Novelty Detection using Deep Normative Modeling for IMU-Based Abnormal Movement Monitoring in Parkinson's Disease and Autism Spectrum Disorders

Prediction of Freezing of Gait in Parkinson's disease based on multi-channel time-series neural network

Freezing of Gait (FOG) is a noticeable symptom of Parkinson's disease, like being stuck in place and increasing the risk of falls. The wearable multi-channel sensor system is an efficient method to predict and monitor the FOG, thus warning the wearer to avoid falls and improving the quality of life. However, the existing approaches for the prediction of FOG mainly focus on a single sensor system and cannot handle the interference between multi-channel wearable sensors. Hence, we propose a novel multi-channel time-series neural network (MCT-Net) approach to merge multi-channel gait features into a comprehensive prediction framework, alerting patients to FOG symptoms in advance. Owing to the causal distributed convolution, MCT-Net is a real-time method available to give optimal prediction earlier and implemented in remote devices. Moreover, intra-channel and inter-channel transformers of MCT-Net extract and integrate different sensor position features into a unified deep learning model. Compared with four other state-of-the-art FOG prediction baselines, the proposed MCT-Net obtains 96.21% in accuracy and 80.46% in F1-score on average 2 s before FOG occurrence, demonstrating the superiority of MCT-Net.

Freezing of gait: pharmacological and surgical options

PURPOSE OF REVIEW

The primary aim of this review is to describe and update the pathophysiological and relevant therapeutic strategies for freezing of gait (FoG) in patients with Parkinson's disease (PD).

RECENT FINDINGS

FoG presumably involves dysfunction of multiple cortical and subcortical components, including dopaminergic and nondopaminergic circuits. In this regard, levodopa and physical therapy represent the first-choice therapeutic options for PD patients with FoG. However, the relationship between FoG and levodopa is not fully predictable. For those patients with levodopa-resistant FoG, there is promising but still controversial data on the benefits of bilateral high-frequency transcranial magnetic stimulation and deep brain stimulation on the subthalamic nuclei, substantia nigra pars reticulata, pedunculopontine nucleus, and the Fields of Forel. On the other hand, general exercise, gait training with a treadmill, focus attention on gait training, and conventional physiotherapy have demonstrated moderate to large benefits in FoG.

SUMMARY

FOG requires different treatment strategies. The inclusion of adequate detection and prediction of FoG combined with double-blind, and statistically powered protocols are needed to improve patients' quality of life, the motor and nonmotor symptoms and societal burden associated with FoG.

A machine learning contest enhances automated freezing of gait detection and reveals time-of-day effects

Freezing of gait (FOG) is a debilitating problem that markedly impairs the mobility and independence of 38-65% of people with Parkinson's disease. During a FOG episode, patients report that their feet are suddenly and inexplicably "glued" to the floor. The lack of a widely applicable, objective FOG detection method obstructs research and treatment. To address this problem, we organized a 3-month machine-learning contest, inviting experts from around the world to develop wearable sensor-based FOG detection algorithms. 1,379 teams from 83 countries submitted 24,862 solutions. The winning solutions demonstrated high accuracy, high specificity, and good precision in FOG detection, with strong correlations to gold-standard references. When applied to continuous 24/7 data, the solutions revealed previously unobserved patterns in daily living FOG occurrences. This successful endeavor underscores the potential of machine learning contests to rapidly engage AI experts in addressing critical medical challenges and provides a promising means for objective FOG quantification.

Distance-based novelty detection model for identifying individuals at risk of developing Alzheimer's disease

Introduction

Novelty detection (ND, also known as one-class classification) is a machine learning technique used to identify patterns that are typical of the majority class and can discriminate deviations as novelties. In the context of Alzheimer's disease (AD), ND could be employed to detect abnormal or atypical behavior that may indicate early signs of cognitive decline or the presence of the disease. To date, few research studies have used ND to discriminate the risk of developing AD and mild cognitive impairment (MCI) from healthy controls (HC).

Methods

In this work, two distinct cohorts with highly heterogeneous data, derived from the Australian Imaging Biomarkers and Lifestyle (AIBL) Flagship Study of Ageing project and the Fujian Medical University Union Hospital (FMUUH) China, were employed. An innovative framework with built-in easily interpretable ND models constructed solely on HC data was introduced along with proposing a strategy of distance to boundary (DtB) to detect MCI and AD. Subsequently, a web-based graphical user interface (GUI) that incorporates the proposed framework was developed for non-technical stakeholders.

