Search Results (36)

Cirrhosis, accounting for 2.4% of global mortality in 2019, represents a leading cause of death in chronic liver disease. Hepatic encephalopathy (HE), a decompensated complication of cirrhosis, is associated with a median survival of only 0.92 years post-diagnosis. Current screening methods relying on neuropsychological tests (e.g., Psychometric Hepatic Encephalopathy Score, PHES) have limitations such as time-consuming procedures and subjective interpretation, potentially delaying diagnosis. To address this, we integrated four cirrhotic transcriptomic cohorts (GSE41919, GSE57193, GSE139602, and GSE15654) and employed an integrated algorithm (LASSO [Least Absolute Shrinkage and Selection Operator]–RFE [Recursive Feature Elimination]–random forest) to identify HE-specific biomarker genes. Ultimately, we developed an HE risk-prediction system centered on eight HE-specific marker genes, namely, PRB2, TUBA1C, NPC2, LRRC32, TLN1, SOX9, SERPINA3 and RNASE4. Based on these genes, an XGBoost (eXtreme Gradient Boosting)-based HE risk stratification model was constructed, and SHAP (SHapley Additive exPlanations) analysis was further introduced to address the “black-box” limitation of conventional machine learning models and to improve the interpretability. The finalized eight-gene system enables accurate, efficient, and interpretable HE risk assessment in patients with cirrhosis. Functional characterization through gene set enrichment analysis and structural equation modeling further revealed that these marker genes converge on four interconnected biological processes, namely, metabolic homeostasis, synaptic and neural transmission, immune inflammatory signaling, and hepatic detoxification, which collectively reflect the gut–liver–brain axis disruption central to HE pathogenesis. This dual-model system, incorporating both cirrhosis progression and survival prognosis, provides a reliable and clinically applicable tool for early HE risk warning and stratification, reducing the limitations of traditional neuropsychological screening and offering a translational foundation for timely intervention and prognostic optimization in high-risk cirrhotic patients. Full article

To address the issues of vibration blind spots and the “black box” of quality control in the vibration process of precast beams caused by dense reinforcement zones and the arbitrariness of manual operation, this paper proposes the development of a closed-loop intelligent vibration system. This system integrates intelligent equipment, evaluation models, adaptive algorithms, and digital twin feedback control. By combining drum-type vibration robots for large-scale operations with wearable sensing devices for complex dead corners, full coverage of the operation area is achieved. Second, based on the coupling mechanism of mechanical-electrical-hydraulic multi-physics fields, a quantitative evaluation model for vibration compactness is established. Furthermore, a hierarchical adaptive control strategy based on feedback of the rheological state is designed. By fusing real-time positioning data with vibration energy indices, process parameters such as vibration frequency and duration are dynamically optimized. Finally, through the developed digital twin feedback control platform, a vibration energy cloud map reflecting the internal quality can be generated in real time, thereby achieving process visualization and early warning of defects. Results show that the system can accurately detect and resolve missed and insufficient vibration issues. Construction activities are thus managed via data rather than subjective empirical judgment. Full article

Global supply chains are increasingly exposed to multi-source uncertainties, ranging from geopolitical tensions to climate extremes, making the accurate and interpretable prediction of disruptions an urgent operational priority. Existing predictive models often rely on either shallow statistical learners, which struggle with high-dimensional interactions, or deep neural networks, which trade off interpretability for marginal performance gains. To address this gap, we propose an interpretable machine learning framework that couples a feature-attention mechanism with a gradient-boosted decision tree ensemble for early warning of shipment-level disruption events. First, a dedicated attention module is trained to assign importance weights to 14 heterogeneous risk factors, generating an interpretable feature ranking that highlights pivotal signals such as lead-time volatility and geopolitical risk. The reweighted features are then fed into a gradient boosting classifier, which effectively captures non-linear patterns and interaction effects. Evaluated on a publicly available dataset of 5000 international freight records available on Kaggle, the proposed framework achieves an AUC of 0.8213 (±0.0002 over three independent runs), matching the best-performing baseline (standard gradient boosting, 0.8212 ± 0.0001) and surpassing logistic regression (0.777), random forest (0.806), and a standalone feature-attention network (0.805). The attention module preserves full predictive accuracy while adding an interpretability layer that conventional black-box implementations lack. Notably, the framework preserves the predictive accuracy of gradient boosting while enhancing interpretability through attention-based feature ranking and dual-perspective importance analysis, achieving a precision of 0.770 and a balanced F1-score of 0.781. The convergence of attention-based interpretability and ensemble learning efficiency provides supply chain managers with a transparent decision-support tool—distinguishing genuine “tipping points” from “false alarms” and enabling targeted risk mitigation under deep uncertainty. Full article

