Discrimination of physiological tremor from pathological tremor using accelerometer and surface EMG signals

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.

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

BACKGROUND

Tremors are involuntary rhythmic movements commonly present in neurological diseases such as Parkinson's disease, essential tremor, and multiple sclerosis. Intention tremor is a subtype associated with lesions in the cerebellum and its connected pathways, and it is a common symptom in diseases associated with cerebellar pathology. While clinicians traditionally use tests to identify tremor type and severity, recent advancements in wearable technology have provided quantifiable ways to measure movement and tremor using motion capture systems, app-based tasks and tools, and physiology-based measurements. However, quantifying intention tremor remains challenging due to its changing nature.

METHODOLOGY & RESULTS

This review examines the current state of upper limb tremor assessment technology and discusses potential directions to further develop new and existing algorithms and sensors to better quantify tremor, specifically intention tremor. A comprehensive search using PubMed and Scopus was performed using keywords related to technologies for tremor assessment. Afterward, screened results were filtered for relevance and eligibility and further classified into technology type. A total of 243 publications were selected for this review and classified according to their type: body function level: movement-based, activity level: task and tool-based, and physiology-based. Furthermore, each publication's methods, purpose, and technology are summarized in the appendix table.

CONCLUSIONS

Our survey suggests a need for more targeted tasks to evaluate intention tremors, including digitized tasks related to intentional movements, neurological and physiological measurements targeting the cerebellum and its pathways, and signal processing techniques that differentiate voluntary from involuntary movement in motion capture systems.

Enhancing Emotion Recognition Using Region-Specific Electroencephalogram Data and Dynamic Functional Connectivity

Recognizing the emotional states of humans through EEG signals are of great significance to the progress of human-computer interaction. The present study aimed to perform automatic recognition of music-evoked emotions through region-specific information and dynamic functional connectivity of EEG signals and a deep learning neural network. EEG signals of 15 healthy volunteers were collected when different emotions (high-valence-arousal vs. low-valence-arousal) were induced by a musical experimental paradigm. Then a sequential backward selection algorithm combining with deep neural network called Xception was proposed to evaluate the effect of different channel combinations on emotion recognition. In addition, we also assessed whether dynamic functional network of frontal cortex, constructed through different trial number, may affect the performance of emotion cognition. Results showed that the binary classification accuracy based on all 30 channels was 70.19%, the accuracy based on all channels located in the frontal region was 71.05%, and the accuracy based on the best channel combination in the frontal region was 76.84%. In addition, we found that the classification performance increased as longer temporal functional network of frontal cortex was constructed as input features. In sum, emotions induced by different musical stimuli can be recognized by our proposed approach though region-specific EEG signals and time-varying functional network of frontal cortex. Our findings could provide a new perspective for the development of EEG-based emotional recognition systems and advance our understanding of the neural mechanism underlying emotion processing.

Wearable sensors during drawing tasks to measure the severity of essential tremor

Commonly used methods to assess the severity of essential tremor (ET) are based on clinical observation and lack objectivity. This study proposes the use of wearable accelerometer sensors for the quantitative assessment of ET. Acceleration data was recorded by inertial measurement unit (IMU) sensors during sketching of Archimedes spirals in 17 ET participants and 18 healthy controls. IMUs were placed at three points (dorsum of hand, posterior forearm, posterior upper arm) of each participant's dominant arm. Movement disorder neurologists who were blinded to clinical information scored ET patients on the Fahn-Tolosa-Marin rating scale (FTM) and conducted phenotyping according to the recent Consensus Statement on the Classification of Tremors. The ratio of power spectral density of acceleration data in 4-12 Hz to 0.5-4 Hz bands and the total duration of the action were inputs to a support vector machine that was trained to classify the ET subtype. Regression analysis was performed to determine the relationship of acceleration and temporal data with the FTM scores. The results show that the sensor located on the forearm had the best classification and regression results, with accuracy of 85.71% for binary classification of ET versus control. There was a moderate to good correlation (r² = 0.561) between FTM and a combination of power spectral density ratio and task time. However, the system could not accurately differentiate ET phenotypes according to the Consensus classification scheme. Potential applications of machine-based assessment of ET using wearable sensors include clinical trials and remote monitoring of patients.

Comprehensive analysis of resting tremor based on acceleration signals of patients with Parkinson's disease

BACKGROUND

Resting tremor is an essential characteristic in patients suffering from Parkinson's disease (PD).

OBJECTIVE

Quantification and monitoring of tremor severity is clinically important to help achieve medication or rehabilitation guidance in daily monitoring.

METHODS

Wrist-worn tri-axial accelerometers were utilized to record the long-term acceleration signals of PD patients with different tremor severities rated by Unified Parkinson's Disease Rating Scale (UPDRS). Based on the extracted features, three kinds of classifiers were used to identify different tremor severities. Statistical tests were further designed for the feature analysis.

RESULTS

The support vector machine (SVM) achieved the best performance with an overall accuracy of 94.84%. Additional feature analysis indicated the validity of the proposed feature combination and revealed the importance of different features in differentiating tremor severities.

CONCLUSION

The present work obtains a high-accuracy classification in tremor severity, which is expected to play a crucial role in PD treatment and symptom monitoring in real life.

Wavelet analysis for early identification of HRV changes in offspring with genetic predisposition to hypertension in Oman

BACKGROUND

Offspring with a genetic predisposition to hypertension may have higher blood pressure (BP) at rest compared with those without a genetic predisposition to hypertension. They are also expected to have a higher sympathetic component in the heart rate variability (HRV) which could be computed with signal processing algorithms.

OBJECTIVE

The purpose of this study is to design a wavelet-based system to estimate the heart rate variability that can be used to detect early cardiovascular changes in offspring with a genetic predisposition to hypertension. Early detection will help in the treatment of those young people. In this work, the relation between the hypertension and the changes in HRV is investigated.

METHODS

The frequency domain and time domain analysis of heart rate variability (HRV) are studied to understand their relationship to the autonomic nervous system in offspring with and without a genetic predisposition to hypertension in Oman at resting state. The wavelet-based soft-decision algorithm is used as the spectral analysis tool to obtain different features from the HRV signal and to select the best performing features for detection of hypertension. The main task is to classify between three categories of subjects: 36 subjects with both normotensive parents (ONT), 22 subjects with single hypertensive parent (OHT1), and 11 subjects with both hypertensive parents (OHT2).

RESULTS

The summation of the power of bands B4 and B5 of the 32 bands HRV wavelet-based spectrum, which is equivalent to the frequency range (0.046875 Hz-0.078125 Hz), is used as a classification factor among OHT2, OHT1, and ONT groups. The efficiency of classification between ONT and OHT2 is 85.10%, and between OHT1 and OHT2 is 81.81%. The result of classifying between (ONT and OHT1 as one group) and OHT2 is 85.50%.

CONCLUSIONS

The work proves that the wavelet-based spectral analysis technique is a successful tool for classifying the three groups of subjects (ONT, OHT1, and OHT2) with different susceptibility for development of hypertension.