Effect of Deep Brain Stimulation on Cerebellar Tremor Compared to Non-Cerebellar Tremor Using a Wearable Device in a Patient With Multiple Sclerosis: Case Report

Tremor of the upper extremity is a significant cause of disability in some patients with multiple sclerosis (MS). The MS tremor is complex because it contains an ataxic intentional tremor component due to the involvement of the cerebellum and cerebellar outflow pathways by MS plaques, which makes the MS tremor, in general, less responsive to medications or deep brain stimulation (DBS) than those associated with essential tremor or Parkinson's disease. The cerebellar component has been thought to be the main reason for making DBS less effective, although it is not clear whether it is due to the lack of suppression of the ataxic tremor by DBS or else. The goal of this study was to clarify the effect of DBS on cerebellar tremor compared to non-cerebellar tremor in a patient with MS. By wearing an accelerometer on the index finger of each hand, we were able to quantitatively characterize kinetic tremor by frequency and amplitude, with cerebellar ataxia component on one hand and that without cerebellar component on the other hand, at the beginning and end of the hand movement approaching a target at DBS Off and On status. We found that cerebellar tremor surprisingly had as good a response to DBS as the tremor without a cerebellar component, but the function control on cerebellar tremor was not as good due to its distal oscillation, which made the amplitude of tremor increasingly greater as it approached the target. This explains why cerebellar tremor or MS tremor with cerebellar component has a poor functional transformation even with a good percentage of tremor control. This case study provides a better understanding of the effect of DBS on cerebellar tremor and MS tremor by using a wearable device, which could help future studies improve patient selection and outcome prediction for DBS treatment of this disabling tremor.

Application of Embedded Smart Wearable Device Monitoring in Joint Cartilage Injury and Rehabilitation Training

Joint injuries cause varying degrees of damage to joint cartilage. The purpose of this paper is to study the application of embedded smart wearable device monitoring in articular cartilage injury and rehabilitation training. This paper studies what an embedded system is and what a smart wearable device is and also introduces the rehabilitation training method of articular cartilage injury. We cited an embedded matching cost algorithm and an improved AD-Census. The joint cartilage damage and rehabilitation training are monitored. Finally, we introduced the types of smart wearable devices and different types of application fields. The results of this paper show that, after an articular cartilage injury, the joint function significantly recovers using the staged exercise rehabilitation training based on embedded smart wearable device monitoring. We concluded that, from 2013 to 2020, smart wearable devices are very promising in the medical field. In 2020, the value will reach 20 million US dollars.

The Views and Needs of People With Parkinson Disease Regarding Wearable Devices for Disease Monitoring: Mixed Methods Exploration

Background Wearable devices can diagnose, monitor, and manage neurological disorders such as Parkinson disease. With a growing number of wearable devices, it is no longer a case of whether a wearable device can measure Parkinson disease motor symptoms, but rather which features suit the user. Concurrent with continued device development, it is important to generate insights on the nuanced needs of the user in the modern era of wearable device capabilities. Objective This study aims to understand the views and needs of people with Parkinson disease regarding wearable devices for disease monitoring and management. Methods This study used a mixed method parallel design, wherein survey and focus groups were concurrently conducted with people living with Parkinson disease in Munster, Ireland. Surveys and focus group schedules were developed with input from people with Parkinson disease. The survey included questions about technology use, wearable device knowledge, and Likert items about potential device features and capabilities. The focus group participants were purposively sampled for variation in age (all were aged >50 years) and sex. The discussions concerned user priorities, perceived benefits of wearable devices, and preferred features. Simple descriptive statistics represented the survey data. The focus groups analyzed common themes using a qualitative thematic approach. The survey and focus group analyses occurred separately, and results were evaluated using a narrative approach. Results Overall, 32 surveys were completed by individuals with Parkinson disease. Four semistructured focus groups were held with 24 people with Parkinson disease. Overall, the participants were positive about wearable devices and their perceived benefits in the management of symptoms, especially those of motor dexterity. Wearable devices should demonstrate clinical usefulness and be user-friendly and comfortable. Participants tended to see wearable devices mainly in providing data for health care professionals rather than providing feedback for themselves, although this was also important. Barriers to use included poor hand function, average technology confidence, and potential costs. It was felt that wearable device design that considered the user would ensure better compliance and adoption. Conclusions Wearable devices that allow remote monitoring and assessment could improve health care access for patients living remotely or are unable to travel. COVID-19 has increased the use of remotely delivered health care; therefore, future integration of technology with health care will be crucial. Wearable device designers should be aware of the variability in Parkinson disease symptoms and the unique needs of users. Special consideration should be given to Parkinson disease–related health barriers and the users’ confidence with technology. In this context, a user-centered design approach that includes people with Parkinson disease in the design of technology will likely be rewarded with improved user engagement and the adoption of and compliance with wearable devices, potentially leading to more accurate disease management, including self-management.

