Search Results (305)

Background: Unplanned 30-day hospital readmissions, a key healthcare quality metric, are common and costly. Prediction models built on structured data often perform modestly, and the added value of unstructured clinical notes remains unclear. Methods: This retrospective cohort study included 4135 general medicine admissions to a tertiary Australian hospital between July 2022 and June 2023. Structured predictors included demographics, comorbidities, frailty, prior healthcare utilisation, length-of-stay, inflammatory markers, socioeconomic indicators, and lifestyle factors. We developed deep learning models using structured data alone, unstructured text alone, and a combined multimodal architecture integrating both modalities. For benchmarking, multiple classical machine learning models trained on structured features were evaluated using identical data splits, including logistic regression, XGBoost, random forest, gradient boosting, extra trees, and HistGradient Boosting. Model performance was assessed on a hold-out test set using ROC-AUC, accuracy, precision, recall, and F1-score. Results: Unplanned readmissions occurred in 24.3% of admissions. Among classical machine learning models, logistic regression achieved the highest discrimination (ROC-AUC 0.64), with no substantial improvement observed from ensemble methods. Structured-only deep learning achieved ROC-AUC 0.62. Unstructured text-only and multimodal models achieved ROC-AUCs of 0.52 and 0.58, respectively. Although overall discrimination of the multimodal model was lower than structured-only performance, it demonstrated improved sensitivity and F1-score for identifying patients who were readmitted. Prior hospitalisations, emergency department visits, and comorbidity burden were the strongest predictors. Conclusions: Structured EMR variables remain the main drivers of 30-day readmission risk. More complex classical machine learning models did not outperform logistic regression, and incorporating unstructured clinical text provided only modest improvement in identifying high-risk patients without enhancing overall discrimination. Full article

Flooding is one of the major natural disasters that have a major impact on urban areas due to the increasing intensity of factors like extreme weather conditions, climate change, and unplanned urbanization. Considering Cook County, Illinois, the rapid development of the region, flat topography, and the induced rainfall extremes from climate change increase the potential risk of flooding when interacting with dense urban exposure and infrastructure. This study employed the Frequency Ratio (FR) model in a GIS environment to create a high-resolution flood susceptibility map of the county. The map was developed using 281 historical flood points collected from several authoritative sources, such as National Oceanic and Atmospheric Administration (NOAA) Storm Events Database records, Federal Emergency Management Agency (FEMA) Flood Insurance Study (FIS) and Flood Insurance Rate Map (FIRM)-based FIRMette products, and U.S. Geological Survey (USGS) flood-inundation studies. Thirteen conditioning factors, including land use, elevation, slope, soil drainage, rainfall, and distance to the stream, were used to calculate FR values and to develop the Flood Susceptibility Index (FSI). The resulting FSI was grouped into four susceptibility zones: low, medium, high, and very high. The findings indicated that more than 64% of Cook County has a high and very high risk of flood susceptibility, particularly in the vicinity of major river corridors. The model was validated using testing data with a 91.4% prediction accuracy, which also demonstrated the reliability and applicability of the FR model in the urban flood susceptibility assessment. The map serves as a valuable tool for risk-based urban planning and design of flood mitigation infrastructure in one of the most populated counties in the United States. Full article