Results

Our experimental results indicate that the best overall performance of detecting AD individuals in AIBL and FMUUH datasets was obtained by using the Mixture of Gaussian-based ND algorithm applied to single modality, with an AUC of 0.8757 and 0.9443, a sensitivity of 96.79% and 89.09%, and a specificity of 89.63% and 90.92%, respectively.

Discussion

The GUI offers an interactive platform to aid stakeholders in making diagnoses of MCI and AD, enabling streamlined decision-making processes. More importantly, the proposed DtB strategy could visually and quantitatively identify individuals at risk of developing AD.

Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence

Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.

Detection and prediction of freezing of gait with wearable sensors in Parkinson's disease

Freezing of gait (FoG) is one of the most distressing symptoms of Parkinson's Disease (PD), commonly occurring in patients at middle and late stages of the disease. Automatic and accurate FoG detection and prediction have emerged as a promising tool for long-term monitoring of PD and implementation of gait assistance systems. This paper reviews the recent development of FoG detection and prediction using wearable sensors, with attention on identifying knowledge gaps that need to be filled in future research. This review searched the PubMed and Web of Science databases to collect studies that detect or predict FoG with wearable sensors. After screening, 89 of 270 articles were included. The data description, extracted features, detection/prediction methods, and classification performance were extracted from the articles. As the number of papers of this area is increasing, the performance has been steadily improved. However, small datasets and inconsistent evaluation processes still hinder the application of FoG detection and prediction with wearable sensors in clinical practice.

[Wearable devices: Perspectives on assessing and monitoring human physiological status]

This review article aims to explore the major challenges that the healthcare system is currently facing and propose a new paradigm shift that harnesses the potential of wearable devices and novel theoretical frameworks on health and disease. Lifestyle-induced diseases currently account for a significant portion of all healthcare spending, with this proportion projected to increase with population aging. Wearable devices have emerged as a key technology for implementing large-scale healthcare systems focused on disease prevention and management. Advancements in miniaturized sensors, system integration, the Internet of Things, artificial intelligence, 5G, and other technologies have enabled wearable devices to perform high-quality measurements comparable to medical devices. Through various physical, chemical, and biological sensors, wearable devices can continuously monitor physiological status information in a non-invasive or minimally invasive way, including electrocardiography, electroencephalography, respiration, blood oxygen, blood pressure, blood glucose, activity, and more. Furthermore, by combining concepts and methods from complex systems and nonlinear dynamics, we developed a novel theory of continuous dynamic physiological signal analysis-dynamical complexity. The results of dynamic signal analyses can provide crucial information for disease prevention, diagnosis, treatment, and management. Wearable devices can also serve as an important bridge connecting doctors and patients by tracking, storing, and sharing patient data with medical institutions, enabling remote or real-time health assessments of patients, and providing a basis for precision medicine and personalized treatment. Wearable devices have a promising future in the healthcare field and will be an important driving force for the transformation of the healthcare system, while also improving the health experience for individuals.

The advantages of artificial intelligence-based gait assessment in detecting, predicting, and managing Parkinson's disease

Background

Parkinson's disease is a neurological disorder that can cause gait disturbance, leading to mobility issues and falls. Early diagnosis and prediction of freeze episodes are essential for mitigating symptoms and monitoring the disease.

Objective

This review aims to evaluate the use of artificial intelligence (AI)-based gait evaluation in diagnosing and managing Parkinson's disease, and to explore the potential benefits of this technology for clinical decision-making and treatment support.

Methods

A thorough review of published literature was conducted to identify studies, articles, and research related to AI-based gait evaluation in Parkinson's disease.

Results

AI-based gait evaluation has shown promise in preventing freeze episodes, improving diagnosis, and increasing motor independence in patients with Parkinson's disease. Its advantages include higher diagnostic accuracy, continuous monitoring, and personalized therapeutic interventions.

Conclusion

AI-based gait evaluation systems hold great promise for managing Parkinson's disease and improving patient outcomes. They offer the potential to transform clinical decision-making and inform personalized therapies, but further research is needed to determine their effectiveness and refine their use.

