Action tremor features discovery for essential tremor and Parkinson's disease with explainable multilayer BiLSTM.

The tremors of Parkinson's disease (PD) and essential tremor (ET) are known to have overlapping characteristics that make it complicated for clinicians to distinguish them. While deep learning is robust in detecting features unnoticeable to humans, an opaque trained model is impractical in clinical scenarios as coincidental correlations in the training data may be used by the model to make classifications, which may result in misdiagnosis. This work aims to overcome the aforementioned challenge of deep learning models by introducing a multilayer BiLSTM network with explainable AI (XAI) that can better explain tremulous characteristics and quantify the respective discovered important regions in tremor differentiation. The proposed network classifies PD, ET, and normal tremors during drinking actions and derives the contribution from tremor characteristics, (i.e., time, frequency, amplitude, and actions) utilized in the classification task. The analysis shows that the XAI-BiLSTM marks the regions with high tremor amplitude as important in classification, which is verified by a high correlation between relevance distribution and tremor displacement amplitude. The XAI-BiLSTM discovered that the transition phases from arm resting to lifting (during the drinking cycle) is the most important action to classify tremors. Additionally, the XAI-BiLSTM reveals frequency ranges that only contribute to the classification of one tremor class, which may be the potential distinctive feature to overcome the overlapping frequencies problem. By revealing critical timing and frequency patterns unique to PD and ET tremors, this proposed XAI-BiLSTM model enables clinicians to make more informed classifications, potentially reducing misclassification rates and improving treatment outcomes.

Design and fabrication of a novel passive hand tremor attenuator.

Parkinson's disease is most highly recognised by tremors of the hands that occur in those afflicted with the disease. Though the symptoms of Parkinson's disease involving motor function begin with very slight tremors of the hands, they further develop into issues such as difficulty swallowing, severe postural problems and extremely limited mobility. In this study, a method of reducing these tremors that appear during the early stages of the disease is developed by creating a wearable passive device that reduces vibrations of the hand and arm through the use of magnetic actuators. The proposed wearable technology has surpassed other known alternatives in selected testing scenarios while possessing a light weight of only 120 grams.

Safety and Tolerability of a Wearable, Vibrotactile Stimulation Device for Parkinson's Disease.

Background: Resting tremor is a cardinal symptom of Parkinson's disease (PD) that contributes to the physical, emotional, and economic burden of the disease. Objective: The goal of this study was to investigate the safety, tolerability, and preliminary effectiveness of a novel wearable vibrotactile stimulation device on resting tremor in individuals with PD. Methods: Using a randomized cross-over design, subjects received two different vibrotactile stimulation paradigms (high amplitude patterned and low amplitude continuous) on two separate laboratory visits. On each visit, resting tremor was video recorded for 10 min at baseline and while the vibrotactile stimulation was applied. Tremor severity was scored by a blinded clinician. Results: Both vibration paradigms were well safe and well tolerated and resulted in a reduction in resting tremor severity with a moderate effect size (n = 44, p < 0.001, r = 0.37-0.54). There was no significant difference between the two vibration paradigms (p = 0.14). Conclusion: Short durations of vibrotactile stimulation delivered via wearable devices were safe and well tolerated and may attenuate resting tremor severity in individuals with PD. The sample size as well as the potential preliminary effectiveness revealed by two arms of the study could not eliminate the potential for a placebo effect.

Vim line technique thalamotomy for Parkinson tremor: Case series.

INTRODUCTION: The ventral intermediate (Vim) nucleus of the thalamus is difficult to identify even with 3 T magnetic resonance imaging. Stereotactic Vim thalamotomy is a usual procedure to control Parkinson tremor. Successful relieving of the tremor depends on the accuracy of defining the Vim location. PRESENTATION OF CASES: Three patients with Parkinson tremor were subjected to stereotactic thalamotomy using the Vim line technique (VLT) so as to precisely determine the Vim location. All patients showed good results, with improved tremors, as indicated by the UPDRS score, without any complications. DISCUSSION: The precise targeting of the Vim nucleus is crucial importance for the successful Vim thalamotomy. Various method has been developed to determine Vim location. Atlas based and Guiot's technique routinely used by neurosurgeon. VLT is a new technique that has been developed to determine the Vim location on MRI. CONCLUSION: VLT is useful for the determination of the Vim location. However, further research is warranted to prove its effectiveness.

Mixed-reality assistive robotic power chair simulator for Parkinson's tremor testing.