Background: Clinicians rely on clinical judgement and vital sign monitoring to identify patient deterioration, commonly supported by systems such as the National Early Warning Score 2 (NEWS2). However, NEWS2 is associated with a high false-positive burden, contributing to alert fatigue in increasingly pressured clinical environments. Consequently, there is a growing need for early warning systems (EWS) that not only detect deterioration but do so with higher precision to prioritise clinically meaningful alerts. We aimed to develop and validate a prognostic EWS capable of predicting real-time clinical deterioration in hospitalised adult patients. Methods: We conducted a retrospective observational cohort study using routinely collected Electronic Patient Record (EPR) data. A Cox proportional hazards model with time-varying covariates was developed to estimate dynamic risk of deterioration. Deterioration was defined as unplanned transfer to intensive care, unplanned surgery, or in-hospital death. Data for model development comprised 37,989 adult inpatient episodes admitted between January 2022 and October 2024, and were initially split into training, temporal validation and test datasets. An extended evaluation period included 11,048 patients admitted through September 2025. Model performance was compared with NEWS2 at the emergency-response threshold (≥7). Results: The final model produced a tiered “traffic-light” risk profile and demonstrated substantially higher precision than NEWS2 while maintaining comparable recall in our test data. At the red alert threshold, precision was 60% compared with 16% for NEWS2 ≥7, with 82% versus 43% of alerts occurring within 24 h of deterioration. Performance remained consistent across the extended evaluation period. Conclusions: A survival-based EWS incorporating time-varying covariates achieved higher precision and improved temporal alignment with deterioration events compared with NEWS2. A tiered amber–red alert framework may support more targeted escalation, reduce alert fatigue, and enhance early identification of clinical deterioration. Full article

Medium-sized cities are increasingly affected by processes of urban fragmentation and residential segregation, despite having traditionally been perceived as more socially cohesive and territorially balanced than large metropolitan areas. Acting as functional connectors between metropolitan hubs and rural regions, these cities are particularly vulnerable to unplanned suburban growth, housing market polarization and uneven access to urban opportunities. This study develops and applies a multidimensional Urban Territorial Index (UTI) to diagnose socio-spatial inequality in medium-sized cities, using Ciudad Real (central Spain) and its functional urban area as a case study. The UTI integrates six indicators across three analytical dimensions—socioeconomic, sociodemographic and housing—through a PCA-informed weighting scheme and GIS-based spatial analysis. The index is calculated at census-tract and neighborhood scales and is validated through internal consistency checks, external comparison with a local Human Development Index (r = 0.87; p < 0.001), and qualitative robustness assessments. Results reveal a pronounced core–periphery polarization: central and strategically located neighborhoods associated with key infrastructures (university, high-speed rail station and hospital) concentrate higher income levels, educational attainment and land values, while peripheral municipalities and disadvantaged neighborhoods exhibit higher unemployment, lower housing values and greater social vulnerability. The analysis also identifies population–housing mismatches linked to suburban expansion without equivalent functional integration. Beyond the local case, the study provides a transparent and replicable methodological framework tailored to medium-sized cities, where metropolitan-scale indices often fail to capture fine-grained socio-spatial disparities. The UTI offers a practical tool for comparative analysis, temporal monitoring and evidence-based urban policy, supporting more inclusive and territorially balanced development strategies in diverse institutional and geographical contexts. Full article

Background: Frailty markedly increases risk of unplanned readmission, 30-day mortality, and discontinuity of care during the transition from hospital to home. Although this transition represents a critical period for patient safety and recovery, the specific needs perceived by individuals with frailty and their caregivers at the time of discharge remain insufficiently understood. Aim: The aim of this study was to explore and synthesize qualitative evidence of perceived needs by individuals with frailty and their caregivers during the transition from hospital to home. Methods: A qualitative systematic review will be conducted following the Joanna Briggs Institute (JBI) methodological guidance. Systematic searches will be performed in PubMed, CINAHL, Web of Science (WoS), Biblioteca Virtual de Salud (BVS), Scopus, and Google Scholar. All primary qualitative and mixed-methods studies with a qualitative component, published in any language and without date restrictions, will be eligible. Methodological quality will be appraised using the JBI Critical Appraisal Checklist for Qualitative Research. A meta-aggregative approach will be applied to extract and synthesize findings using JBI SUMARI software. Confidence in the synthesized findings will be assessed using the ConQual approach. Expected results: The results will describe the perceived needs of this population and their caregivers and will support the development of practical recommendations for transitional care. Conclusions: The findings are expected to inform person-centered transitional care practices and support the development of clinical strategies to improve continuity of care. Full article