Atopic dermatitis (AD) is a common chronic inflammatory condition of the skin that has increased dramatically over the past decade and significantly impacts individual quality of life. Corticosteroids are still the primary therapy for AD, but there are limitations to their continued use due to potential adverse effects, particularly when used in sensitive areas. Topical calcineurin inhibitors (CNIs), such as tacrolimus and pimecrolimus, are available as a safe, steroid-sparing alternative that directly inhibit calcineurin-mediated activation of T cells and have been shown to be efficacious according to varying clinical study designs including randomized controlled trials, registry studies and meta-analyses. Although there was controversy regarding the safety of CNIs subsequent to the FDA’s black-box warning in 2006, the preponderance of evidence supports their continued safety when used as directed. In contrast to biologics and JAK inhibitors, CNIs occupy an inherently unique therapeutic niche for use in pediatric patients, have demonstrated historical efficacy, and can provide localized affordable treatment in sensitive areas including the face, eyelids and intertriginous surfaces. Furthermore, the role of CNIs in the context of precision dermatology continues to be defined through new innovations including barrier-repair strategies used in combination with topical medications, microneedle systems, and nanocarrier formulations. Hence, the role of CNIs in the current AD treatment paradigm is crucial and lies at the interface between topical corticosteroids and systemic immunomodulatory agents. The narrative review discusses recent advances in formulation strategies, combination approaches, and targeted delivery systems, underscoring how CNIs continue to bridge established practice and emerging therapeutic innovation in AD. Full article

Coal spontaneous combustion in gob areas is a major disaster endangering safe production in underground coal mines, and accurate prediction of carbon monoxide (CO), the core signature gas of coal oxidation, is critical for early warning and targeted prevention of mine fire disasters. However, CO concentration in gob areas is governed by complex gas–solid thermal–chemical multi-field coupling, presenting strong nonlinear characteristics. Traditional numerical methods suffer from prohibitive computational cost, purely data-driven models have inherent black-box defects, and conventional Physics-Informed Neural Networks (PINNs) require explicit full governing equations, which are hard to establish for such complex systems. This paper first proposes a Physics-Informed Modified Kolmogorov–Arnold Network (PIM-KAN), which deeply integrates domain physical knowledge with KAN architecture via a physics encoding layer, a residual-modified KAN layer, a multi-physics attention mechanism, and a multi-term physical consistency constraint framework. Experiments on 3125 real coal mine field samples show that the PIM-KAN achieves R² = 0.9965 and RMSE = 0.9290 ppm, reducing RMSE by 19.5% compared with MLP, and outperforming all baseline models. Ablation studies confirm the significant contribution of each innovation module, and attention weight analysis is highly consistent with Arrhenius reaction kinetics, verifying its superior prediction accuracy, physical consistency and intrinsic interpretability. Full article

Extreme meteorological phenomena—characterized by gale-force winds, torrential rainfall, and ice-snow accumulation—pose significant threats to the operational safety of high-speed railways, with wind-induced hazards being especially critical. Such events can trigger catastrophic incidents, including train derailments and service disruptions, as evidenced by numerous documented cases worldwide. To bolster the wind resilience of high-speed railway systems, high-precision wind speed prediction has become a cornerstone for ensuring operational safety. This research presents a systematic review of international advancements in railway wind early warning systems, critically evaluating the technical attributes and performance constraints of four primary paradigms: physical numerical models, statistical methods, machine learning algorithms, and hybrid frameworks. Moving beyond a simple taxonomy, this paper delineates the strengths, limitations, and domain-specific applicability of each approach within the high-speed railways context. Furthermore, it assesses the transformative potential of emerging large-scale Artificial Intelligence (AI) meteorological models for wind speed forecasting. A quantitative comparison is provided to facilitate rigorous methodological assessment. The findings reveal four critical technical bottlenecks: (1) low computational efficiency of numerical models; (2) insufficient spatiotemporal resolution of monitoring data; (3) poor generalization of predictive models; and (4) the “black-box” nature and weak interpretability of AI models. To address these, this paper posits that future research should prioritize key technologies including multi-source heterogeneous data fusion, algorithmic optimization, design of intelligent algorithms, probabilistic risk forecasting, and the synergistic integration of AI with numerical weather prediction (NWP). Such advancements will catalyze the development of more robust HSR wind warning systems, ensuring sustained safety and operational efficiency under volatile meteorological conditions. Full article