Real world validation of activity recognition algorithm and development of novel behavioral biomarkers of falls in aged control and movement disorder patients

The use of wearable sensors in movement disorder patients such as Parkinson's disease (PD) and normal pressure hydrocephalus (NPH) is becoming more widespread, but most studies are limited to characterizing general aspects of mobility using smartphones. There is a need to accurately identify specific activities at home in order to properly evaluate gait and balance at home, where most falls occur. We developed an activity recognition algorithm to classify multiple daily living activities including high fall risk activities such as sit to stand transfers, turns and near-falls using data from 5 inertial sensors placed on the chest, upper-legs and lower-legs of the subjects. The algorithm is then verified with ground truth by collecting video footage of our patients wearing the sensors at home. Our activity recognition algorithm showed >95% sensitivity in detection of activities. Extracted features from our home monitoring system showed significantly better correlation (~69%) with prospectively measured fall frequency of our subjects compared to the standard clinical tests (~30%) or other quantitative gait metrics used in past studies when attempting to predict future falls over 1 year of prospective follow-up. Although detecting near-falls at home is difficult, our proposed model suggests that near-fall frequency is the most predictive criterion in fall detection through correlation analysis and fitting regression models.

Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks

Due to wearables' popularity, human activity recognition (HAR) plays a significant role in people's routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models' decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR's high performance with SD comes not only from physical activity learning but also from learning an individual's signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability.

IMU-Based Monitoring for Assistive Diagnosis and Management of IoHT: A Review

With the rapid development of Internet of Things (IoT) technologies, traditional disease diagnoses carried out in medical institutions can now be performed remotely at home or even ambient environments, yielding the concept of the Internet of Health Things (IoHT). Among the diverse IoHT applications, inertial measurement unit (IMU)-based systems play a significant role in the detection of diseases in many fields, such as neurological, musculoskeletal, and mental. However, traditional numerical interpretation methods have proven to be challenging to provide satisfying detection accuracies owing to the low quality of raw data, especially under strong electromagnetic interference (EMI). To address this issue, in recent years, machine learning (ML)-based techniques have been proposed to smartly map IMU-captured data on disease detection and progress. After a decade of development, the combination of IMUs and ML algorithms for assistive disease diagnosis has become a hot topic, with an increasing number of studies reported yearly. A systematic search was conducted in four databases covering the aforementioned topic for articles published in the past six years. Eighty-one articles were included and discussed concerning two aspects: different ML techniques and application scenarios. This review yielded the conclusion that, with the help of ML technology, IMUs can serve as a crucial element in disease diagnosis, severity assessment, characteristic estimation, and monitoring during the rehabilitation process. Furthermore, it summarizes the state-of-the-art, analyzes challenges, and provides foreseeable future trends for developing IMU-ML systems for IoHT.

A novelty detection approach to effectively predict conversion from mild cognitive impairment to Alzheimer’s disease

Accurately recognising patients with progressive mild cognitive impairment (pMCI) who will develop Alzheimer’s disease (AD) in subsequent years is very important, as early identification of those patients will enable interventions to potentially reduce the number of those transitioning from MCI to AD. Most studies in this area have concentrated on high-dimensional neuroimaging data with supervised binary/multi-class classification algorithms. However, neuroimaging data is more costly to obtain than non-imaging, and healthcare datasets are normally imbalanced which may reduce classification performance and reliability. To address these challenges, we proposed a new strategy that employs unsupervised novelty detection (ND) techniques to predict pMCI from the AD neuroimaging initiative non-imaging data. ND algorithms, including the k-nearest neighbours (kNN), k-means, Gaussian mixture model (GMM), isolation forest (IF) and extreme learning machine (ELM), were employed and compared with supervised binary support vector machine (SVM) and random forest (RF). We introduced optimisation with nested cross-validation and focused on maximising the adjusted F measure to ensure maximum generalisation of the proposed system by minimising false negative rates. Our extensive experimental results show that ND algorithms (0.727 ± 0.029 kNN, 0.7179 ± 0.0523 GMM, 0.7276 ± 0.0281 ELM) obtained comparable performance to supervised binary SVM (0.7359 ± 0.0451) with 20% stable MCI misclassification tolerance and were significantly better than RF (0.4771 ± 0.0167). Moreover, we found that the non-invasive, readily obtainable, and cost-effective cognitive and functional assessment was the most efficient predictor for predicting the pMCI within 2 years with ND techniques. Importantly, we presented an accessible and cost-effective approach to pMCI prediction, which does not require labelled data.

