia, and COVID-19 cases.

Methods

A total of 2,809 chest CT scans (1,105 COVID-19, 854 normal, and 850 non-3COVID-19 pneumonia cases) were acquired for this study and classified into the training set (n = 2,329) and test set (n = 480). A U-net-based convolutional neural network was used for lung segmentation, and a mask-weighted global average pooling (GAP) method was proposed for the deep neural network to improve the performance of COVID-19 classification between COVID-19 and normal or common pneumonia cases.

Results

The results for lung segmentation reached a dice value of 96.5% on 30 independent CT scans. The performance of the mask-weighted GAP method achieved the COVID-19 triage with a sensitivity of 96.5% and specificity of 87.8% using the testing dataset. The mask-weighted GAP method demonstrated 0.9% and 2% improvements in sensitivity and specificity, respectively, compared with the normal GAP. In addition, fusion images between the CT images and the highlighted area from the deep learning model using the Grad-CAM method, indicating the lesion region detected using the deep learning method, were drawn and could also be confirmed by radiologists.

Conclusions

This study proposed a mask-weighted GAP-based deep learning method and obtained promising results for COVID-19 triage based on chest CT images. Furthermore, it can be considered a convenient tool to assist doctors in diagnosing COVID-19.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson’s Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson’s disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

Application of Deep Learning Models for Automated Identification of Parkinson's Disease: A Review (2011-2021)

Parkinson’s disease (PD) is the second most common neurodegenerative disorder affecting over 6 million people globally. Although there are symptomatic treatments that can increase the survivability of the disease, there are no curative treatments. The prevalence of PD and disability-adjusted life years continue to increase steadily, leading to a growing burden on patients, their families, society and the economy. Dopaminergic medications can significantly slow down the progression of PD when applied during the early stages. However, these treatments often become less effective with the disease progression. Early diagnosis of PD is crucial for immediate interventions so that the patients can remain self-sufficient for the longest period of time possible. Unfortunately, diagnoses are often late, due to factors such as a global shortage of neurologists skilled in early PD diagnosis. Computer-aided diagnostic (CAD) tools, based on artificial intelligence methods, that can perform automated diagnosis of PD, are gaining attention from healthcare services. In this review, we have identified 63 studies published between January 2011 and July 2021, that proposed deep learning models for an automated diagnosis of PD, using various types of modalities like brain analysis (SPECT, PET, MRI and EEG), and motion symptoms (gait, handwriting, speech and EMG). From these studies, we identify the best performing deep learning model reported for each modality and highlight the current limitations that are hindering the adoption of such CAD tools in healthcare. Finally, we propose new directions to further the studies on deep learning in the automated detection of PD, in the hopes of improving the utility, applicability and impact of such tools to improve early detection of PD globally.

Diagnostic AI Modeling and Pseudo Time Series Profiling of AD and PD Based on Individualized Serum Proteome Data

Background: Parkinson's disease (PD), Alzheimer's disease (AD) are common neurodegenerative disease, while mild cognitive impairment (MCI) may be happened in the early stage of AD or PD. Blood biomarkers are considered to be less invasive, less cost and more convenient, and there is tremendous potential for the diagnosis and prediction of neurodegenerative diseases. As a recently mentioned field, artificial intelligence (AI) is often applied in biology and shows excellent results. In this article, we use AI to model PD, AD, MCI data and analyze the possible connections between them. Method: Human blood protein microarray profiles including 156 CT, 50 MCI, 132 PD, 50 AD samples are collected from Gene Expression Omnibus (GEO). First, we used bioinformatics methods and feature engineering in machine learning to screen important features, constructed artificial neural network (ANN) classifier models based on these features to distinguish samples, and evaluated the model's performance with classification accuracy and Area Under Curve (AUC). Second, we used Ingenuity Pathway Analysis (IPA) methods to analyse the pathways and functions in early stage and late stage samples of different diseases, and potential targets for drug intervention by predicting upstream regulators. Result: We used different classifier to construct the model and finally found that ANN model would outperform the traditional machine learning model. In summary, three different classifiers were constructed to be used in different application scenarios, First, we incorporated 6 indicators, including EPHA2, MRPL19, SGK2, to build a diagnostic model for AD with a test set accuracy of up to 98.07%. Secondly, incorporated 15 indicators such as ERO1LB, FAM73B, IL1RN to build a diagnostic model for PD, with a test set accuracy of 97.05%. Then, 15 indicators such as XG, FGFR3 and CDC37 were incorporated to establish a four-category diagnostic model for both AD and PD, with a test set accuracy of 98.71%. All classifier models have an auc value greater than 0.95. Then, we verified that the constructed feature engineering filtered out fewer important features but contained more information, which helped to build a better model. In addition, by classifying the disease types more carefully into early and late stages of AD, MCI, and PD, respectively, we found that early PD may occur earlier than early MCI. Finally, there are 24 proteins that are both differentially expressed proteins and upstream regulators in the disease group versus the normal group, and these proteins may serve as potential therapeutic targets and targets for subsequent studies. Conclusion: The feature engineering we build allows better extraction of information while reducing the number of features, which may help in subsequent applications. Building a classifier based on blood protein profiles using deep learning methods can achieve better classification performance, and it can help us to diagnose the disease early. Overall, it is important for us to study neurodegenerative diseases from both diagnostic and interventional aspects.

The Role of Neural Network for the Detection of Parkinson's Disease: A Scoping Review

Background: Parkinson’s Disease (PD) is a chronic neurodegenerative disorder that has been ranked second after Alzheimer’s disease worldwide. Early diagnosis of PD is crucial to combat against PD to allow patients to deal with it properly. However, there is no medical test(s) available to diagnose PD conclusively. Therefore, computer-aided diagnosis (CAD) systems offered a better solution to make the necessary data-driven decisions and assist the physician. Numerous studies were conducted to propose CAD to diagnose PD in the early stages. No comprehensive reviews have been conducted to summarize the role of AI tools to combat PD. Objective: The study aimed to explore and summarize the applications of neural networks to diagnose PD. Methods: PRISMA Extension for Scoping Reviews (PRISMA-ScR) was followed to conduct this scoping review. To identify the relevant studies, both medical databases (e.g., PubMed) and technical databases (IEEE) were searched. Three reviewers carried out the study selection and extracted the data from the included studies independently. Then, the narrative approach was adopted to synthesis the extracted data. Results: Out of 1061 studies, 91 studies satisfied the eligibility criteria in this review. About half of the included studies have implemented artificial neural networks to diagnose PD. Numerous studies included focused on the freezing of gait (FoG). Biomedical voice and signal datasets were the most commonly used data types to develop and validate these models. However, MRI- and CT-scan images were also utilized in the included studies. Conclusion: Neural networks play an integral and substantial role in combating PD. Many possible applications of neural networks were identified in this review, however, most of them are limited up to research purposes.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.