Search Results (8,397)

Human digital twins (HDTs) are patient-specific computational models that combine medical imaging, physiological measurements and predictive algorithms. They are moving from an exciting concept to a realistic clinical opportunity. The key question is no longer whether HDTs can be built. The key question is which methods are mature enough to support clinical decisions and what is still missing for routine use. This systematic review maps the methodological landscape of HDTs and highlights practical bottlenecks that limit clinical translation. A PRISMA 2020 guided search of PubMed, Scopus, IEEE Xplore, and the Cochrane Library, covering publications from 2016 to 2026, identified 151 eligible studies. Bibliometric mapping and thematic synthesis were used to characterize research clusters, computational paradigms, and collaboration patterns. Three dominant application streams were identified: cardiovascular HDTs for hemodynamic simulation and procedural planning, musculoskeletal HDTs for biomechanics-driven orthopedic innovation, and neurological HDTs integrating neuroimaging with computational neuroscience. Across domains, the strongest technical trend is the rise in hybrid pipelines that combine physics-based simulation, including finite element and computational fluid dynamics models, with machine learning for segmentation, parameter identification, reduced-order modeling, and faster inference. However, reporting of verification, validation, uncertainty quantification, and explicit context of use remains uneven and prospective clinical evidence is still limited. Overall, the literature shows rapid progress toward clinically credible HDTs, while highlighting the need for scalable computation, standardized credibility pipelines, and workflow-integrated platforms to support safe and reproducible clinical adoption. Full article

Background: A subgroup of adolescent and young adult patients (AYAs; 18 to 39 years at diagnosis) face an uncertain or poor cancer prognosis (UPCP). Previous qualitative research identified dual coping pathways in this population: engagement in life versus the reality of premature death. This study examines whether similar psychosocial profiles can be identified through quantitative data, aiming to differentiate patient experiences and identify characteristic features of each cluster. Additionally, this study examines the association between cluster membership and social support needs to understand psychosocial disparities. Methods: Eligible participants completed questionnaires assessing physical, psychosocial, and existential outcomes related to their disease and prognosis. An ensemble clustering approach was applied, including evaluation of clustering tendency and multiple algorithms, with stable clusters identified through majority voting. Associations with social support needs were analyzed using Fisher’s exact test. Results: Data from 155 AYAs with a UPCP were included. The mean age at diagnosis was 31.2 years, with glioma (34.8%) and breast cancer (17.4%) as the most common diagnoses. Two distinct clusters were identified: one (22%) characterized by poorer functional outcomes and fewer protective factors (e.g., hope, meaning in life), and another cluster (78%) with better functioning and less frequent needs for social support (p < 0.00043). Conclusions: Findings revealed divergent psychosocial profiles within the AYA-UPCP population, highlighting the importance of early identification of vulnerable subgroups. Strengthening protective factors may enhance resilience and reduce unmet support needs. Validation in larger, external datasets is needed to confirm these pathways and guide tailored supportive care strategies. Full article

This paper investigates the feasibility of 3D self-localization and tracking using chipless radio frequency identification (RFID) tags operating in the terahertz (THz) frequency band. The primary objective is to achieve sub-millimeter (sub-mm) localization and tracking accuracy while minimizing reliance on external infrastructure. To this end, a hybrid localization framework is proposed that jointly exploits round-trip time-of-flight (RToF) and angle-of-arrival (AoA) measurements to enhance localization performance. Although near-field propagation effects are inherently significant in the considered THz operating regime, a simplified far-field approximation is adopted to facilitate tractable system modeling and analytical development. The proposed framework is further extended to dynamic scenarios through an extended Kalman filter (EKF)-based tracking algorithm, which incorporates temporal state evolution to improve estimation robustness under noisy measurements. Furthermore, the Cramér–Rao lower bound (CRLB) for the hybrid RToF-AoA system is derived to establish the fundamental limits of localization accuracy under varying system configurations and measurement conditions. Simulation results demonstrate that the proposed approach is capable of achieving sub-mm localization and tracking accuracy with a highly constrained anchor infrastructure, including operation with a single anchor in the considered scenario. These findings highlight the potential of THz chipless RFID technology as a promising enabling solution for next-generation high-accuracy localization and tracking applications. Full article