The motion prediction of semi-submersible platforms is of significant importance for improving operational efficiency, ensuring platform safety, and providing early warning information for potential risks. Traditional prediction methods, such as those based on hydrodynamic simulations combined with Kalman filters, often face limitations due to their reliance on precise hydrodynamic parameters, which are difficult to obtain in practice. More recently, data-driven approaches, particularly deep learning models like Long Short-Term Memory (LSTM) networks, have shown promise in predicting complex motions. However, these methods often treat the prediction process as a “black box,” leading to issues such as a lack of generalization ability, overfitting, and an inability to quantify the uncertainty of prediction results. To address these challenges, this paper proposes a novel motion prediction method for semi-submersible platforms based on a Bayesian neural network (BNN). The BNN incorporates Bayesian inference to effectively integrate prior knowledge and measured data, thereby quantifying uncertainties and improving prediction accuracy. The method is validated using field-measured motion data from a semi-submersible platform in the South China Sea. Compared with LSTM and feedforward neural network, the BNN demonstrates superior anti-noise performance and prediction accuracy, achieving an accuracy rate (R²) of up to 91.5%. Moreover, over 92% of the true values are captured within the 95% confidence interval of the prediction results. This study highlights the potential of BNNs for the real-time motion prediction of offshore platforms, providing valuable support for early warning systems and operational decision-making. Full article

Postural orthostatic tachycardia syndrome (POTS), characterized by a rise in heart rate of at least 30 beats per minute from supine to standing position without accompanying orthostatic hypotension, is one of the most common autonomic disorders with disabling cardiovascular and neurologic manifestations. Hormonal influence has been long recognized by the disorder predominantly affecting women of reproductive age, with frequent onset around menarche, exacerbation of symptoms before or during menses, and pregnancy being one of POTS triggers. Hormone replacement therapy (HRT) and menopause in women with POTS have not been studied, but issues surrounding HRT are highly relevant as women with POTS transition from reproductive age to menopause. Given a rising prevalence of POTS due to post-COVID onset and the US Food and Drug Administration recently removing the black box warning on estrogen-containing HRT formulations, informed decisions and risk assessments regarding HRT use in women with POTS are warranted. In this narrative review, existing studies on hormones and POTS and its common comorbidities are reviewed, and key points in decision-making on the use of HRT in women with POTS are discussed. In summary, for women with significant menopausal symptoms and/or exacerbation of POTS during the peri- or postmenopausal period, using some forms of HRT for treatment of menopausal symptoms may be considered, accounting for comorbidities, cardiovascular risk and other factors. Vaginal estrogen appears to be safe for most women while transdermal estrogen and micronized progesterone can be utilized for significant menopausal symptoms, although outcomes of their long-term use are unknown. Full article

Locust outbreaks cause a significant threat to global food security and ecosystem stability, with particularly severe consequences in grassland regions, where grasshoppers also exert considerable ecological pressure. In comparison to grasshoppers, locusts typically occur at much larger spatial scales, as their strong migratory ability and collective movement behavior lead to greater spatial connectivity and autocorrelation. The forecasting of both locust and grasshopper outbreaks remains a formidable scientific challenge, primarily due to the complex, nonlinear spatiotemporal interactions among environmental drivers such as weather, vegetation, and soil conditions. This review compares the evolution of prediction methodologies for locust and grasshopper outbreaks, focusing on the application of deep learning (DL) methods to ecological forecasting tasks. It traces the development from traditional statistical models to classical machine learning, and ultimately to DL, assessing the strengths and limitations of key DL architectures—including Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRUs)—in modeling the intricate dynamics of locust populations. While most studies have concentrated on locust outbreaks, this review emphasizes the adaptation of these models to grassland ecosystems, such as those in Inner Mongolia, where grasshopper outbreaks exhibit similarities to locust plagues but have been largely overlooked in DL research. Despite the potential of DL, challenges such as data scarcity, limited model generalizability across regions, and the “black box” issue of low interpretability remain. To address these issues, we propose future research directions that integrate Explainable AI (XAI), transfer learning, and generative models like GANs to development more robust, transparent, and ecologically grounded forecasting tools. By promoting the use of efficient architectures like GRUs within customized frameworks, this review aims to guide the development of effective early warning systems for sustainable locust management in vulnerable grassland ecosystems. Full article

