Search

Aims: Patients with Parkinson's disease (PD) have various motor difficulties, including standing up, gait initiation and freezing of gait. These abnormalities are associated with cortico‐subthalamic dysfunction. We aimed to reveal the characteristics of cortico‐subthalamic activity in PD patients during different motor statuses. Methods: Potentials were recorded in the superior parietal lobule (SPL), the primary motor cortex (M1), premotor cortex (PMC), and the bilateral subthalamic nucleus (STN) in 18 freely walking patients while sitting, standing, walking, dual‐task walking, and freezing in medication "off" (Moff) and "on" (Mon) states. Different motor status activities were compared in band power, and a machine learning classifier was used to differentiate the motor statuses. Results: SPL beta power was specifically inhibited from standing to walking, and negatively correlated with walking speed; M1 beta power reflected the degree of rigidity and was reversed by medication; XGBoost algorithm classified the five motor statuses with acceptable accuracy (68.77% in Moff, 60.58% in Mon). SPL beta power ranked highest in feature importance in both Moff and Mon states. Conclusion: SPL beta power plays an essential role in walking status classification and could be a physiological biomarker for walking speed, which would aid the development of adaptive DBS. [ABSTRACT FROM AUTHOR]

The Chimp Optimization Algorithm (ChOA) is a heuristic algorithm proposed in recent years. It models the cooperative hunting behaviour of chimpanzee populations in nature and can be used to solve numerical as well as practical engineering optimization problems. ChOA has the problems of slow convergence speed and easily falling into local optimum. In order to solve these problems, this paper proposes a novel chimp optimization algorithm with refraction learning (RL-ChOA). In RL-ChOA, the Tent chaotic map is used to initialize the population, which improves the population's diversity and accelerates the algorithm's convergence speed. Further, a refraction learning strategy based on the physical principle of light refraction is introduced in ChOA, which is essentially an Opposition-Based Learning, helping the population to jump out of the local optimum. Using 23 widely used benchmark test functions and two engineering design optimization problems proved that RL-ChOA has good optimization performance, fast convergence speed, and satisfactory engineering application optimization performance. [ABSTRACT FROM AUTHOR]

Gait and waist motions always contain massive personnel information and it is feasible to extract these data via wearable electronics for identification and healthcare based on the Internet of Things (IoT). There also remains a demand to develop a cost‐effective human‐machine interface to enhance the immersion during the long‐term rehabilitation. Meanwhile, triboelectric nanogenerator (TENG) revealing its merits in both wearable electronics and IoT tends to be a possible solution. Herein, the authors present wearable TENG‐based devices for gait analysis and waist motion capture to enhance the intelligence and performance of the lower‐limb and waist rehabilitation. Four triboelectric sensors are equidistantly sewed onto a fabric belt to recognize the waist motion, enabling the real‐time robotic manipulation and virtual game for immersion‐enhanced waist training. The insole equipped with two TENG sensors is designed for walking status detection and a 98.4% identification accuracy for five different humans aiming at rehabilitation plan selection is achieved by leveraging machine learning technology to further analyze the signals. Through a lower‐limb rehabilitation robot, the authors demonstrate that the sensory system performs well in user recognition, motion monitoring, as well as robot and gaming‐aided training, showing its potential in IoT‐based smart healthcare applications. [ABSTRACT FROM AUTHOR]

Gait and waist motions always contain massive personnel information and it is feasible to extract these data via wearable electronics for identification and healthcare based on the Internet of Things (IoT). There also remains a demand to develop a cost‐effective human‐machine interface to enhance the immersion during the long‐term rehabilitation. Meanwhile, triboelectric nanogenerator (TENG) revealing its merits in both wearable electronics and IoT tends to be a possible solution. Herein, the authors present wearable TENG‐based devices for gait analysis and waist motion capture to enhance the intelligence and performance of the lower‐limb and waist rehabilitation. Four triboelectric sensors are equidistantly sewed onto a fabric belt to recognize the waist motion, enabling the real‐time robotic manipulation and virtual game for immersion‐enhanced waist training. The insole equipped with two TENG sensors is designed for walking status detection and a 98.4% identification accuracy for five different humans aiming at rehabilitation plan selection is achieved by leveraging machine learning technology to further analyze the signals. Through a lower‐limb rehabilitation robot, the authors demonstrate that the sensory system performs well in user recognition, motion monitoring, as well as robot and gaming‐aided training, showing its potential in IoT‐based smart healthcare applications. [ABSTRACT FROM AUTHOR]

