Search

Abstract Background: Characterizing the condition of patients suffering from knee osteoarthritis is complex due to multiple associations between clinical, functional, and structural parameters. While significant variability exists within this population, especially in candidates for total knee arthroplasty, there is increasing interest in knee kinematics among orthopedic surgeons aiming for more personalized approaches to achieve better outcomes and satisfaction. The primary objective of this study was to identify distinct kinematic phenotypes in total knee arthroplasty candidates and to compare different methods for the identification of these phenotypes. Methods: Three-dimensional kinematic data obtained from a Knee Kinesiography exam during treadmill walking in the clinic were used. Various aspects of the clustering process were evaluated and compared to achieve optimal clustering, including data preparation, transformation, and representation methods. Results: A K-Means clustering algorithm, performed using Euclidean distance, combined with principal component analysis applied on data transformed by standardization, was the optimal approach. Two unique kinematic phenotypes were identified among 80 total knee arthroplasty candidates. The two distinct phenotypes divided patients who significantly differed both in terms of knee kinematic representation and clinical outcomes, including a notable variation in 63.3% of frontal plane features and 81.8% of transverse plane features across 77.33% of the gait cycle, as well as differences in the Pain Catastrophizing Scale, highlighting the impact of these kinematic variations on patient pain and function. Conclusion: Results from this study provide valuable insights for clinicians to develop personalized treatment approaches based on patients’ phenotype affiliation, ultimately helping to improve total knee arthroplasty outcomes.

BackgroundImbalanced datasets pose challenges for developing accurate seizure detection systems based on electroencephalogram (EEG) data. Generative AI techniques may help augment minority class data to facilitate automatic epileptic seizure detection.New methodThis study investigates the impact of various data augmentation (DA) approaches, including Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), Vanilla GAN, Conditional GAN (CGAN), and Cramer GAN, on classification performance with Random Forest models. The best-performing GAN variant, WGAN-GP, was then integrated with a bidirectional Long Short-Term Memory (LSTM) architecture and compared against traditional and synthetic oversampling methods.ResultsThe evaluation of different GAN variants for data augmentation with Random Forest classifiers identified WGAN-GP as the most effective approach. The integration of WGAN-GP with bidirectional LSTM yielded substantial performance improvements, outperforming traditional oversampling methods and achieving an accuracy of 91.73% on the augmented data, compared to 86% accuracy on real data without augmentation.Comparison with existing methodsThe proposed generative AI approach combining WGAN-GP and recurrent neural network models outperforms comparative synthetic oversampling methods on metrics relevant for reliable seizure detection from imbalanced EEG datasets.ConclusionsIncorporating the WGAN-GP generative AI technique for data augmentation and integrating it with bidirectional LSTM elevates seizure detection accuracy for imbalanced EEG datasets, surpassing the performance of traditional oversampling and class weight adjustment methods. This approach shows promise for improving epilepsy monitoring and management through enhanced automated detection system effectiveness.

The ability to predict the occurrence of an epileptic seizure is a safeguard against patient injury and health complications. However, a major challenge in seizure prediction arises from the significant variability observed in patient data. Common patient-specific approaches, which apply to each patient independently, often perform poorly for other patients due to the data variability. The aim of this study is to propose deep learning models which can handle this variability and generalize across various patients. This study addresses this challenge by introducing a novel cross-subject and multi-subject prediction models. Multiple-subject modeling broadens the scope of patient-specific modeling to account for the data from a dedicated ensemble of patients, thereby providing some useful, though relatively modest, level of generalization. The basic neural network architecture of this model is then adapted to cross-subject prediction, thereby providing a broader, more realistic, context of application. For accrued performance, and generalization ability, cross-subject modeling is enhanced by domain adaptation. Experimental evaluation using the publicly available CHB-MIT and SIENA data datasets shows that our multiple-subject model achieved better performance compared to existing works. However, the cross-subject faces challenges when applied to different patients. Finally, through investigating three domain adaptation methods, the model accuracy has been notably improved by 10.30% and 7.4% for the CHB-MIT and SIENA datasets, respectively.