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human-computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

Wearable IMU-Based Human Activity Recognition Algorithm for Clinical Balance Assessment Using 1D-CNN and GRU Ensemble Model

In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.

A literature review on one-class classification and its potential applications in big data

In severely imbalanced datasets, using traditional binary or multi-class classification typically leads to bias towards the class(es) with the much larger number of instances. Under such conditions, modeling and detecting instances of the minority class is very difficult. One-class classification (OCC) is an approach to detect abnormal data points compared to the instances of the known class and can serve to address issues related to severely imbalanced datasets, which are especially very common in big data. We present a detailed survey of OCC-related literature works published over the last decade, approximately. We group the different works into three categories: outlier detection, novelty detection, and deep learning and OCC. We closely examine and evaluate selected works on OCC such that a good cross section of approaches, methods, and application domains is represented in the survey. Commonly used techniques in OCC for outlier detection and for novelty detection, respectively, are discussed. We observed one area that has been largely omitted in OCC-related literature is its application context for big data and its inherently associated problems, such as severe class imbalance, class rarity, noisy data, feature selection, and data reduction. We feel the survey will be appreciated by researchers working in these areas of big data.

Unsupervised Pre-trained Models from Healthy ADLs Improve Parkinson's Disease Classification of Gait Patterns

Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challenging as they require large amounts of training data that capture different possible variations. This makes it difficult to use them in a clinical setting since in most health applications researchers often have to work with limited data. Less data can cause the deep learning model to over-fit. In this paper, we ask how can we use data from a different environment, different use-case, with widely differing data distributions. We exemplify this use case by using single-sensor accelerometer data from healthy subjects performing activities of daily living - ADLs (source dataset), to extract features relevant to multi-sensor accelerometer gait data (target dataset) for Parkinson's disease classification. We train the pre-trained model using the source dataset and use it as a feature extractor. We show that the features extracted for the target dataset can be used to train an effective classification model. Our pretrained source model consists of a convolutional autoencoder, and the target classification model is a simple multi-layer perceptron model. We explore two different pre-trained source models, trained using different activity groups, and analyze the influence the choice of pre-trained model has over the task of Parkinson's disease classification.

Deep Learning Approaches for Detecting Freezing of Gait in Parkinson's Disease Patients through On-Body Acceleration Sensors

Freezing of gait (FOG) is one of the most incapacitating motor symptoms in Parkinson's disease (PD). The occurrence of FOG reduces the patients' quality of live and leads to falls. FOG assessment has usually been made through questionnaires, however, this method can be subjective and could not provide an accurate representation of the severity of this symptom. The use of sensor-based systems can provide accurate and objective information to track the symptoms' evolution to optimize PD management and treatments. Several authors have proposed specific methods based on wearables and the analysis of inertial signals to detect FOG in laboratory conditions, however, its performance is usually lower when being used at patients' homes. This study presents a new approach based on a recurrent neural network (RNN) and a single waist-worn triaxial accelerometer to enhance the FOG detection performance to be used in real home-environments. Also, several machine and deep learning approaches for FOG detection are evaluated using a leave-one-subject-out (LOSO) cross-validation. Results show that modeling spectral information of adjacent windows through an RNN can bring a significant improvement in the performance of FOG detection without increasing the length of the analysis window (required to using it as a cue-system).

Analysis of Machine Learning-Based Assessment for Elbow Spasticity Using Inertial Sensors

Spasticity is a frequently observed symptom in patients with neurological impairments. Spastic movements of their upper and lower limbs are periodically measured to evaluate functional outcomes of physical rehabilitation, and they are quantified by clinical outcome measures such as the modified Ashworth scale (MAS). This study proposes a method to determine the severity of elbow spasticity, by analyzing the acceleration and rotation attributes collected from the elbow of the affected side of patients and machine-learning algorithms to classify the degree of spastic movement; this approach is comparable to assigning an MAS score. We collected inertial data from participants using a wearable device incorporating inertial measurement units during a passive stretch test. Machine-learning algorithms-including decision tree, random forests (RFs), support vector machine, linear discriminant analysis, and multilayer perceptrons-were evaluated in combinations of two segmentation techniques and feature sets. A RF performed well, achieving up to 95.4% accuracy. This work not only successfully demonstrates how wearable technology and machine learning can be used to generate a clinically meaningful index but also offers rehabilitation patients an opportunity to monitor the degree of spasticity, even in nonhealthcare institutions where the help of clinical professionals is unavailable.

