Novelty Detection using Deep Normative Modeling for IMU-Based Abnormal Movement Monitoring in Parkinson’s Disease and Autism Spectrum Disorders (original) (raw)
Related papers
Signal Processing
Autism Spectrum Disorders are associated with atypical movements, of which stereotypical motor movements (SMMs) interfere with learning and social interaction. The automatic SMM detection using inertial measurement units (IMU) remains complex due to the strong intra and inter-subject variability, especially when handcrafted features are extracted from the signal. We propose a new application of the deep learning to facilitate automatic SMM detection using multiaxis IMUs. We use a convolutional neural network (CNN) to learn a discriminative feature space from raw data. We show how the CNN can be used for parameter transfer learning to enhance the detection rate on longitudinal data. We also combine the long short-term memory (LSTM) with CNN to model the temporal patterns in a sequence of multi-axis signals. Further, we employ ensemble learning to combine multiple LSTM learners into a more robust SMM detector. Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors. These findings provide a significant step toward accurate SMM detection in real-time scenarios.
Deep Learning for Daily Monitoring of Parkinson’s Disease Outside the Clinic Using Wearable Sensors
Sensors
Now that wearable sensors have become more commonplace, it is possible to monitor individual healthcare-related activity outside the clinic, unleashing potential for early detection of events in diseases such as Parkinson’s disease (PD). However, the unsupervised and “open world” nature of this type of data collection make such applications difficult to develop. In this proof-of-concept study, we used inertial sensor data from Verily Study Watches worn by individuals for up to 23 h per day over several months to distinguish between seven subjects with PD and four without. Since motor-related PD symptoms such as bradykinesia and gait abnormalities typically present when a PD subject is walking, we initially used human activity recognition (HAR) techniques to identify walk-like activity in the unconstrained, unlabeled data. We then used these “walk-like” events to train one-dimensional convolutional neural networks (1D-CNNs) to determine the presence of PD. We report classification ac...
Gait Anomaly Detection of Subjects with Parkinson’s Disease Using a Deep Time Series-based Approach
IEEE Access
Parkinson's disease (PD) is a cognitive degenerative disorder of the central nervous system that mainly affects the motor system. The earliest symptoms evidence a general deficit of coordination and an unsteady gait. Current approaches for the evaluation and assessment of gait disturbances in PD have proved to be expensive, inconvenient and ineffective in the detection of anomalous walking patterns. In this paper, we address these issues by defining a deep time series-based approach for the detection of anomalous walking patterns in the gait dynamics of elderly people by analyzing the acceleration values of their movements. The results show a training accuracy and testing accuracy of over 90% with an accuracy improvement of 4.28% in comparison with related works.
2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016
The development of wearable sensors has opened the door for long-term assessment of movement disorders. However, there is still a need for developing methods suitable to monitor motor symptoms in and outside the clinic. The purpose of this paper was to investigate deep learning as a method for this monitoring. Deep learning recently broke records in speech and image classification, but it has not been fully investigated as a potential approach to analyze wearable sensor data. We collected data from ten patients with idiopathic Parkinson's disease using inertial measurement units. Several motor tasks were expert-labeled and used for classification. We specifically focused on the detection of bradykinesia. For this, we compared standard machine learning pipelines with deep learning based on convolutional neural networks. Our results showed that deep learning outperformed other state-of-the-art machine learning algorithms by at least 4.6 % in terms of classification rate. We contribute a discussion of the advantages and disadvantages of deep learning for sensor-based movement assessment and conclude that deep learning is a promising method for this field.
Scientific Reports
Parkinson’s Disease (PD) is the second most common neurodegenerative disorder, affecting more than 1% of the population above 60 years old with both motor and non-motor symptoms of escalating severity as it progresses. Since it cannot be cured, treatment options focus on the improvement of PD symptoms. In fact, evidence suggests that early PD intervention has the potential to slow down symptom progression and improve the general quality of life in the long term. However, the initial motor symptoms are usually very subtle and, as a result, patients seek medical assistance only when their condition has substantially deteriorated; thus, missing the opportunity for an improved clinical outcome. This situation highlights the need for accessible tools that can screen for early motor PD symptoms and alert individuals to act accordingly. Here we show that PD and its motor symptoms can unobtrusively be detected from the combination of accelerometer and touchscreen typing data that are passiv...