Large-amplitude and long-term vibration deformation under external environmental loads often occurs on tensile membrane structures. Proper sensor placement plays a vital role in effectively achieving the objectives of a structural health monitoring system. In order to optimize the sensor placement to identify the modal vibration parameters for tensile membrane structures, this paper proposes an optimal sensor placement method based on the Fisher information matrix (FIM) and improved random strategy discrete particle swarm optimization algorithm (IRSDPSO). Firstly, the structural modal order is selected by using the two-norm difference and trace change rate of FIM, and the number of sensors is determined based on the QR decomposition and MAC criterion. Secondly, an improved particle swarm optimization algorithm named IRSDPSO, which has the discrete characteristic, is proposed to arrange the placement of sensors. Finally, the convergence, stability and sensitivity are used to evaluate the effectiveness of optimal sensor placement results using a numerical modal test example of the plane bidirectional tensile membrane structure. The results show that the first nineteen modal frequencies can be accurately identified. This indicates that the proposed optimal sensor placement method can determine the number of sensors and arrange the placement of the sensors. The work is reasonable and feasible in the optimal sensor placement for the tensile membrane structure. Full article

As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction. Full article

Introduction: Adolescent depression and anxiety are major public health concerns. Previous studies showed that low mental health literacy is associated with depressive and anxiety symptoms. However, how its core dimensions—knowledge, attitudes, and skills—differentially relate to emotional symptoms remains unclear. Methods: A school-based survey was conducted among 6400 adolescents in Guangdong, China. Eligible participants completed the MHL questionnaire and assessments for depressive and anxiety symptoms. We assessed whether MHL was associated with depressive and anxiety symptoms in adolescents. Machine learning algorithms with SHAP analysis were applied to explore complex associations and validate key findings. Results: A total of 5759 adolescents were included. MHL and the knowledge dimension were negatively associated with depressive and anxiety symptoms. The attitudes dimension showed a negative association with both mental health outcomes (depression: OR = 0.83; anxiety: OR = 0.84) and machine learning confirmed attitudes as the key factor. Skills were unrelated to depressive symptoms. At the highest quartile, skills showed a positive association with anxiety symptoms (OR = 1.29). Conclusions: The attitudes dimension is negatively associated with adolescent depressive and anxiety symptoms and emerged as a key feature in ML identification models. Full article

With the increasing scale of new energy grid integration, the risk of low-frequency oscillation in the power system has increased, which seriously affect system safety and stability. It is urgent to identify the risk of low-frequency oscillations through steady-state operating features. This article first analyzes the features that affect low-frequency oscillations and constructs a low-frequency oscillation dataset using transient simulations. Secondly, feature selection was performed using the random forest algorithm, and a low-frequency oscillation risk identification model for GA-CNN was proposed. Thirdly, by combining Pearson correlation coefficient and RF algorithm to eliminate redundant features and screen important features, a low-frequency oscillation frequency recognition model based on GBRT was proposed, and hyperparameter optimization was performed using grid search. Finally, the effectiveness of the proposed method was verified by ablation experiments and comparative experiments using low-frequency oscillation datasets under different operating conditions. Full article