Introduction to Extreme Seeking Entropy

Recently, the concept of evaluating an unusually large learning effort of an adaptive system to detect novelties in the observed data was introduced. The present paper introduces a new measure of the learning effort of an adaptive system. The proposed method also uses adaptable parameters. Instead of a multi-scale enhanced approach, the generalized Pareto distribution is employed to estimate the probability of unusual updates, as well as for detecting novelties. This measure was successfully tested in various scenarios with (i) synthetic data, (ii) real time series datasets, and multiple adaptive filters and learning algorithms. The results of these experiments are presented.

Wearable-Sensor-based Detection and Prediction of Freezing of Gait in Parkinson's Disease: A Review

Freezing of gait (FOG) is a serious gait disturbance, common in mid- and late-stage Parkinson's disease, that affects mobility and increases fall risk. Wearable sensors have been used to detect and predict FOG with the ultimate aim of preventing freezes or reducing their effect using gait monitoring and assistive devices. This review presents and assesses the state of the art of FOG detection and prediction using wearable sensors, with the intention of providing guidance on current knowledge, and identifying knowledge gaps that need to be filled and challenges to be considered in future studies. This review searched the Scopus, PubMed, and Web of Science databases to identify studies that used wearable sensors to detect or predict FOG episodes in Parkinson's disease. Following screening, 74 publications were included, comprising 68 publications detecting FOG, seven predicting FOG, and one in both categories. Details were extracted regarding participants, walking task, sensor type and body location, detection or prediction approach, feature extraction and selection, classification method, and detection and prediction performance. The results showed that increasingly complex machine-learning algorithms combined with diverse feature sets improved FOG detection. The lack of large FOG datasets and highly person-specific FOG manifestation were common challenges. Transfer learning and semi-supervised learning were promising for FOG detection and prediction since they provided person-specific tuning while preserving model generalization.

Vision-Based Novelty Detection Using Deep Features and Evolved Novelty Filters for Specific Robotic Exploration and Inspection Tasks

One of the essential abilities in animals is to detect novelties within their environment. From the computational point of view, novelty detection consists of finding data that are different in some aspect to the known data. In robotics, researchers have incorporated novelty modules in robots to develop automatic exploration and inspection tasks. The visual sensor is one of the preferred sensors to perform this task. However, there exist problems as illumination changes, occlusion, and scale, among others. Besides, novelty detectors vary their performance depending on the specific application scenario. In this work, we propose a visual novelty detection framework for specific exploration and inspection tasks based on evolved novelty detectors. The system uses deep features to represent the visual information captured by the robots and applies a global optimization technique to design novelty detectors for specific robotics applications. We verified the performance of the proposed system against well-established state-of-the-art methods in a challenging scenario. This scenario was an outdoor environment covering typical problems in computer vision such as illumination changes, occlusion, and geometric transformations. The proposed framework presented high-novelty detection accuracy with competitive or even better results than the baseline methods.

A New Time-Frequency Feature Extraction Method for Action Detection on Artificial Knee by Fractional Fourier Transform

With the aim of designing an action detection method on artificial knee, a new time-frequency feature extraction method was proposed. The inertial data were extracted periodically using the microelectromechanical systems (MEMS) inertial measurement unit (IMU) on the prosthesis, and the features were extracted from the inertial data after fractional Fourier transform (FRFT). Then, a feature vector composed of eight features was constructed. The transformation results of these features after FRFT with different orders were analyzed, and the dimensions of the feature vector were reduced. The classification effects of different features and different orders are analyzed, according to which order and feature of each sub-classifier were designed. Finally, according to the experiment with the prototype, the method proposed above can reduce the requirements of hardware calculation and has a better classification effect. The accuracies of each sub-classifier are 95.05%, 95.38%, 91.43%, and 89.39%, respectively; the precisions are 78.43%, 98.36%, 98.36%, and 93.41%, respectively; and the recalls are 100%, 93.26%, 86.96%, and 86.68%, respectively.