Peri-urbanization is one of the most complex and rapidly territorial phenomena in African metropolitan areas, including Morocco. This dynamic, characterized by unplanned urban growth, presents significant challenges in terms of land management and sustainable territorial planning. In this context, this work proposes a methodology for detecting and analyzing peri-urban areas using a deep learning model based on the Global Human Settlement Layer and Global Land Analysis and Discovery Land Cover data. The Multi-Layer Perceptron model was trained on a manually annotated dataset covering the Casablanca metropolitan region and then used to classify the area into four categories: urban, peri-urban, rural, and water. Model interpretability was ensured through the Shapley Additive Explanations method, and a diachronic analysis was conducted from 2005 to 2025. The model achieved high accuracy (90.6%), with strong performance in identifying urban (F1 ≈ 0.996) and rural (F1 ≈ 0.94) areas. However, peri-urban areas represent some challenges, which result in a lower F1-score of about 0.63 due to transitional land patterns. The results reveal a significant expansion of peri-urban areas (+28,000 ha) at the expense of rural lands. These findings offer valuable insights for policymakers to develop sustainable land-use planning strategies and to anticipate urban sprawl dynamics. Full article

The mining industry relies heavily on large-scale machinery, making operational efficiency highly sensitive to equipment breakdowns and maintenance interruptions. Such breakdowns directly affect production performance, operational costs, and planning accuracy. Therefore, the ability to predict machinery downtime particularly for haul trucks, loaders, drilling machinery, and dozers used in open-pit operations is essential for improving productivity and ensuring reliable mine planning. This study aims to predict machinery breakdowns and estimate the annual total number of breakdowns using machine-learning techniques applied to a fully digitalized dataset of 16,027 breakdown and maintenance records collected from an open-pit coal mine. A Random Forest classification model was developed to identify the breakdown unit for each event, achieving an accuracy of 94%, while a Random Forest regression model estimated the annual breakdown counts with an R² value of 0.98. In addition, the relationships between breakdown frequency and key production indicators were examined using linear regression and correlation analyses. The results show a strong association between run-of-mine quantities and coal production, a moderate relationship between stripping activity and breakdown frequency, and negligible linear relationships between breakdowns and production volumes. Overall, the findings demonstrate that integrating machine-learning models with operational mining data can significantly enhance predictive maintenance, reduce unplanned downtime, and improve production planning in open-pit mining operations. Full article

Squirrel-cage induction generators often perform better without a mechanical speed sensor. Eliminating an encoder or resolver removes one of the most fragile and failure-prone components, while modern control algorithms can estimate speed with sufficient accuracy. Shaft-mounted sensors are vulnerable to heat, vibration, dust, moisture, and electrical noise; they require precise mounting and additional cabling and typically fail long before the machine itself. In many industrial and marine applications, unplanned shutdowns are more often caused by damaged sensors or cables than by the generator. Unlike sensorless speed-detection methods developed for motoring operation, the proposed approach targets the generator mode, where both phase currents and the DC-link voltage are measured. It uses two indicators: the magnitude and sign of the active current, and the instantaneous rise in DC-link voltage when the converter output frequency matches the machine’s shaft speed. Because active current remains negative over a wide frequency range during start-up, its sign change alone cannot uniquely identify the synchronization point. In generator operation, however, the DC-link capacitor voltage provides an additional criterion: the speed at which power reverses sign, indicated by a change in the sign of the DC-voltage derivative. As the inverter frequency approaches the machine rotational frequency from below, the DC voltage increases, reaches a maximum at maximum slip, and then decreases once the inverter frequency exceeds the machine speed. The article demonstrates how these signals can be used in practice to identify the rotational speed of a squirrel-cage generator. Full article

Demagnetization faults in direct-drive permanent magnet synchronous motors (DDPMSM) can cause significant performance degradation and unplanned downtime. Traditional fault location methods, which rely on manual feature extraction, exhibit limited accuracy and efficiency in complex and variable operating conditions. To address these limitations, this study presents a demagnetization fault location method based on a search coil employing a data-driven one-dimensional convolutional neural network (1D-CNN). Firstly, the arrangement of search coils was determined, and a partitioned mathematical model was established, using the residual back electromotive force (back-EMF) of the search coil over a single electrical cycle as the fundamental unit. Secondly, the residual back-EMF in the search coil is analyzed under various demagnetization parameters and operating conditions to assess the robustness of the proposed method. Furthermore, a 1D-CNN-based fault location model was developed using residual back-EMF signals as the input and targeting the identification of demagnetized permanent magnet types. Simulation and experimental results demonstrate that the proposed method can effectively detect and locate demagnetization faults across different operating conditions. When the demagnetization degree is not less than 10%, the fault location accuracy reaches 99.58%, and the minimum detectable demagnetization degree is 8%. The approach demonstrates excellent robustness and generalization, offering an intelligent solution for demagnetization fault location in PMSMs. Full article

