Dyskinesia Severity Estimation in Patients with Parkinson's Disease Using Wearable Sensors and A Deep LSTM Network

Real-time detection of freezing of gait in Parkinson's disease using multi-head convolutional neural networks and a single inertial sensor

BACKGROUND

Freezing of gait (FOG) is one of the most disabling symptoms of Parkinson's disease (PD), contributing to poor quality of life and increased risk of falls. Wearable sensors represent a valuable means for detecting FOG in the home environment. Moreover, real-time feedback has proven to help reduce the duration of FOG episodes. This work proposes a robust real-time FOG detection algorithm, which is easy to implement in stand-alone devices working in non-supervised conditions.

METHOD

Data from three different data sets were used in this study, with two employed as independent test sets. Acceleration recordings from 118 PD patients and 21 healthy elderly subjects were collected while they performed simulated daily living activities. A single inertial sensor was attached to the waist of each subject. More than 17 h of valid data and a total number of 1110 FOG episodes were analyzed in this study. The implemented algorithm consisted of a multi-head convolutional neural network, which exploited different spatial resolutions in the analysis of inertial data. The architecture and the model parameters were designed to provide optimal performance while reducing computational complexity and testing time.

RESULTS

The developed algorithm demonstrated good to excellent classification performance, with more than 50% (30%) of FOG episodes predicted on average 3.1 s (1.3 s) before the actual onset in the main (independent) data set. Around 50% of FOG was detected with an average delay of 0.8 s (1.1 s) in the main (independent) data set. Moreover, a specificity above 88% (93%) was obtained when testing the algorithm on the main (independent) test set, while 100% specificity was obtained on healthy elderly subjects.

CONCLUSION

The algorithm proved robust, with low computational complexity and processing time, thus paving the way to a real-time implementation in a stand-alone device that can be used in non-supervised environments.

Activity Recognition in Parkinson's Patients from Motion Data Using a CNN Model Trained by Healthy Subjects

Physical activity recognition in patients with Parkinson's Disease (PwPD) is challenging due to the lack of large-enough and good quality motion data for PwPD. A common approach to this obstacle involves the use of models trained on better quality data from healthy patients. Models can struggle to generalize across these domains due to motor complications affecting the movement patterns in PwPD and differences in sensor axes orientations between data. In this paper, we investigated the generalizability of a deep convolutional neural network (CNN) model trained on a young, healthy population to PD, and the role of data augmentation on alleviating sensor position variability. We used two publicly available healthy datasets - PAMAP2 and MHEALTH. Both datasets had sensor placements on the chest, wrist, and ankle with 9 and 10 subjects, respectively. A private PD dataset was utilized as well. The proposed CNN model was trained on PAMAP2 in k-fold cross-validation based on the number of subjects, with and without data augmentation, and tested directly on MHEALTH and PD data. Without data augmentation, the trained model resulted in 48.16% accuracy on MHEALTH and 0% on the PD data when directly applied with no model adaptation techniques. With data augmentation, the accuracies improved to 87.43% and 44.78%, respectively, indicating that the method compensated for the potential sensor placement variations between data. Clinical Relevance- Wearable sensors and machine learning can provide important information about the activity level of PwPD. This information can be used by the treating physician to make appropriate clinical interventions such as rehabilitation to improve quality of life.

Wearable sensors in the diagnosis and study of Parkinson's disease symptoms: a systematic review

Nowadays, there are several diseases which affect different systems of the body, producing changes in the correct functioning of the organism and the people lifestyles. One of them is Parkinson's disease (PD), which is defined as a neurodegenerative disorder provoked by the destruction of dopaminergic neurons in the brain, resulting in a set of motor and non-motor symptoms. As this disease affects principally to ancient people, several researchers have studied different treatments and therapies for stopping neurodegeneration and diminishing symptoms, to improve the quality patients' lives. The most common therapies created for PD are based on pharmacological treatment for controlling the degeneration advance and the physical ones which do not reveal the progress of patients. For this reason, this review paper opens the possibility for using wearable motion capture systems as an option for the control and study of PD. Therefore, it aims to (1) study the different wearable systems used for capture the movements of PD patients and (2) determine which of them bring better results for monitoring and assess PD people. For the analysis, it uses papers based on experiments that prove the functioning of several motion systems in different aspects as monitoring, treatment and diagnose of the disease. As a result, it works with 30 papers which describe the factors mentioned before. Additionally, the paper uses journals and literature review about the pathology, its characteristics and the function of wearable sensors for the correct understanding of the topic.