Gait and waist motions always contain massive personnel information and it is feasible to extract these data via wearable electronics for identification and healthcare based on the Internet of Things (IoT). There also remains a demand to develop a cost‐effective human‐machine interface to enhance the immersion during the long‐term rehabilitation. Meanwhile, triboelectric nanogenerator (TENG) revealing its merits in both wearable electronics and IoT tends to be a possible solution. Herein, the authors present wearable TENG‐based devices for gait analysis and waist motion capture to enhance the intelligence and performance of the lower‐limb and waist rehabilitation. Four triboelectric sensors are equidistantly sewed onto a fabric belt to recognize the waist motion, enabling the real‐time robotic manipulation and virtual game for immersion‐enhanced waist training. The insole equipped with two TENG sensors is designed for walking status detection and a 98.4% identification accuracy for five different humans aiming at rehabilitation plan selection is achieved by leveraging machine learning technology to further analyze the signals. Through a lower‐limb rehabilitation robot, the authors demonstrate that the sensory system performs well in user recognition, motion monitoring, as well as robot and gaming‐aided training, showing its potential in IoT‐based smart healthcare applications. [ABSTRACT FROM AUTHOR]

Sustainable and efficient hydrochar production via microwave-assisted hydrothermal carbonization (MW-HTC) and co-hydrothermal carbonization (co-HTC) has garnered increasing attention. This review offers a comprehensive analysis of recent advancements, primarily focusing on the performance and potential applications of hydrochar produced through these two processes. MW-HTC of lignocellulosic biomass yields hydrochar in the range of 30–80 dwt.%, with higher heating values of 19–23 MJ/kg and energy yields of 50–85%. Its adsorption capacity reaches around 50 mg/g for heavy metals and 1–5 mg/g for organic pollutants. Principal component analysis reveals significant differences in MW-HTC treatment of lignocellulosic and non-lignocellulosic materials. In the co-HTC process, sewage sludge and lignocellulosic biomass are the most studied feedstocks. Synergistic and antagonistic effects on hydrochar yield were identified, with most studies reporting a synergistic effect, particularly when protein and carbohydrate co-exist, potentially due to the Maillard reaction. The adsorption capacities of co-HTC hydrochars depend on the raw material mix, process parameters, and target contaminants. This review highlights the promising potential of MW-HTC and co-HTC for enhanced hydrochar production and application, emphasizing the necessity for future advancements, including machine learning for prediction of hydrochar yield, HTC process optimization, and feedstock's single model components-based HTC to elucidate the MW effect and synergism/antagonism. • MW-HTC and co-HTC processes offer a sustainable approach to efficient hydrochar production. • MW-HTC of algal feedstocks exhibit different performances than other types of feedstocks. • Co-HTC shows synergy in hydrochar yield when protein and carbohydrate co-exist. • The need of machine learning modeling for product prediction and synergy exploration. [ABSTRACT FROM AUTHOR]

Endocrine disrupting chemicals (EDCs) can exhibit adverse effects by increasing or blocking hormonal activities as agonists or antagonists through nuclear receptors. Computational toxicology research provides a fast and automated screening tool for determining the potential effects of EDCs. Here, we collected a large dataset of known hormonal activities to develop ternary classification models of androgen receptor (AR) and thyroid hormone receptor (TR), in combination linear discriminant analysis (LDA), classification and regression trees (CART), and support vector machines (SVM). The optimum model for classifying AR and TR activities was SVM. These newly developed models constitute a rapidly systematic early-warning technical system for identifying different hormone activities. [ABSTRACT FROM AUTHOR]

Endocrine-disrupting chemicals (EDCs), which can threaten ecological safety and be harmful to human beings, have been cause for wide concern. There is a high demand for efficient methodologies for evaluating potential EDCs in the environment. Herein an evaluation platform was developed using novel and statistically robust ternary models via different machine learning models ( i . e ., linear discriminant analysis, classification and regression tree, and support vector machines). The platform is aimed at effectively classifying chemicals with agonistic, antagonistic, or no estrogen receptor (ER) activities. A total of 440 chemicals from the literature were selected to derive and optimize the three-class model. One hundred and nine new chemicals appeared on the 2014 EPA list for EDC screening, which were used to assess the predictive performances by comparing the E -screen results with the predicted results of the classification models. The best model was obtained using support vector machines (SVM) which recognized agonists and antagonists with accuracies of 76.6% and 75.0%, respectively, on the test set (with an overall predictive accuracy of 75.2%), and achieved a 10-fold cross-validation (CV) of 73.4%. The external predicted accuracy validated by the E -screen assay was 87.5%, which demonstrated the application value for a virtual alert for EDCs with ER agonistic or antagonistic activities. It was demonstrated that the ternary computational model could be used as a faster and less expensive method to identify EDCs that act through nuclear receptors, and to classify these chemicals into different mechanism groups. [ABSTRACT FROM AUTHOR]