People with urinary incontinence (UI) often face a significant social stigma feeling ashamed of their condition and worrying about others discovering it. In order to improve the quality of life of those with incontinence, recent technological advancements enabled the development of non-invasive devices for detecting urinary leakage (UL). However, no comprehensive study has been conducted to state the most suitable types of sensors and the fundamental features necessary to design such devices, while also pointing gaps for future research. To address this, we conducted a mini review using four electronic databases limiting our search to English-written papers published in peer-reviewed journals. We retrieved articles that met the chosen inclusion criteria and classified them based on sensor type used, its location, the detection technique employed, and whether it was an e-Textile design and a reusable product or not. Across the studies, UL was detected using different approaches leading to heterogeneous results. Electrodes commonly used as sensing elements, along with textile as substrate material, and an indicator of UL based on resistance value, appeared to be widely exploited. However, the outcomes were not correlated with any specific type of UI. Consequently, we hypothesize that any non-invasive device could potentially be used for different types of UI. Nevertheless, further studies need to be conducted to confirm this statement. The designed literature mapping provides readers with an overview of the recent non-invasive wearable technologies in UL detection and offers a roadmap for future innovations.

Abstract Background Conventional radiography is commonly used to diagnose knee osteoarthritis (OA), but also to guide clinical decision-making, despite a well-established discordance between radiographic severity and patient symptoms. The incidence and progression of OA is driven, in part, by biomechanical markers. Therefore, these dynamic markers may be a good metric of functional status and actionable targets for clinicians when developing conservative treatment plans. The aim of this study was to assess the associations between biomechanical markers and self-reported knee function compared to radiographic severity. Methods This was a secondary analysis of data from a randomized controlled trial (RCT) conducted in primary care clinics with knee OA participants. Correlation coefficients (canonical (ρ) and structural (Corr)) were assessed between the Knee Injury and Osteoarthritis Outcome Score (KOOS) and both, radiographic OA severity using the Kellgren-Lawrence grade, and three-dimensional biomechanical markers quantified by a knee kinesiography exam. Significant differences between coefficients were assessed using Fischer’s z-transformation method to compare correlations from dependent samples. Results KOOS and biomechanical data were significantly more associated than KOOS and X-ray grading (ρ: 0.41 vs 0.20; p 36% variance explained), while X-ray grading was most associated with Symptoms subscale (21% explained; all p ≤ 0.001). Conclusions Knee biomechanical markers are associated with patient-reported knee function to a greater extent than X-ray grading, but both provide complementary information in the assessment of OA patients. Understanding how dynamic markers relate to function compared to radiographic severity is a valuable step towards precision medicine, allowing clinicians to refine and tailor therapeutic measures by prioritizing and targeting modifiable biomechanical markers linked to pain and function. Trial registration Original RCT was approved by the Research Ethics Boards of École de technologie supérieure (H20150505) and Centre hospitalier de l’Université de Montréal (CHUM-CE.14.339), first registered at https://www.isrctn.com/ (ID-ISRCTN16152290) on May 27, 2015.

Back mobility is a criterion of well-being in a horse. Veterinarians visually assess the mobility of a horse’s back during a locomotor examination. Quantifying it with on-board technology could be a major breakthrough to help them. The aim of this study was to evaluate the accuracy of a method of quantifying the back mobility of horses from inertial measurement units (IMUs) compared to motion capture (MOCAP) as a gold standard. Reflective markers and IMUs were positioned on the withers, eighteenth thoracic vertebra, and pelvis of four sound horses. The horses performed a walk and trot in straight lines and performed a gallop in circles on a soft surface. The developed method, based on the three IMUs, consists of calculating the flexion/extension angle of the thoracolumbar region. The IMU method showed a mean bias of 0.8° (±1.5°) (mean (±SD)) and 0.8° (±1.4°), respectively, for the flexion and extension movements, all gaits combined, compared to the MOCAP method. The results of this study suggest that the developed method has a similar accuracy to that of MOCAP, opening up possibilities for easy measurements under field conditions. Future studies will need to examine the correlations between these biomechanical measures and clinicians’ visual assessment of back mobility defects.