In recent years, financial statement fraud schemes have evolved to become markedly more sophisticated and concealed, thereby posing severe threats to both social stability and economic health. Traditional detection methods, which rely primarily on fragmented corporate data, exhibit significant limitations in capturing the dynamic evolution and spatial diffusion characteristics of fraudulent behaviors over time and space. To address this issue, in this study, we undertake a thorough analysis of the intrinsic nature of fraud risk from a sociotechnical systems perspective and construct a multi-level indicator system to comprehensively quantify risk elements. Furthermore, recognizing the dynamic evolution nature and propagating characteristics of fraud risk, we propose a novel financial statement fraud detection framework to capture behavior patterns in temporal and spatial dimensions. Experiments on A-share-listed companies of high-risk industries in China demonstrate that the proposed framework significantly outperforms other mainstream machine learning and deep learning techniques. In addition, we open the “black box” of the detection framework and empirically validate fraud risk patterns with respect to social–technical elements by leveraging explainable AI techniques. Practically, the proposed framework and interpretable analysis are capable of providing precise early warnings and supervision. Full article

Recent advancements in large language models (LLMs) have increased the necessity of alignment and safety mechanisms. Despite these efforts, jailbreak attacks remain a significant threat, exploiting vulnerabilities to elicit harmful responses. While white-box attacks, such as the Greedy Coordinate Gradient (GCG) method, have demonstrated promise, their efficacy is often limited by non-smooth optimization landscapes and a tendency to converge to local minima. To mitigate these issues, we propose Spatial Momentum GCG (SM-GCG), a novel method that incorporates spatial momentum. This technique aggregates gradient information across multiple transformation spaces—including text, token, one-hot, and embedding spaces—to stabilize the optimization process and enhance the estimation of update directions, thereby more effectively exploiting model vulnerabilities to elicit harmful responses. Experimental results on models including Vicuna-7B, Guanaco-7B, and Llama2-7B-Chat demonstrate that SM-GCG significantly enhances the attack success rate in white-box settings. The method achieves a 10–15% improvement in attack success rate over baseline methods against robust models such as Llama2, while also exhibiting enhanced transferability to black-box models. These findings indicate that spatial momentum effectively mitigates the problem of local optima in discrete prompt optimization, thereby offering a more powerful and generalizable approach for red-team assessments of LLM safety. Warning: This paper contains potentially offensive and harmful text. Full article

Groundwater level (GWL) prediction in arid regions faces two fundamental challenges in conventional numerical modeling: (i) irreducible parameter uncertainty, which systematically reduces predictive accuracy; (ii) oversimplification of nonlinear process interactions, which leads to error propagation. Although machine learning (ML) methods demonstrate strong nonlinear mapping capabilities, their standalone applications often encounter prediction bias and face the accuracy–generalization trade-off. This study proposes a hybrid TCN–Transformer–LSTM (TTL) model designed to address three key challenges in groundwater prediction: high-frequency fluctuations, medium-range dependencies, and long-term memory effects. The TTL framework integrates TCN layers for short-term features, Transformer blocks to model cross-temporal dependencies, and LSTM to preserve long-term memory, with residual connections facilitating hierarchical feature fusion. The results indicate that (1) at the monthly scale, TTL reduced RMSE by 20.7% (p < 0.01) and increased R² by 0.15 compared with the Groundwater Modeling System (GMS); (2) during abrupt hydrological events, TTL achieved superior performance (R² = 0.96–0.98, MAE < 0.6 m); (3) PCA revealed site-specific responses, corroborating the adaptability and interpretability of TTL; (4) Grad-CAM analysis demonstrated that the model captures physically interpretable attention mechanisms—particularly evapotranspiration and rainfall—thereby providing clear cause–effect explanations and enhancing transparency beyond black-box models. This transferable framework supports groundwater forecasting, risk warning, and practical deployment in arid regions, thereby contributing to sustainable water resource management. Full article