Compressed sensing is an alternative to Shannon/Nyquist sampling for acquiring sparse or compressible signals. Sparse coding represents a signal as a sparse linear combination of atoms, which are elementary signals derived from a predefined dictionary. Compressed sensing, sparse approximation, and dictionary learning are topics similar to sparse coding. Matrix completion is the process of recovering a data matrix from a subset of its entries, and it extends the principles of compressed sensing and sparse approximation. The nonnegative matrix factorization is a low-rank matrix factorization technique for nonnegative data. All of these low-rank matrix factorization techniques are unsupervised learning techniques, and can be used for data analysis tasks, such as dimension reduction, feature extraction, blind source separation, data compression, and knowledge discovery. In this paper, we survey a few emerging matrix factorization techniques that are receiving wide attention in machine learning, signal processing, and statistics. The treated topics are compressed sensing, dictionary learning, sparse representation, matrix completion and matrix recovery, nonnegative matrix factorization, the Nyström method, and CUR matrix decomposition in the machine learning framework. Some related topics, such as matrix factorization using metaheuristics or neurodynamics, are also introduced. A few topics are suggested for future investigation in this article. [ABSTRACT FROM AUTHOR]

There is no gold standard to tell frustrating outcomes after the catheter ablation of paroxysmal atrial fibrillation (PAF). The study aims to construct a prognostic tool. We retrospectively analyzed 315 patients with PAF who underwent first-time ablation at the Second Xiangya Hospital of Central South University. The endpoint was identified as any documented relapse of atrial tachyarrhythmia lasting longer than 30 s after the three-month blanking period. Univariate Cox regression analyzed eleven preablation parameters, followed by two supervised machine learning algorithms and stepwise regression to construct a nomogram internally validated. Five factors related to ablation failure were as follows: female sex, left atrial appendage emptying flow velocity ≤31 cm/s, estimated glomerular filtration rate <65.8 mL/(min·1.73 m2), P wave duration in lead aVF ≥ 120 ms, and that in lead V1 ≥ 100 ms, which constructed a nomogram. It was correlated with the CHA2DS2-VASc score but outperformed the latter evidently in discrimination and clinical utility, not to mention its robust performances in goodness-of-fit and calibration. In addition, the nomogram-based risk stratification could effectively separate ablation outcomes. Patients at risk of relapse after PAF ablation can be recognized at baseline using the proposed five-factor nomogram. [ABSTRACT FROM AUTHOR]

PURPOSE: A multi-cancer detection test using a targeted methylation assay and machine learning classifiers was validated and optimized for screening in prospective, case-controlled Circulating Cell-free Genome Atlas (ClinicalTrials.gov identifier: NCT02889978) substudy 3. Here, we report test performance in a subgroup of participants with symptoms suspicious for cancer to assess the test's ability to potentially facilitate efficient diagnostic evaluation in symptomatic individuals. METHODS: We evaluated test performance (sensitivity, specificity, and accuracy of cancer signal origin [CSO] prediction accuracy) in participants with clinically presenting cancers (CPCs) and noncancer with underlying medical conditions and among two subgroups (65 years and older and GI cancers). Overall survival (OS) of participants who had a cancer signal detected/not detected was compared with SEER-based expected survival. RESULTS: A total of 2,036 cancer and 1,472 noncancer participants were included. Specificity was high in all noncancer participants (99.5% [95% CI, 98.4 to 99.8]). In participants with CPCs, the overall sensitivity was 64.3% (95% CI, 62.2 to 66.4) and the overall accuracy of CSO prediction in true positives was 90.3%. For GI cancers, the overall sensitivity was 84.1% (95% CI, 80.6 to 87.1). In participants 65 years and older, test performance was similar to that of all participants. Individuals with cancers not detected had a significantly better OS than that expected from SEER (P <.01). CONCLUSION: This test detected a cancer signal with high specificity and CSO prediction accuracy and moderate sensitivity in symptomatic individuals, with especially high performance in participants with GI cancers. The survival analysis implied that the cancers not detected were less clinically aggressive than cancers detected by the test, providing prognostic insights to physicians. This multi-cancer detection test could facilitate efficient workup and stratify cancer risk in symptomatic individuals. A multicancer detection test may facilitate workup and stratification of cancer risk in symptomatic individuals. [ABSTRACT FROM AUTHOR]