Deep learning has served pattern classification in many applications, with a performance which often well exceeds that of other machine learning paradigms. Yet, in general, deep learning has used computational architectures built, albeit partially, by ad hoc means, and its classification decisions are not necessarily interpretable in terms of knowledge relevant to the application it serves. This is often referred to as the black box problem, which in certain applications, such as epileptic seizure prediction, can be a serious impediment. The purpose of this study is to investigate an interpretable deep learning classifier for epileptic EEG-driven seizure prediction. This neural network is interpretable because its layers can be visualized and interpreted as a result of a novel architecture where the learned weights follow from signal processing computations such as frequency sub-band and spatial filters. Consequently, the extracted features are no longer abstract as they correspond to the features commonly used for decoding EEG data. In addition, the network uses layer-wise relevance propagation to reveal pertinent features which can further explain the computations leading to the decisions. In seizure prediction experiments using the CHB-MIT data set, the method produced classification results which improved on the state-of-the art, with first network layer filters corresponding to clinically relevant frequency bands, and the input channels in the brain location in which the seizure originates contributing most significantly to the network predictions.

Feature selection is a challenging problem that occurs in the high-dimensional data analysis of many major applications. It addresses the curse of dimensionality by determining a small set of features to represent high-dimensional data without significant or noticeable loss of information. The purpose of this study is to develop and investigate a new unsupervised feature selection method which uses the k-influence space concept and subspace learning to map features onto a weighted graph and rank them by importance according to the PageRank graph centrality measure. The graph design in this method promotes feature relevance, downgrades redundancy, and is robust to outliers and cluster imbalances. In K-Means classification experiments using the ASU feature selection testing datasets, the method produces better accuracy and normalized mutual information results than state-of-the-art unsupervised feature selection algorithms. In a further evaluation, using a dataset of over 14,000 tweets, conventional classification of features selected by the method gave better sentiment analysis results than deep learning feature selection and classification.

Abstract Background Biomechanical and clinical parameters contribute very closely to functional evaluations of the knee joint. To better understand knee osteoarthritis joint function, the association between a set of knee biomechanical data and a set of clinical parameters of an osteoarthritis population (OA) is investigated in this study. Methods The biomechanical data used here are a set of characteristics derived from 3D knee kinematic patterns: flexion/extension, abduction/adduction, and tibial internal/external rotation measurements, all determined during gait recording. The clinical parameters include a KOOS questionnaire and the patient’s demographic characteristics. Canonical correlation analysis (CCA) is used (1) to evaluate the multivariate relationship between biomechanical data and clinical parameter sets, and (2) to cluster the most correlated parameters. Multivariate models were created within the identified clusters to determine the effect of each parameter’s subset on the other. The analyses were performed on a large database containing 166 OA patients. Results The CCA results showed meaningful correlations that gave rise to three different clusters. Multivariate linear models were found explaining the subjective clinical parameters by evaluating the biomechanical data contained within each cluster. Conclusion The results showed that a multivariate analysis of the clinical symptoms and the biomechanical characteristics of knee joint function allowed a better understanding of their relationships.