Background/objectives: In 9/2020, the United States Food and Drug Administration )FDA( posted a black box warning for all benzodiazepines, addressing their association with serious risks of abuse, addiction, physical dependence, and withdrawal reactions. We evaluated changes in benzodiazepine dispensing rate trends after this warning. Methods: The dataset of Clalit Health Services (Israel’s largest insurer, with 5 million members) was used to identify and collect benzodiazepine dispensing data for all patients who were dispensed these drugs at least once during the study period (1/2017–12/2021). The dispensing rate (number of patients who were dispensed benzodiazepines per month divided by the number of patients alive during that month) was calculated for each month in the study period. Linear regression and change point regression were used to review the change in trend before and after the black box warning. New users of benzodiazepines after the black box warning were analyzed by age. Results: A total of 639,515 patients using benzodiazepines were reviewed. The mean benzodiazepine dispensing rate per month was 0.21 and ranged from 0.17 (in 2/2017) to 0.24 (in 3/2020). No significant change in trend was observed before vs. after the black box warning (slopes of 0.00675 percentage points per month and 0.00001 percentage points per month, respectively; p = 0.38). The change point regression analysis identified a change point in 4/2019, which is prior to the black box warning. New users were younger after the black box warning compared to before this warning. Conclusions: The FDA black box warning did not affect the dispensing rate of benzodiazepines. Full article

The mRNA vaccine has protected humans from the Coronavirus disease 2019 (COVID-19) and has taken the lead in reversing the epidemic efficiently. However, the Centre of Disease Control (CDC) reported and raised the alarm of allergic or acute inflammatory adverse reactions after vaccination with mRNA-LNP vaccines. Meanwhile, the US Food and Drug Administration (FDA) has added four black-box warnings in the instructions for mRNA-LNP vaccines. Numerous studies have proven that the observance of side effects after vaccination is indeed positively correlated to the level of anti-PEG antibodies (IgM or IgG), which are enhanced by PEGylated preparations like LNP vaccine and environmental exposure. After literature research and review in the past two decades, it was found that the many clinical trial failures (BIND-014, RB006 fell in phase II) of PEG modified delivery system or PEGylated drug were related to the high expression of anti-PEG IgM and IgG. In the background of shooting multiple mRNA-LNP vaccines in billions of people around the world in the past three years, the level of anti-PEG antibodies in the population may have significantly increased, which brings potential risks for PEG-modified drug development and clinical safety. This review summarizes the experience of using mRNA-LNP vaccines from the mechanism of the anti-PEG antibodies generation, detection methods, clinical failure cases of PEG-containing products, harm analysis of abuse of PEGylation, and alternatives. In light of the increasing prevalence of anti-PEG antibodies in the population and the need to avoid secondary injuries, this review article holds greater significance by offering insights for drug developers. It suggests avoiding the use of PEG excipients when designing PEGylated drugs or PEG-modified nano-formulations and provides references for strategies such as utilizing PEG-free or alternative excipients. Full article

Sclerostin, encoded by the SOST gene, is a novel bone anabolic target for bone diseases. Humanized anti-sclerostin antibody, romosozumab, was approved for treatment of postmenopausal osteoporosis by the US Food and Drug Administration (FDA), but with a black-box warning on cardiovascular risk. The clinical data regarding cardiovascular events from various pre-marketing and post-marketing studies of romosozumab were inconsistent. Overall, the cardiovascular risk of sclerostin inhibition could not be excluded. The restriction of romosozumab in patients with cardiovascular disease history would be necessary. Moreover, genome-wide association study (GWAS) analyses of SOST variants revealed inconsistent results of the association between SOST variations and cardiovascular diseases. Further research incorporating larger sample sizes and functional analyses are necessary. In analyses of serum/tissue sclerostin levels in patients with cardiovascular diseases, the results were controversial but indicated an association between sclerostin and the presence/severity/outcomes of cardiovascular diseases. Nonclinical studies in rodents indicated the inhibitory effect of sclerostin on inflammation, aortic aneurysm, atherosclerosis, and vascular calcification. Sclerostin loop3 participated in the inhibitory effect of sclerostin on bone formation, while the cardiovascular protective effect of sclerostin was independent of sclerostin loop3. Macrophagic sclerostin loop2–apolipoprotein E receptor 2 (ApoER2) interaction participated in the inhibitory effect of sclerostin on inflammation in vitro. Sclerostin in human aortic smooth muscle cells participated in the reduction in calcium deposition. The role of sclerostin in cardiovascular system deserves further investigation. Full article