This note describes the development of a mixed-reality assistive robotic wheel chair simulator for testing of Parkinson's tremor mitigation and operator assistance. It consists of a power chair (PCh), roller dynamometer, head mounted virtual reality (VR) display, computer with VR game engine, and microcontroller to interface the PCh and computer. Unlike past VR PCh simulators, both a tremor notch filter and basic collision avoidance is implemented. Further, the simulator identifies the Parkinson's tremor frequency. Operator performance is assessed using deviations from a given route and velocity profile. To demonstrate the simulator's operation, an operator with Parkinson's tremor drove the PCh down two 20 m long hallways connected by a 90∘ turn while operating data was collected. Results show less variation in velocity tracking with use of the notch filter than without it; route tracking was nearly the same. Advantages of the simulator compared to a wholly physical approach are low cost, improved safety, portability, small footprint, and environments and robotic features are virtual.

Rehabilitation of the Parkinson's tremor by using robust adaptive sliding mode controller: a simulation study.

One of the efficient methods in controlling the Parkinson's tremor is Deep Brain Stimulation (DBS) therapy. The stimulation of Basal Ganglia (BG) by DBS brings no feedback though the existence of feedback reduces the additional stimulatory signal delivered to the brain. So this study offers a new adaptive architecture of a closed-loop control system in which two areas of BG are stimulated simultaneously to decrease the following three indicators: hand tremor, the level of a delivered stimulation signal in the disease condition, and the level of a delivered stimulation signal in health condition to the disease condition. One area (STN: subthalamic nucleus) is stimulated with an adaptive sliding mode controller and the other area (GPi: Globus Pallidus internal) with partial state feedback controller. The simulation results of stimulating two areas of BG showed satisfactory performance.

Vib-bracelet: a passive absorber for attenuating forearm tremor.

Tremor is a rhythmic, involuntary, oscillatory movement of a limb produced by alternating contractions of reciprocally innervated muscles. More than 4% of the population over 40 years old suffer from tremor. There is no cure for most tremors, and while psychological therapy is sometimes helpful, tremors are usually treated with either medication or invasive surgery including thalamotomy and deep brain stimulation. Both medications and surgery may have adverse effects, and thus, there is a growing interest in developing non-invasive vibration attenuation devices. This paper presents a passive absorber device for attenuating pronation/supination tremor, dubbed Vib-bracelet. It is based on the principles of dynamic vibration absorption and is tuned to the frequency of the tremor. Prototypes were manufactured and tested on a mechanical model of the human forearm. Simulations and experiments demonstrate the efficiency of the device in attenuating vibrations in the range of 4-6 Hz, which is the range of frequency of observed tremor, with maximum amplitude attenuation of 85%.

A Classification System for Assessment and Home Monitoring of Tremor in Patients with Parkinson's Disease.

BACKGROUND: Tremor is one of the most common symptoms of Parkinson's disease (PD), which is widely being used in the diagnosis procedure. Accurate estimation of PD tremor based on Unified PD Rating Scale (UPDRS) provides aid for physicians in prescription and home monitoring. This article presents a robust design of a classification system to estimate PD patient's hand tremors and the results of the proposed system as compared to the UPDRS. METHODS: A smartphone accelerometer sensor is used for accurate and noninvasive data acquisition. We applied short-time Fourier transform to time series data of 52 PD patients. Features were extracted based on the severity of PD patients' hand tremor. The wrapper method was employed to determine the most discriminative subset of the extracted features. Four different classifiers were implemented for achieving best possible accuracy in the estimation of PD hand tremor based on UPDRS. Of the four tested classifiers, the Naive Bayesian approach proved to be the most accurate one. RESULTS: The classification result for the assessment of PD tremor achieved close to 100% accuracy by selecting an optimum combination of extracted features of the acceleration signal acquired. For home health-care monitoring, the proposed algorithm was also implemented on a cost-effective embedded system equipped with a microcontroller, and the implemented classification algorithm achieved 93.8% average accuracy. CONCLUSIONS: The accuracy result of both implemented systems on MATLAB and microcontroller is acceptable in comparison with the previous works.

Discrimination of Parkinsonian tremor from essential tremor using statistical signal characterization of the spectrum of accelerometer signal.

A new technique for discrimination of Parkinson tremor from essential tremor is presented in this paper. This technique is based on Statistical Signal Characterization (SSC) of the spectrum of the accelerometer signal. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. Two sets of data are used. The training set, which consists of 21 essential-tremor (ET) subjects and 19 Parkinson-disease (PD) subjects, is used to obtain the threshold value of the classification factor differentiating between the two subjects. The test data set, which consists of 20 ET and 20 PD subjects, is used to test the technique and evaluate its performance. Three of twelve newly derived SSC parameters show good discrimination results. Specific results of those three parameters on training data and test data are shown in detail. A linear combination of the effects of those parameters on the discrimination results is also included. A total discrimination accuracy of 90% is obtained.