Search for: All records

Abstract BackgroundEmerging evidence indicates an elevated risk of post-concussion musculoskeletal injuries in collegiate athletes; however, identifying athletes at highest risk remains to be elucidated. ObjectiveThe purpose of this study was to model post-concussion musculoskeletal injury risk in collegiate athletes by integrating a comprehensive set of variables by machine learning. MethodsA risk model was developed and tested on a dataset of 194 athletes (155 in the training set and 39 in the test set) with 135 variables entered into the analysis, which included participant’s heath and athletic history, concussion injury and recovery-specific criteria, and outcomes from a diverse array of concussion assessments. The machine learning approach involved transforming variables by the weight of evidence method, variable selection using L1-penalized logistic regression, model selection via the Akaike Information Criterion, and a final L2-regularized logistic regression fit. ResultsA model with 48 predictive variables yielded significant predictive performance of subsequent musculoskeletal injury with an area under the curve of 0.82. Top predictors included cognitive, balance, and reaction at baseline and acute timepoints. At a specified false-positive rate of 6.67%, the model achieves a true-positive rate (sensitivity) of 79% and a precision (positive predictive value) of 95% for identifying at-risk athletes via a well-calibrated composite risk score. ConclusionsThese results support the development of a sensitive and specific injury risk model using standard data combined with a novel methodological approach that may allow clinicians to target high injury risk student athletes. The development and refinement of predictive models, incorporating machine learning and utilizing comprehensive datasets, could lead to improved identification of high-risk athletes and allow for the implementation of targeted injury risk reduction strategies by identifying student athletes most at risk for post-concussion musculoskeletal injury. 

Abstract BackgroundEmerging evidence indicates an elevated risk of post-concussion musculoskeletal (MSK) injuries in collegiate athletes; however, identifying athletes at highest risk remains to be elucidated. ObjectiveThe purpose of this study was to model post-concussion MSK injury risk in collegiate athletes by integrating a comprehensive set of variables by machine learning. MethodsA risk model was developed and tested on a dataset of 194 athletes (155 in the training set and 39 in the test set) with 135 variables entered into the analysis, which included participant’s heath and athletic history, concussion injury and recovery specific criteria, and outcomes from a diverse array of concussions assessments. The machine learning approach involved transforming variables by the Weight of Evidence method, variable selection using L1-penalized logistic regression, model selection via the Akaike Information Criterion, and a final L2-regularized logistic regression fit. ResultsA model with 48 predictive variables yielded significant predictive performance of subsequent MSK injury with an area under the curve of 0.82. Top predictors included cognitive, balance, and reaction at Baseline and Acute timepoints. At a specified false positive rate of 6.67%, the model achieves a true positive rate (sensitivity) of 79% and a precision (positive predictive value) of 95% for identifying at-risk athletes via a well calibrated composite risk score. ConclusionThese results support the development of a sensitive and specific injury risk model using standard data combined with a novel methodological approach that may allow clinicians to target high injury risk student-athletes. The development and refinement of predictive models, incorporating machine learning and utilizing comprehensive datasets, could lead to improved identification of high-risk athletes and allow for the implementation of targeted injury risk reduction strategies by identifying student-athletes most at risk for post-concussion MSK injury. Key PointsThere is a well-established elevated risk of post-concussion subsequent musculoskeletal injury; however, prior efforts have failed to identify risk factors.This study developed a composite risk score model with an AUC of 0.82 from common concussion clinical measures and participant demographics.By identifying athletes at elevated risk, clinicians may be able to reduce injury risk through targeted injury risk reduction programs. 

Abstract Reactive sulfane sulfur species such as persulfides (RSSH) and H₂S₂are important redox regulators and closely linked to H₂S signaling. However, the study of these species is still challenging due to their instability, high reactivity, and the lack of suitable donors to produce them. Herein we report a unique compound,2H-thiopyran-2-thione sulfine (TTS), which can specifically convert H₂S to HSOH, and then to H₂S₂in the presence of excess H₂S. Meanwhile, the reaction product2H-thiopyran-2-thione (TT) can be oxidized to reform TTS by biological oxidants. The reaction mechanism of TTS is studied experimentally and computationally. TTS can be conjugated to proteins to achieve specific delivery, and the combination of TTS and H₂S leads to highly efficient protein persulfidation. When TTS is applied in conjunction with established H₂S donors, the corresponding donors of H₂S₂(or its equivalents) are obtained. Cell-based studies reveal that TTS can effectively increase intracellular sulfane sulfur levels and compensate for certain aspects of sulfide:quinone oxidoreductase (SQR) deficiency. These properties make TTS a conceptually new strategy for the design of donors of reactive sulfane sulfur species. 