Monitoring patients at risk of epileptic seizure is critical for optimal treatment and ensuing the reduction of seizure risk and complications. In general, seizure detection is done manually in hospitals and involves time-consuming visual inspection and interpretation by experts of electroencephalography (EEG) recordings. The purpose of this study is to investigate the pertinence of band-limited spectral power and signal complexity in order to discriminate between seizure and seizure-free EEG brain activity. The signal complexity and spectral power are evaluated in five frequency intervals, namely, the delta, theta, alpha, beta, and gamma bands, to be used as EEG signal feature representation. Classification of seizure and seizure-free data was performed by prevalent potent classifiers. Substantial comparative performance evaluation experiments were performed on a large EEG data record of 341 patients in the Temple University Hospital EEG seizure database. Based on statistically validated criteria, results show the efficiency of band-limited spectral power and signal complexity when using random forest and gradient-boosting decision tree classifiers (95% of the area under the curve (AUC) and 91% for both F-measure and accuracy). These results support the use of these automatic classification schemes to assist the practicing neurologist interpret EEG records more accurately and without tedious visual inspection.

The purpose of this study is to identify healthy phenotypes in knee kinematics based on clustering data analysis. Our analysis uses the 3D knee kinematics curves, namely, flexion/extension, abduction/adduction, and tibial internal/external rotation, measured via a KneeKG™ system during a gait task. We investigated two data representation approaches that are based on the joint analysis of the three dimensions. The first is a global approach that is considered a concatenation of the kinematic data without any dimensionality reduction. The second is a local approach that is considered a set of 69 biomechanical parameters of interest extracted from the 3D kinematic curves. The data representations are followed by a clustering process, based on the BIRCH (balanced iterative reducing and clustering using hierarchies) discriminant model, to separate 3D knee kinematics into homogeneous groups or clusters. Phenotypes were obtained by averaging those groups. We validated the clusters using inter-cluster correlation and statistical hypothesis tests. The simulation results showed that the global approach is more efficient, and it allows the identification of three descriptive 3D kinematic phenotypes within a healthy knee population.

Human activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification to provide healthcare of higher standards. The purpose of this study is to investigate a human activity recognition method of accrued decision accuracy and speed of execution to be applicable in healthcare. This method classifies wearable sensor acceleration time series data of human movement using an efficient classifier combination of feature engineering-based and feature learning-based data representation. Leave-one-subject-out cross-validation of the method with data acquired from 44 subjects wearing a single waist-worn accelerometer on a smart textile, and engaged in a variety of 10 activities, yielded an average recognition rate of 90%, performing significantly better than individual classifiers. The method easily accommodates functional and computational parallelization to bring execution time significantly down.

The assessment of genetic diversity and structure of a gene pool is a prerequisite for efficient organization, conservation, and utilization for crop improvement. This study evaluated the genetic diversity and population structure of 24 Tunisian melon accessions, by using 24 phenotypic traits and eight microsatellite (SSR) markers. A considerable phenotypic diversity among accessions was observed for many characters including those related to agronomical performance. All the microsatellites were polymorphic and detected 30 distinct alleles with a moderate (0.43) polymorphic information content. Shannon’s diversity index (0.82) showed a high degree of polymorphism between melon genotypes. The observed heterozygosity (0.10) was less than the expected heterozygosity (0.12), displaying a deficit in heterozygosity because of selection pressure. Molecular clustering and structure analyses based on SSRs separated melon accessions into five groups and showed an intermixed genetic structure between landraces and breeding lines belonging to the different botanical groups. Phenotypic clustering separated the accessions into two main clusters belonging to sweet and non-sweet melon; however, a more precise clustering among inodorus, cantalupensis, and reticulatus subgroups was obtained using combined phenotypic–molecular data. The discordance between phenotypic and molecular data was confirmed by a negative correlation (r = −0.16, p = 0.06) as revealed by the Mantel test. Despite these differences, both markers provided important information about the diversity of the melon germplasm, allowing the correct use of these accessions in future breeding programs. Together they provide a powerful tool for future agricultural and conservation tasks.