With the advancement of industrial systems toward greater complexity and higher asset value, unexpected equipment failures now risk severe production interruptions, substantial economic costs, and critical safety hazards. Conventional maintenance strategies, which are primarily reactive or schedule-based, have proven inadequate in preventing unplanned downtime, underscoring a pressing demand for more intelligent monitoring solutions. In this context, intelligent spectral detection has arisen as a transformative methodology to bridge this gap. This review explores the integration of spectroscopic techniques with machine learning for equipment defect diagnosis and prognosis, with a particular focus on applications such as hydrogen leak detection and transformer oil aging assessment. Key aging indicators derived from spectral data are systematically evaluated to establish a robust basis for condition monitoring. The paper also identifies prevailing challenges in the field, including spectral data scarcity, limited model interpretability, and poor generalization across different operational scenarios. Future research directions emphasize the construction of large-scale, annotated spectral databases, the development of multimodal data fusion frameworks, and the optimization of lightweight algorithms for practical, real-time deployment. Ultimately, this work aims to provide a clear roadmap for implementing predictive maintenance paradigms, thereby contributing to safer, more reliable, and more efficient industrial operations. Full article

Background: Otitis media with effusion (OME) is a widespread condition that causes hearing impairment, particularly in pediatric populations. Existing non-absorbable tubes often require elective or unplanned removal surgery. Bioabsorbable polylactic acid (PLA) offers a promising alternative due to its inherent biocompatibility and tunable degradation characteristics. In this study, we designed, fabricated, and comprehensively evaluated a novel PLA middle-ear ventilation tube. Methods: Bioabsorbable PLA tubes were designed and fabricated based on commercial models. In vitro biocompatibility was assessed according to ISO 10993 guidelines. A guinea pig model was used to perform in vivo evaluations, including otoscopic examinations, auditory brainstem response (ABR) measurements, micro-computed tomography (micro-CT) imaging, and histological analyses. Results: The PLA tubes were successfully designed and fabricated, exhibiting dimensions comparable to those of commercially available products. In vitro testing confirmed their biocompatibility. In vivo observations revealed that the PLA segments remained stable, with no significant inflammation detected. ABR measurements revealed no adverse impacts on hearing function. Micro-CT imaging confirmed tube integrity and indicated initial signs of degradation over a 9-month period, as evidenced by radiographic morphology. Histological analyses indicated a favorable tissue response with minimal foreign body reaction. Conclusions: The developed PLA middle-ear ventilation tube represents a highly promising alternative to conventional non-absorbable tubes. It demonstrates excellent biocompatibility, preserves auditory function, and exhibits a controlled degradation profile. This preclinical study provides strong support for further investigation and subsequent clinical trials to validate its safety and efficacy in human patients. Full article

Background: Pancreatic and periampullary cancers are common tumors of the digestive tract. As a radical surgical approach, laparoscopic pancreaticoduodenectomy requires crucial preoperative assessment of its surgical difficulty. Materials and methods: A retrospective cohort of 150 patients who underwent LPD between June 2019 and June 2023 was enrolled. The criteria for defining the difficult group were identified as unplanned conversion to open procedure, intraoperative blood loss, and operative time. Participants were randomly allocated to a training set (n = 105) or a testing set (n = 45) in a 7:3 ratio. Hand-crafted radiomics (HCR) features and deep learning-derived radiomics (DLR) features were extracted from portal venous phase CT images, focusing on gross tumor volume and gross peri-tumor volume. A hybrid prediction model was developed using a support vector machine algorithm, with performance evaluated through receiver operating characteristic analysis, calibration curves, and decision curve analysis (DCA). Results: The combined model demonstrated significantly superior discriminative ability, achieving an area under the curve (AUC) of 0.942 (95% CI: 0.893–0.992) in the training set and 0.848 (95% CI: 0.738–0.958) in the testing set. This performance exceeded both the standalone HCR model (testing AUC = 0.754) and the DLR model (testing AUC = 0.816). DCA further confirmed the clinical utility of the combined model, showing the highest net benefit across threshold probabilities exceeding 20%. Conclusions: The novel integrated model combining hand-crafted and deep learning-derived radiomics features enables effective prediction of surgical difficulty in laparoscopic pancreaticoduodenectomy. Full article

