PHTNet: Characterization and Deep Mining of Involuntary Pathological Hand Tremor using Recurrent Neural Network Models

Explainable artificial intelligence for searching frequency characteristics in Parkinson's disease tremor

The distinction between Parkinson's disease (PD) and essential tremor (ET) tremors is subtle, posing challenges in differentiation. To accurately classify the PD and ET, BiLSTM-based recurrent neural networks are employed to classify between normal patients (N), PD patients, and ET patients using accelerometry data on their lower arm (L), hand (H), and upper arm (U) as inputs. The trained recurrent neural network (RNN) has reached 80% accuracy. The neural network is analyzed using layer-wise relevance propagation (LRP) to understand the internal workings of the neural network. A novel explainable AI method, called LRP-based approximate linear weights (ALW), is introduced to identify the similarities in relevance when assigning the class scores in the neural network. The ALW functions as a 2D kernel that linearly transforms the input data directly into the class scores, which significantly reduces the complexity of analyzing the neural network. This new classification method reconstructs the neural network's original function, achieving a 73% PD and ET tremor classification accuracy. By analyzing the ALWs, the correlation between each input and the class can also be determined. Then, the differentiating features can be subsequently identified. Since the input is preprocessed using short-time Fourier transform (STFT), the differences between the magnitude of tremor frequencies ranging from 3 to 30 Hz in the mean N, PD, and ET subjects are successfully identified. Aside from matching the current medical knowledge on frequency content in the tremors, the differentiating features also provide insights about frequency contents in the tremors in other frequency bands and body parts.

A Computerized Analysis with Machine Learning Techniques for the Diagnosis of Parkinson's Disease: Past Studies and Future Perspectives

According to the World Health Organization (WHO), Parkinson's disease (PD) is a neurodegenerative disease of the brain that causes motor symptoms including slower movement, rigidity, tremor, and imbalance in addition to other problems like Alzheimer's disease (AD), psychiatric problems, insomnia, anxiety, and sensory abnormalities. Techniques including artificial intelligence (AI), machine learning (ML), and deep learning (DL) have been established for the classification of PD and normal controls (NC) with similar therapeutic appearances in order to address these problems and improve the diagnostic procedure for PD. In this article, we examine a literature survey of research articles published up to September 2022 in order to present an in-depth analysis of the use of datasets, various modalities, experimental setups, and architectures that have been applied in the diagnosis of subjective disease. This analysis includes a total of 217 research publications with a list of the various datasets, methodologies, and features. These findings suggest that ML/DL methods and novel biomarkers hold promising results for application in medical decision-making, leading to a more methodical and thorough detection of PD. Finally, we highlight the challenges and provide appropriate recommendations on selecting approaches that might be used for subgrouping and connection analysis with structural magnetic resonance imaging (sMRI), DaTSCAN, and single-photon emission computerized tomography (SPECT) data for future Parkinson's research.

Using Deep Learning for Task and Tremor Type Classification in People with Parkinson's Disease

Hand tremor is one of the dominating symptoms of Parkinson's disease (PD), which significantly limits activities of daily living. Along with medications, wearable devices have been proposed to suppress tremor. However, suppressing tremor without interfering with voluntary motion remains challenging and improvements are needed. The main goal of this work was to design algorithms for the automatic identification of the tremor type and voluntary motions, using only surface electromyography (sEMG) data. Towards this goal, a bidirectional long short-term memory (BiLSTM) algorithm was implemented that uses sEMG data to identify the motion and tremor type of people living with PD when performing a task. Moreover, in order to automate the training process, hyperparamter selection was performed using a regularized evolutionary algorithm. The results show that the accuracy of task classification among 15 people living with PD was 84±8%, and the accuracy of tremor classification was 88±5%. Both models performed significantly above chance levels (20% and 33% for task and tremor classification, respectively). Thus, it was concluded that the trained models, based on using purely sEMG signals, could successfully identify the task and tremor types.

Real-Time Voluntary Motion Prediction and Parkinson's Tremor Reduction Using Deep Neural Networks

Wearable tremor suppression devices (WTSD) have been considered as a viable solution to manage parkinsonian tremor. WTSDs showed their ability to improve the quality of life of individuals suffering from parkinsonian tremor, by helping them to perform activities of daily living (ADL). Since parkinsonian tremor has been shown to be nonstationary, nonlinear, and stochastic in nature, the performance of the tremor models used by WTSDs is affected by their inability to adapt to the nonlinear behaviour of tremor. Another drawback that the models have is their limitation to estimate or predict one step ahead, which introduces delay when used in real time with WTSDs, which compromises performance. To address these issues, this work proposes a deep neural network model that learns the correlations and nonlinearities of tremor and voluntary motion, and is capable of multi-step prediction with minimal delay. A generalized model that is task and user-independent is presented. The model achieved an average estimation percentage accuracy of 99.2%. The average future voluntary motion prediction percentage accuracy with 10, 20, 50, and 100 steps ahead was 97.0%, 94.0%, 91.6%, and 89.9%, respectively, with prediction time as low as 1.5 ms for 100 steps ahead. The proposed model also achieved an average of 93.8% ± 1.5% in tremor reduction when it was tested in an experimental setup in real time. The tremor reduction showed an improvement of 25% over the Weighted Fourier Linear Combiner (WFLC), an estimator commonly used with WTSDs.

A deep explainable artificial intelligent framework for neurological disorders discrimination

Pathological hand tremor (PHT) is a common symptom of Parkinson's disease (PD) and essential tremor (ET), which affects manual targeting, motor coordination, and movement kinetics. Effective treatment and management of the symptoms relies on the correct and in-time diagnosis of the affected individuals, where the characteristics of PHT serve as an imperative metric for this purpose. Due to the overlapping features of the corresponding symptoms, however, a high level of expertise and specialized diagnostic methodologies are required to correctly distinguish PD from ET. In this work, we propose the data-driven [Formula: see text] model, which processes the kinematics of the hand in the affected individuals and classifies the patients into PD or ET. [Formula: see text] is trained over 90 hours of hand motion signals consisting of 250 tremor assessments from 81 patients, recorded at the London Movement Disorders Centre, ON, Canada. The [Formula: see text] outperforms its state-of-the-art counterparts achieving exceptional differential diagnosis accuracy of [Formula: see text]. In addition, using the explainability and interpretability measures for machine learning models, clinically viable and statistically significant insights on how the data-driven model discriminates between the two groups of patients are achieved.