Background/Objectives: In gas chromatography–mass spectrometry (GC-MS) library-based compound identification, spectrum preprocessing and associated tuning parameters critically influence identification performance. These parameters are conventionally optimized using grid search, which requires predefined parameter spaces and becomes computationally inefficient as dimensionality increases, often failing to identify optimal values because of discretization. Differential evolution (DE), a population-based metaheuristic optimization algorithm, provides a flexible alternative through efficient global exploration of the parameter space. This study compared the performance of DE and grid search for optimizing compound identification. Methods: Cosine similarity was applied to the NIST GC-MS library. DE was used to maximize either cross-validated accuracy or mean reciprocal rank (MRR). Results were compared with those from a grid search over five equally spaced parameter values. Identification performance was evaluated using accuracy, MRR, and area under the receiver operating characteristic curve (AUC). Results: When all four parameters were optimized simultaneously, DE achieved slightly higher cross-validated accuracy and MRR than grid search, although the absolute differences were modest. More pronounced differences were observed in specific unidimensional tuning scenarios, particularly for the intensity weight factor. Simultaneous multidimensional parameter optimization yielded better performance than isolated parameter tuning. Conclusions: Grid search may be computationally advantageous when the parameter space is known and limited, whereas DE provides a more flexible approach for unknown or high-dimensional search spaces. Overall, DE achieved comparable identification performance to grid search, with modest improvements observed in some optimization settings. A command line Julia-based tool, MSTune, was developed for spectrum preprocessing parameter optimization and is publicly available on GitHub. Full article

To address the limitations of traditional controllers for the considered six-degree-of-freedom multi-thruster underwater robot under strong nonlinearities and environmental disturbances, this paper proposes a particle swarm optimization–radial basis function–proportional–integral–derivative (PSO-RBF-PID) control algorithm. The proposed method combines the nonlinear identification capability of the RBF neural network, the global optimization capability of PSO, and the stable closed-loop structure of PID control, thereby enabling adaptive parameter tuning and disturbance compensation. Unlike existing PSO-PID- and RBF-based controllers, the proposed method combines offline global optimization and online adaptive gain tuning within a unified control framework. Although the framework is modular and can be extended to underwater robotic systems with different degrees of freedom by redefining the state vector, controller channels, and thrust allocation matrix, the present study validates the method through a six-degree-of-freedom multi-thruster underwater robot case study. Comparative simulations were conducted under the same model, disturbance conditions, sampling settings, and evaluation indices for six controllers: PID, cascade PID, fuzzy PID, FOPID, PSO-PID, and PSO-RBF-PID. For the considered 6-DOF multi-thruster underwater robot, PSO-RBF-PID achieved the best overall performance in steady-state error, settling time, overshoot, and IAE. This improvement is mainly attributed to the combination of PSO-based offline optimization and RBF-based online adaptive compensation. Full article

Current deep learning methods for tool wear monitoring suffer from poor interpretability and struggle to reveal the intrinsic relationship between signals and wear states. To address this issue, this paper presents an interpretable tool wear monitoring method based on Sparse Identification of Nonlinear Dynamics (SINDy). Multi-domain features are extracted from cutting force and acoustic emission signals to construct a time series. The SINDy algorithm is used to identify ordinary differential equations that describe the evolution of tool wear. An iterative “predict-validate-correct” mechanism is applied to optimize model parameters. Experimental results show that the mean absolute percentage error (MAPE) between the predicted and actual values is below 6%. Moreover, the optimal model demonstrates an average MAPE as low as 0.067% in cross-condition tests. This study provides an effective solution for online tool wear monitoring that achieves high precision, strong generalization, and physical interpretability. Full article