Purpose: To explore the feasibility and performance of machine learning-based radiomics models in predicting thyroid transcription factor-1 (TTF-1) expression in non-small cell lung cancer (NSCLC). Methods: A total of 227 NSCLC patients were included in this retrospective study and divided into the training set and test set with a ratio of 8:2 randomly. Lung tumors on CT images were semi-automatic segmented utilizing 3D Slicer. Radiomic features quantifying tumor intensity, shape, texture, and transformed wavelet were extracted using a Python toolkit. Variance threshold (VT), principal component analysis (PCA), and least absolute shrinkage selection operator (LASSO) were used to reduce features; logistic regression (LR), random forest (RF), and support vector machine (SVM) were used to develop classifier, respectively. The performance of the models was evaluated by areas under the curves (AUC) of receiver operating characteristic (ROC) curves. Different models were compared by the Delong test to determine the optimal algorithms. Results: Total 1968 radiomic features were extracted from the lung tumors images, and then 13, 15, and 13 stable features were selected by VT, PCA, and LASSO, respectively. Each classifier could discriminate against the TTF-1-positive groups with average AUC ranging from 0.601 to 0.784 in the training set. Among the models, three models constructed by the LASSO method showed satisfactory performance in the test set with AUC ranging from 0.715 to 0.787. The Delong test showed no significant difference between the LASSO models (P > 0.05). Conclusion: Machine learning-based radiomics model could predict the expression of TTF-1 in NSCLC patients. [ABSTRACT FROM AUTHOR]

Spaceflight associated neuro-ocular syndrome (SANS) refers to a unique collection of neuro-ophthalmic clinical and imaging findings observed in astronauts after long-duration spaceflight. Current in-flight and postflight imaging modalities (e.g., optical coherence tomography, orbital ultrasound, and funduscopy) have played an instrumental role in the understanding and monitoring of SANS development; however, the precise etiology for this neuro-ophthalmic phenomenon is still not completely understood. SANS may be a potential barrier to future deep space missions, and therefore it is critical to further elucidate the underlying pathophysiology for effective countermeasures. The complexity and unique limitations of spaceflight require careful consideration and integration of leading technology to advance our knowledge of this extraterrestrial syndrome. We describe the current neuro-ophthalmic imaging modalities and hypotheses that have improved our current understanding of SANS, discuss newer developments in SANS imaging (including noninvasive near-infrared spectroscopy) and summarize emerging research in the development of an aspirational future head-mounted virtual reality display with multimodal visual assessment technology for the detection of neuro-ocular findings in SANS. [ABSTRACT FROM AUTHOR]

3D point clouds have gained much research attention because of their ability to represent the spatial information of real-world environments in a detailed manner. Despite recent progress in point cloud processing with deep neural networks, most of them either implement sophisticated local feature aggregation methods or imitate 2D convolution operations in the range of K nearest neighbors with limited local context information. These methods may struggle to distinguish between similar geometric shapes within the local region of K nearest neighbors, such as doors and walls. To address this issue, we propose a novel local–global fusion network that captures the diverse local geometric shapes with global structure information. The proposed local–global fusion network comprises two main modules. Firstly, we have developed an effective approach for local context learning using incremental dilated KNN (IDKNN) as the neighbor selecting mechanism to enlarge the receptive field and incorporate more reliable points for local geometric shape learning. Secondly, a three-direction region-wise spatial attention (TRSA) algorithm has been developed to explore the global contextual dependencies. For global context learning, we first split the entire 3D space into regions with equal numbers of points, and, then, intra-region context features are extracted to learn the inter-region relations from three orthogonal directions, taking global structural knowledge into account. By fusing the local context information and global contextual dependencies, we establish a Local-Global Fusion Network, end-to-end framework, called LGFNet. Extensive experimental results on several benchmark datasets clearly demonstrate our approach can achieve state-of-the-art (SOTA) performance on point cloud classification, part segmentation, and indoor semantic segmentation. In addition, TRSA and IKDNN can be easily used in a plug-and-play fashion with various existing SOTA networks to substantially improve their performance. Our code is available at https://github.com/jasonwjw/IDKNN • A fusion model is proposed for point cloud classification and segmentation. • Incremented dilated KNN enlarges the receptive field for local context learning. • Three-direction region-wise spatial attention captures the global context dependency. [ABSTRACT FROM AUTHOR]