Wearable Device for Observation of Physical Activity with the Purpose of Patient Monitoring Due to COVID-19

In late 2019, a new genre of coronavirus (COVID-19) was first identified in humans in Wuhan, China. In addition to this, COVID-19 spreads through droplets, so quarantine is necessary to halt the spread and to recover physically. This modern urgency creates a critical challenge for the latest technologies to detect and monitor potential patients of this new disease. In this vein, the Internet of Things (IoT) contributes to solving such problems. This paper proposed a wearable device that utilizes real-time monitoring to detect body temperature and ambient conditions. Moreover, the system automatically alerts the concerned person using this device. The alert is transmitted when the body exceeds the allowed temperature threshold. To achieve this, we developed an algorithm that detects physical exercise named “Continuous Displacement Algorithm” based on an accelerometer to see whether a potential temperature rise can be attributed to physical activity. The people responsible for the person in quarantine can then connect via nRF Connect or a similar central application to acquire an accurate picture of the person’s condition. This experiment included an Arduino Nano BLE 33 Sense which contains several other sensors like a 9-axis IMU, several types of temperature, and ambient and other sensors equipped. This device successfully managed to measure wrist temperature at all states, ranging from 32 °C initially to 39 °C, providing better battery autonomy than other similar devices, lasting over 12 h, with fast charging capabilities (500 mA), and utilizing the BLE 5.0 protocol for data wireless data transmission and low power consumption. Furthermore, a 1D Convolutional Neural Network (CNN) was employed to classify whether the user is feverish while considering the physical activity status. The results obtained from the 1D CNN illustrated the manner in which it can be leveraged to acquire insight regarding the health of the users in the setting of the COVID-19 pandemic.

Sleep Stage Classification For Medical Purposes: Machine Learning Evaluation For Imbalanced Data

Background: Sleep is commonly associated with physical and mental health status. Sleep quality can be determined from the dynamic of sleep stages during the night. Data from the wearable device can potentially be used as predictors to classify the sleep stage. Robust Machine Learning (ML) model is needed to learn the pattern within wearable data to be associated with the sleep-wake classification, especially to handle the imbalanced proportion between wake and sleep stages. In this study, we incorporated a publicy available dataset consists of three features captured from a consumer wearable device and the labelled sleep stages from a polysomnogram. We implemented Random Forest, Support Vector Machine , Extreme Gradiet Boosting Tree, Densed Neural Network (DNN), and Long Short-Term Memory (LSTM), complemented by three strategies to handle the imbalanced data problem. Results: In total, we included more than 24,815 rows of preprocessed data from 31 samples. The proportion of minority-majority data is 1:10. In classifying this extreme imbalanced data, the DNN model was found to have the best performance compared to the previous best model, which is based on basic Multi-Layer Perceptron. Our best model successfully achieved a 12% higher specificity score (prediction score for minority class) and 1% improvement on the sensitivity score (prediction score for majority class) by including all features in the model. This achievement was affected by the implementation of custom class weight and oversampling strategy. In contrast, when we only used two features, XGB achieved a specificity improvement only by 1%, while keeping the sensitivity at the same level.Conclusions: The non-linear operation within the DNN model could successfully learn the hidden pattern from the combination of three features. Additionally, the class weight parameter avoided the model ignoring the minority class by giving more weight for this class in the loss function. The feature engineering process seemed to obscure the time-series characteristics within the data. This is why LSTM, as one of the best methods for time-series data, failed to perform well in this classification task.