In response to the issues of subjective weighting of indicators and insufficient consideration of the temporal dimension of risk factors in current operational safety risk assessments for electric utilities, this paper proposes a method for assessing operational safety risks in electric utilities based on the Accident-Calibrated Cumulative Risk Index (ACCRI). First, in accordance with current standards and operational guidelines, a multi-level indicator system covering four dimensions, namely human resources and personnel behavior, equipment and facilities, environment and conditions, and management and systems, is established to provide a systematic characterization of operational safety risks in electric utilities. On this basis, the ACCRI is defined by weighted accumulation of the average risk exposure values of tertiary indicators within their characteristic periods. Historical accident sample importance is used to calibrate and identify tertiary indicator weights and characteristic periods, thereby reducing the subjectivity of traditional expert-based weighting. Furthermore, considering the differing temporal-scale characteristics of various risk indicators, a characteristic-period identification model is established and solved using an improved sparrow search algorithm to balance the timeliness and accuracy of risk assessment. By incorporating chaotic initialization, Gaussian mutation, and adaptive weighting mechanisms, this algorithm enhances population diversity and balances global search capability with local optimization capability across different solution stages, thereby improving the solution efficiency and accuracy of the model. Finally, the case study preliminarily demonstrates that the proposed method can characterize the temporal-scale differences among risk factors and shows potential for engineering application under the available enterprise data. Full article

The performance of the aircraft anti-skid braking system is critical to the ground operational safety of an aircraft. Conventional Pressure Bias Modulation (PBM) can suffer from deep skidding under low runway friction coefficients or low aircraft speeds. To address these issues, a composite control strategy based on Gaussian Quantum Particle Swarm Optimization (GQPSO) is proposed. This strategy employs the GQPSO algorithm for offline Proportional–Integral–Derivative (PID) parameter optimization, followed by real-time adaptive scheduling through a lookup table to accommodate varying speed domains and runway conditions. Simultaneously, by integrating the main-wheel dynamics model and friction characteristics, a runway identification function based on a Back Propagation Neural Network (BPNN) is designed to provide runway status information. The stability of the controller is verified via phase-plane analysis and Monte Carlo simulation. Subsequently, comparative Hardware-in-the-Loop (HIL) tests are conducted among PBM, PSO-PID, and the proposed GQPSO-PID controller under various runway conditions. The experimental results demonstrate that this composite controller can adapt to different speed domains and runway conditions, stably track the target slip ratio, effectively suppress skidding, and significantly improve braking efficiency, as well as exhibiting excellent robustness and control performance. Full article

One of the keys to improving feed conversion rates in Precision Livestock Farming (PLF) is the early identification of growth impediments. However, the swine farming data collected by Electronic Feeding Station (EFS) are often disorganized and lack effective labeling. Data from healthy pigs are frequently intermixed with that from sick pigs, leading to label leakage and survivor bias in models, particularly when age is included as a feature. To address these known issues, this study breaks away from traditional modeling methods. First, we clean and classify the time-series data from electronic feeding stations, using age-cohort baselines as one of the criteria for determining high and low productivity, thereby avoiding problems such as label leakage. Next, we construct a high-dimensional feature matrix that captures dynamic derivatives such as feeding acceleration and weight gain acceleration, which together serve as behavioral feature fingerprints. To test the system, we optimized the mixed-model algorithm and evaluated the model based on behavioral deviations among individual pigs after removing all absolute age labels. Our results indicate that the full-feature model achieved an ROC-AUC of 0.778 and an F1-score of 0.4137 at the optimal threshold. Interestingly, SHAP attribution analysis revealed that “intake peer deviation,” “Cumulative Intake and Lifetime Avg Intake,” and “feeding acceleration” served as precursors to low productivity and growth retardation in this dataset, with these factors proving more significant than absolute feed intake or age. Our ablation experiments confirmed that a model based solely on behavioral features (excluding age labels) maintained an ROC-AUC of 0.773, successfully decoupling pig growth performance from growth stage. Our model can detect changes in feeding dynamic signatures at an average of 12.3 days, thereby providing insights for pig growth assessment, health monitoring, or more informed culling decisions. Full article