Sleep disturbances are highly prevalent in movement disorders, potentially due to the malfunctioning of basal ganglia structures. Pallidal deep brain stimulation (DBS) has been widely used for multiple movement disorders and been reported to improve sleep. We aimed to investigate the oscillatory pattern of pallidum during sleep and explore whether pallidal activities can be utilized to differentiate sleep stages, which could pave the way for sleep-aware adaptive DBS. We directly recorded over 500 h of pallidal local field potentials during sleep from 39 subjects with movement disorders (20 dystonia, 8 Huntington's disease, and 11 Parkinson's disease). Pallidal spectrum and cortical-pallidal coherence were computed and compared across sleep stages. Machine learning approaches were utilized to build sleep decoders for different diseases to classify sleep stages through pallidal oscillatory features. Decoding accuracy was further associated with the spatial localization of the pallidum. Pallidal power spectra and cortical-pallidal coherence were significantly modulated by sleep-stage transitions in three movement disorders. Differences in sleep-related activities between diseases were identified in non-rapid eye movement (NREM) and REM sleep. Machine learning models using pallidal oscillatory features can decode sleep-wake states with over 90% accuracy. Decoding accuracies were higher in recording sites within the internus-pallidum than the external-pallidum, and can be precited using structural (P < 0.0001) and functional (P < 0.0001) whole-brain neuroimaging connectomics. Our findings revealed strong sleep-stage dependent distinctions in pallidal oscillations in multiple movement disorders. Pallidal oscillatory features were sufficient for sleep stage decoding. These data may facilitate the development of adaptive DBS systems targeting sleep problems that have broad translational prospects. • Pallidal activities during sleep are recorded in 39 patients with dystonia, HD, or PD. • Pallidal spectra and connectivity with cortex are modulated by sleep-wake transitions. • Differences in sleep-related activities may underly disease-specific abnormalities. • Pallidal activity-based ML decoder predicts sleep stages with accuracies of over 90%. • Decoding accuracies are influenced by the anatomical localization of the DBS lead. [ABSTRACT FROM AUTHOR]

Smartphone has long been considered as one excellent platform for disease screening and diagnosis, especially when combined with microfluidic paper-based analytical devices (μPADs) that feature low cost, ease of use, and pump-free operations. In this paper, we report a deep learning-assisted smartphone platform for ultra-accurate testing of paper-based microfluidic colorimetric enzyme-linked immunosorbent assay (c-ELISA). Different from existing smartphone-based μPAD platforms, whose sensing reliability is suffered from uncontrolled ambient lighting conditions, our platform is able to eliminate those random lighting influences for enhanced sensing accuracy. We first constructed a dataset that contains c-ELISA results (n = 2048) of rabbit IgG as the model target on μPADs under eight controlled lighting conditions. Those images are then used to train four different mainstream deep learning algorithms. By training with these images, the deep learning algorithms can well eliminate the influences of lighting conditions. Among them, the GoogLeNet algorithm gives the highest accuracy (>97%) in quantitative rabbit IgG concentration classification/prediction, which also provides 4% higher area under curve (AUC) value than that of the traditional curve fitting results analysis method. In addition, we fully automate the whole sensing process and achieve the "image in, answer out" to maximize the convenience of the smartphone. A simple and user-friendly smartphone application has been developed that controls the whole process. This newly developed platform further enhances the sensing performance of μPADs for use by laypersons in low-resource areas and can be facilely adapted to the real disease protein biomarkers detection by c-ELISA on μPADs. [Display omitted] • This deep learning-assisted smartphone platform is unaffected by ambient lighting. • A fully automated "image in, answer out" operation fashion. • A 2048 custom image dataset is used to test 4 mainstream deep learning algorithms. • GoogLeNet provides >97% accuracy in quantitative rabbit IgG testing. • The area under the curve (AUC) is 4% higher than that of conventional methods. [ABSTRACT FROM AUTHOR]