Background. The purpose of this study is to review the current literature on knee joint biomechanical gait data analysis for knee pathology classification. The review is prefaced by a presentation of the prerequisite knee joint biomechanics background and a description of biomechanical gait pattern recognition as a diagnostic tool. It is postfaced by discussions that highlight the current research findings and future directions. Methods. The review is based on a literature search in PubMed, IEEE Xplore, Science Direct, and Google Scholar on April 2019. Inclusion criteria admitted articles, written in either English or French, on knee joint biomechanical gait data classification in general. We recorded the relevant information pertaining to the investigated knee joint pathologies, the participants’ attributes, data acquisition, feature extraction, and selection used to represent the data, as well as the classification algorithms and validation of the results. Results. Thirty-one studies met the inclusion criteria for review. Conclusions. The review reveals that the importance of medical applications of knee joint biomechanical gait data classification and recent progress in data acquisition technology are fostering intense interest in the subject and giving a strong impetus to research. The review also reveals that biomechanical data during locomotion carry essential information on knee joint conditions to infer an early diagnosis. This survey paper can serve as a useful informative reference for research on the subject.

The purpose of this study is (1) to provide EEG feature complexity analysis in seizure prediction by inter-ictal and pre-ital data classification and, (2) to assess the between-subject variability of the considered features. In the past several decades, there has been a sustained interest in predicting epilepsy seizure using EEG data. Most methods classify features extracted from EEG, which they assume are characteristic of the presence of an epilepsy episode, for instance, by distinguishing a pre-ictal interval of data (which is in a given window just before the onset of a seizure) from inter-ictal (which is in preceding windows following the seizure). To evaluate the difficulty of this classification problem independently of the classification model, we investigate the complexity of an exhaustive list of 88 features using various complexity metrics, i.e., the Fisher discriminant ratio, the volume of overlap, and the individual feature efficiency. Complexity measurements on real and synthetic data testbeds reveal that that seizure prediction by pre-ictal/inter-ictal feature distinction is a problem of significant complexity. It shows that several features are clearly useful, without decidedly identifying an optimal set.

This paper has two objectives: the first is to generate two binary flags to indicate useful frames permitting the measurement of cardiac and respiratory rates from Ballistocardiogram (BCG) signals—in fact, human body activities during measurements can disturb the BCG signal content, leading to difficulties in vital sign measurement; the second objective is to achieve refined BCG signal segmentation according to these activities. The proposed framework makes use of two approaches: an unsupervised classification based on the Gaussian Mixture Model (GMM) and a supervised classification based on K-Nearest Neighbors (KNN). Both of these approaches consider two spectral features, namely the Spectral Flatness Measure (SFM) and Spectral Centroid (SC), determined during the feature extraction step. Unsupervised classification is used to explore the content of the BCG signals, justifying the existence of different classes and permitting the definition of useful hyper-parameters for effective segmentation. In contrast, the considered supervised classification approach aims to determine if the BCG signal content allows the measurement of the heart rate (HR) and the respiratory rate (RR) or not. Furthermore, two levels of supervised classification are used to classify human-body activities into many realistic classes from the BCG signal (e.g., coughing, holding breath, air expiration, movement, et al.). The first one considers frame-by-frame classification, while the second one, aiming to boost the segmentation performance, transforms the frame-by-frame SFM and SC features into temporal series which track the temporal variation of the measures of the BCG signal. The proposed approach constitutes a novelty in this field and represents a powerful method to segment BCG signals according to human body activities, resulting in an accuracy of 94.6%.

Measuring knee biomechanics provides valuable clinical information for defining patient-specific treatment options, including patient-oriented physical exercise programs. It can be done by a knee kinesiography test measuring the three-dimensional rotation angles (3D kinematics) during walking, thus providing objective knowledge about knee function in dynamic and weight-bearing conditions. The purpose of this study was to assess whether 3D kinematics can be efficiently used to predict the impact of a physical exercise program on the condition of knee osteoarthritis (OA) patients. The prediction was based on 3D knee kinematic data, namely flexion/extension, adduction/abduction and external/internal rotation angles collected during a treadmill walking session at baseline. These measurements are quantifiable information suitable to develop automatic and objective methods for personalized computer-aided treatment systems. The dataset included 221 patients who followed a personalized therapeutic physical exercise program for 6 months and were then assigned to one of two classes, Improved condition (I) and not-Improved condition (nI). A 10% improvement in pain was needed at the 6-month follow-up compared to baseline to be in the improved group. The developed model was able to predict I and nI with 84.4% accuracy for men and 75.5% for women using a decision tree classifier trained with 3D knee kinematic data taken at baseline and a 10-fold validation procedure. The models showed that men with an impaired control of their varus thrust and a higher pain level at baseline, and women with a greater amplitude of internal tibia rotation were more likely to report improvements in their pain level after 6 months of exercises. Results support the effectiveness of decision trees and the relevance of 3D kinematic data to objectively predict knee OA patients’ response to a treatment consisting of a physical exercise program.