Computational Intelligence and Neuroscience
Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by persistent difficulties including repetitive patterns of behavior known as stereotypical motor movements (SMM). So far, several techniques have been implemented to track and identify SMMs. In this context, we propose a deep learning approach for SMM recognition, namely, convolutional neural networks (CNN) in time and frequency-domains. To solve the intrasubject SMM variability, we propose a robust CNN model for SMM detection within subjects, whose parameters are set according to a proper analysis of SMM signals, thereby outperforming state-of-the-art SMM classification works. And, to solve the intersubject variability, we propose a global, fast, and light-weight framework for SMM detection across subjects which combines a knowledge transfer technique with an SVM classifier, therefore resolving the “real-life” medical issue associated with the lack of supervised SMMs per testing subject in particular. We...
Granular Motor State Monitoring of Free Living Parkinson's Disease Patients via Deep Learning
ArXiv, 2019
Parkinson's disease (PD) is the second most common neurodegenerative disease worldwide and affects around 1% of the (60+ years old) elderly population in industrial nations. More than 80% of PD patients suffer from motor symptoms, which could be well addressed if a personalized medication schedule and dosage could be administered to them. However, such personalized medication schedule requires a continuous, objective and precise measurement of motor symptoms experienced by the patients during their regular daily activities. In this work, we propose the use of a wrist-worn smart-watch, which is equipped with 3D motion sensors, for estimating the motor fluctuation severity of PD patients in a free-living environment. We introduce a novel network architecture, a post-training scheme and a custom loss function that accounts for label noise to improve the results of our previous work in this domain and to establish a novel benchmark for nine-level PD motor state estimation.
Sensors
Remote assessment of the gait of older adults (OAs) during daily living using wrist-worn sensors has the potential to augment clinical care and mobility research. However, hand movements can degrade gait detection from wrist-sensor recordings. To address this challenge, we developed an anomaly detection algorithm and compared its performance to four previously published gait detection algorithms. Multiday accelerometer recordings from a wrist-worn and lower-back sensor (i.e., the “gold-standard” reference) were obtained in 30 OAs, 60% with Parkinson’s disease (PD). The area under the receiver operator curve (AUC) and the area under the precision–recall curve (AUPRC) were used to evaluate the performance of the algorithms. The anomaly detection algorithm obtained AUCs of 0.80 and 0.74 for OAs and PD, respectively, but AUPRCs of 0.23 and 0.31 for OAs and PD, respectively. The best performing detection algorithm, a deep convolutional neural network (DCNN), exhibited high AUCs (i.e., 0....
International journal of advanced research in computer science, 2024
A group of neurological disorders that manifests in a wide range of motor and cognitive symptoms, Parkinson's Disease (PD) ranks second among those affecting older adults. Many people mistakenly believe that PD symptoms are caused by other conditions, such as essential tremor or natural aging. There may not be a cure for PD, but there are numerous medications that can help with symptoms. Since gait impairment is a prominent and early sign of PD in a clinical context, doctors typically use visual observations to analyse gait abnormalities as one of many manifestations to determine the severity of PD. Nevertheless, therapists' reliance on their own knowledge and judgment makes gait examination a difficult and subjective process. Extracting useful gait features from various input signals for gait analysis has recently been used Deep Learning (DL) models. Intermediate Medical Unit (IMU) patients with movement problems may benefit from a quick and clinically relevant evaluation of gait abnormalities performed automatically utilizing DL algorithms. Using gait analysis, this study provides a comprehensive overview of various DL frameworks that have been created for the purpose of PD prediction and categorization. At the outset, In the first part of the study, various PD prediction and classification systems that have been developed by various researchers and that rely on DL algorithms via gait analysis are reviewed briefly. To find a better way to identify and categorize the PD, we next undertake a comparative analysis to learn about the shortcomings of those algorithms.
Cueing of Parkinson's Disease Patients by Standard Smart Devices and Deep Learning Approach
Acta Polytechnica Hungarica, 2023
Parkinson's disease is one of the most common neurological diseases. The patients suffer from different symptoms, e.g., tremor, bradykinesia, or walk gait disorders. One of the gait disorders which affects Parkinson's disease patients is freezing of gait, which shows as a sudden gait interruption without the ability to take the next step. It is hard to manage this symptom by medication. However, there are ways to address this symptom by applying different visual or vibration aids. This work presents a system for automatic detection and cue of freezing of gait events provided by ordinary smart devices. We used a deep learning approach to detect such events automatically. The test results and the doctors' opinions on the practical experience with the patients suggest the benefits of the provided solution.