Interpreting deep neural networks through examining neurons offers distinct advantages when it comes to exploring the inner workings of Deep Neural Networks. Previous research has indicated that specific neurons within deep vision networks possess semantic meaning and play pivotal roles in model performance. Nonetheless, the current methods for generating neuron semantics heavily rely on human intervention, which hampers their scalability and applicability. To address this limitation, this paper proposes a novel post-hoc framework for generating semantic explanations of neurons with large foundation models, without requiring human intervention or prior knowledge. Experiments are conducted with both qualitative and quantitative analysis to verify the effectiveness of our proposed approach. 

Hypergraph neural networks (HyperGNNs) are a family of deep neural networks designed to perform inference on hypergraphs. HyperGNNs follow either a spectral or a spatial approach, in which a convolution or message-passing operation is conducted based on a hypergraph algebraic descriptor. While many HyperGNNs have been proposed and achieved state-of-the-art performance on broad applications, there have been limited attempts at exploring high-dimensional hypergraph descriptors (tensors) and joint node interactions carried by hyperedges. In this article, we depart from hypergraph matrix representations and present a new tensor-HyperGNN (T-HyperGNN) framework with cross-node interactions (CNIs). The T-HyperGNN framework consists of T-spectral convolution, T-spatial convolution, and T-message-passing HyperGNNs (T-MPHN). The T-spectral convolution HyperGNN is defined under the t-product algebra that closely connects to the spectral space. To improve computational efficiency for large hypergraphs, we localize the T-spectral convolution approach to formulate the T-spatial convolution and further devise a novel tensor-message-passing algorithm for practical implementation by studying a compressed adjacency tensor representation. Compared to the state-of-the-art approaches, our T-HyperGNNs preserve intrinsic high-order network structures without any hypergraph reduction and model the joint effects of nodes through a CNI layer. These advantages of our T-HyperGNNs are demonstrated in a wide range of real-world hypergraph datasets. The implementation code is available at https://github.com/wangfuli/T-HyperGNNs.git. 

Given the availability of abundant data, deep learning models have been advanced and become ubiquitous in the past decade. In practice, due to many different reasons (e.g., privacy, usability, and fidelity), individuals also want the trained deep models to forget some specific data. Motivated by this, machine unlearning (also known as selective data forgetting) has been intensively studied, which aims at removing the influence that any particular training sample had on the trained model during the unlearning process. However, people usually employ machine unlearning methods as trusted basic tools and rarely have any doubt about their reliability. In fact, the increasingly critical role of machine unlearning makes deep learning models susceptible to the risk of being maliciously attacked. To well understand the performance of deep learning models in malicious environments, we believe that it is critical to study the robustness of deep learning models to malicious unlearning attacks, which happen during the unlearning process. To bridge this gap, in this paper, we first demonstrate that malicious unlearning attacks pose immense threats to the security of deep learning systems. Specifically, we present a broad class of malicious unlearning attacks wherein maliciously crafted unlearning requests trigger deep learning models to misbehave on target samples in a highly controllable and predictable manner. In addition, to improve the robustness of deep learning models, we also present a general defense mechanism, which aims to identify and unlearn effective malicious unlearning requests based on their gradient influence on the unlearned models. Further, theoretical analyses are conducted to analyze the proposed methods. Extensive experiments on real-world datasets validate the vulnerabilities of deep learning models to malicious unlearning attacks and the effectiveness of the introduced defense mechanism. 

Abstract Functional magnetic resonance imaging faces inherent challenges when applied to deep-brain areas in rodents, e.g. entorhinal cortex, due to the signal loss near the ear cavities induced by susceptibility artifacts and reduced sensitivity induced by the long distance from the surface array coil. Given the pivotal roles of deep brain regions in various diseases, optimized imaging techniques are needed. To mitigate susceptibility-induced signal losses, we introduced baby cream into the middle ear. To enhance the detection sensitivity of deep brain regions, we implemented inductively coupled ear-bars, resulting in approximately a 2-fold increase in sensitivity in entorhinal cortex. Notably, the inductively coupled ear-bar can be seamlessly integrated as an add-on device, without necessitating modifications to the scanner interface. To underscore the versatility of inductively coupled ear-bars, we conducted echo-planner imaging-based task functional magnetic resonance imaging in rats modeling Alzheimer’s disease. As a proof of concept, we also demonstrated resting-state-functional magnetic resonance imaging connectivity maps originating from the left entorhinal cortex—a central hub for memory and navigation networks-to amygdala hippocampal area, Insular Cortex, Prelimbic Systems, Cingulate Cortex, Secondary Visual Cortex, and Motor Cortex. This work demonstrates an optimized procedure for acquiring large-scale networks emanating from a previously challenging seed region by conventional magnetic resonance imaging detectors, thereby facilitating improved observation of functional magnetic resonance imaging outcomes.