This paper aims to analyze the correlation structure between the kinematic and clinical parameters of an end-staged knee osteoarthritis population. The kinematic data are a set of characteristics derived from 3D knee kinematic patterns. The clinical parameters include the answers of a clinical questionnaire and the patient’s demographic characteristics. The proposed method performs, first, a regularized canonical correlation analysis (RCCA) to evaluate the multivariate relationship between the clinical and kinematic datasets, and second, a combined visualization method to better understand the relationships between these multivariate data. Results show the efficiency of using different and complementary visual representation tools to highlight hidden relationships and find insights in data.

Three-dimensional (3D) knee kinematic data, measuring flexion/extension, abduction/adduction, and internal/external rotation angle variations during locomotion, provide essential information to diagnose, classify, and treat musculoskeletal knee pathologies. However, and so across genders, the curse of dimensionality, intra-class high variability, and inter-class proximity make this data usually difficult to interpret, particularly in tasks such as knee pathology classification. The purpose of this study is to use data complexity analysis to get some insight into this difficulty. Using 3D knee kinematic measurements recorded from osteoarthritis and asymptomatic subjects, we evaluated both single feature complexity, where each feature is taken individually, and global feature complexity, where features are considered simultaneously. These evaluations afford a characterization of data complexity independent of the used classifier and, therefore, provide information as to the level of classification performance one can expect. Comparative results, using reference databases, reveal that knee kinematic data are highly complex, and thus foretell the difficulty of knee pathology classification.

Knee kinematic data consist of a small sample of high-dimensional vectors recording repeated measurements of the temporal variation of each of the three fundamental angles of knee three-dimensional rotation during a walking cycle. In applications such as knee pathology classification, the notorious problems of high-dimensionality (the curse of dimensionality), high intra-class variability, and inter-class similarity make this data generally difficult to interpret. In the face of these difficulties, the purpose of this study is to investigate knee kinematic data classification by a Kohonen neural network generalized to encode samples of multidimensional data vectors rather than single such vectors as in the standard network. The network training algorithm and its ensuing classification function both use the Hotelling T 2 statistic to evaluate the underlying sample similarity, thus affording efficient use of training data for network development and robust classification of observed data. Applied to knee osteoarthritis pathology discrimination, namely the femoro-rotulian (FR) and femoro-tibial (FT) categories, the scheme improves on the state-of-the-art methods.

Recent studies have shown that the Gibbs density function is a good model for visual patterns and that its parameters can be learned from pattern category training data by a gradient algorithm optimizing a constrained entropy criterion. These studies represented each pattern category by a single density. However, the patterns in a category can be so complex as to require a representation spread over several densities to more accurately account for the shape of their distribution in the feature space. The purpose of the present study is to investigate a representation of visual pattern category by several Gibbs densities using a Kohonen neural structure. In this Gibbs density based Kohonen network, which we call a Gibbsian Kohonen network, each node stores the parameters of a Gibbs density. Collectively, these Gibbs densities represent the pattern category. The parameters are learned by a gradient update rule so that the corresponding Gibbs densities maximize entropy subject to reproducing observed feature statistics of the training patterns. We verified the validity of the method and the efficiency of the ensuing Gibbs density pattern representation on a handwritten character recognition application.