Small-molecule drug development faces high attrition rates driven by complex pharmacokinetics and unforeseen toxicities. While deep learning offers high predictive accuracy, its opaque “black-box” nature hinders mechanistic transparency, clinical trust, and regulatory approval. This review synthesizes how Interpretable Machine Learning, synergized with systems pharmacology, advances this paradigm by enhancing mechanistic transparency in drug development. By providing insights into algorithmic decisions, Interpretable Machine Learning helps researchers identify molecular features that are statistically associated with absorption, distribution, metabolism, and excretion optimization and preemptively mitigate toxicophores, while noting that these associations require experimental validation to establish genuine causality. Furthermore, integrating multi-omics data via Interpretable Machine Learning guides rational polypharmacology, bridging in silico target identification with “dry-wet loop” validations. Crucially, Interpretable Machine Learning accelerates clinical translation by discovering causal biomarkers, refining patient stratification, and generating transparent “Model Cards” to satisfy U.S. Food and Drug Administration/European Medicines Agency regulations. We also discuss future challenges: data heterogeneity, out-of-distribution generalizability, and the evolution toward Causal Artificial Intelligence. Ultimately, the integration of Interpretable Machine Learning provides a framework for more transparent and evidence-based drug design, realizing the promise of precision medicine. Full article

Background: Radiology underpins diagnosis and treatment across pediatrics, yet most artificial intelligence (AI) tools are developed for adults and validated on adult datasets only. Of more than 200 AI systems cleared by the United States (U.S.) Food and Drug Administration (FDA), only about 3% include pediatric validation. Because children differ from adults in anatomy, physiology, pathology, epidemiology, and imaging protocols, adult-trained models often perform sub-optimally in pediatric settings. Methods: A narrative review of peer-reviewed literature from 2000 to 2025 was conducted using PubMed, MEDLINE, Google Scholar, and Scopus. Studies involving AI applications in pediatric X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), echocardiography, and point-of-care ultrasound with quantitative performance metrics were included. Findings were synthesized by imaging modality, clinical task, and differences between high-income countries (HICs) and low- and middle-income countries (LMICs). Results: AI demonstrated strong performance across multiple pediatric imaging tasks. In X-ray interpretation, AI detected fractures with area under the curve (AUC) values up to 0.96 (sensitivity, 90.8%; specificity, 88.7%). Pneumonia classification achieved 76.5% accuracy, and foreign body aspiration detection showed 95.3% specificity in HICs. In ultrasound, AI improved junior sonographers’ detection of intussusception (AUC 0.857 to 0.966) and reduced scan time by more than 50%. AI-assisted bone age estimation achieved a mean error of 0.39 years. In echocardiography, AI-derived ejection fraction showed excellent agreement with experts’ interclass correlation coefficient (ICC 0.983), and AI support improved atrioventricular septal defect detection (84.4% to 86.5%). In MRI, the use of AI enhanced lesion detection and supported quantitative analysis. Deep-learning models trained on routine T1- and T2-weighted sequences predicted liver stiffness across multi-site datasets, while advanced neuroimaging pipelines improved the identification of subtle epileptogenic lesions that are often missed on conventional pediatric MRI. However, adult-trained models showed limited generalizability to children. Still, excluding children under the age of two years improved the reading accuracy of pediatric chest X-rays (CXRs) by adult-trained models from 88% to 97%. AI faces challenges beyond the development of age-specific models. Substantial heterogeneity, limited pediatric-specific datasets, and unresolved medicolegal responsibility further restrict adoption worldwide. Challenges are amplified in LMICs, where unstable electricity, limited radiology resources, weak digital infrastructure, and scarce pediatric providers limit implementation. Additionally, many large language models underperform and lack inclusive algorithms suitable for pediatric radiology in many LMICs. Conclusions: AI can enhance diagnostic accuracy, efficiency, and access to pediatric imaging, particularly in resource-limited settings, through task-shifting and decision support. However, it cannot replace pediatric radiologists as of today. Safe adoption requires pediatric-specific model development, standardized validation metrics, diverse datasets that include LMIC populations, stronger digital infrastructure, robust radiologist training in AI capabilities, and the establishment of clear guidelines and medicolegal policies. Full article