Inter-basin water transfer projects are core infrastructure for achieving sustainable water resource allocation and addressing regional water scarcity, and pumping station units, as their critical energy-consuming and operation-controlling components, are vital to the projects’ sustainable performance. With the growing complexity and scale of these projects, pumping station units have become more intricate, leading to a gradual rise in failure rates. However, existing fault diagnosis methods are relatively backward, failing to promptly detect potential faults—this not only threatens operational safety but also undermines sustainable development goals: equipment failures cause excessive energy consumption (violating energy efficiency requirements for sustainability), unplanned downtime disrupts stable water supply (impairing reliable water resource access), and even leads to water waste or environmental risks. To address this sustainability-oriented challenge, this paper focuses on the fault characteristics of pumping station units and proposes a comprehensive and accurate fault diagnosis model, aiming to enhance the sustainability of water transfer projects through technical optimization. The model utilizes advanced algorithms and data processing technologies to accurately identify fault types, thereby laying a technical foundation for the low-energy, reliable, and sustainable operation of pumping stations. Firstly, continuous wavelet transform (CWT) converts one-dimensional time-domain signals into two-dimensional time-frequency graphs, visually displaying dynamic signal characteristics to capture early fault features that may cause energy waste. Next, the multi-head attention mechanism (MHA) segments the time-frequency graphs and correlates feature-location information via independent self-attention layers, accurately capturing the temporal correlation of fault evolution—this enables early fault warning to avoid prolonged inefficient operation and energy loss. Finally, the improved convolutional neural network (CNN) layer integrates feature information and temporal correlation, outputting predefined fault probabilities for accurate fault determination. Experimental results show the model effectively solves the difficulty of feature extraction in pumping station fault diagnosis, considers fault evolution timeliness, and significantly improves prediction accuracy and anti-noise performance. Comparative experiments with three existing methods verify its superiority. Critically, this model strengthens sustainability in three key ways: (1) early fault detection reduces unplanned downtime, ensuring stable water supply (a core sustainable water resource goal); (2) accurate fault localization cuts unnecessary maintenance energy consumption, aligning with energy-saving requirements; (3) reduced equipment failure risks minimize water waste and environmental impacts. Thus, it not only provides a new method for pumping station fault diagnosis but also offers technical support for the sustainable operation of water conservancy infrastructure, contributing to global sustainable development goals (SDGs) related to water and energy. Full article

Guidance information plays an important role in influencing metro passengers’ travel choices and enhancing their travel experience during unplanned service disruptions. However, limited research has examined passengers’ behavioral responses to personalized guidance information in such contexts. This study aims to fill the gap and explore the impact of personalized guidance information on passengers’ travel choice behavior during unplanned metro service disruptions. First, we reconstruct the decision-making process of metro passengers under disruption scenarios and design personalized guidance strategies, followed by a stated preference survey to collect preference data. Using data from Beijing, China, a hybrid utility–regret model is developed to analyze how the content and frequency of personalized guidance information affect passengers’ travel choice preferences. The results show that recommended plans with explanatory information are more likely to be adopted, particularly when explanations are framed from the passenger’s perspective. A single notification serves as a timely reminder, whereas overly frequent messages may trigger annoyance and reduce effectiveness. These findings provide practical implications for the design of personalized guidance strategies, thereby mitigating the impacts of metro service disruptions. Full article

This study presents a methodology for optimizing repair intervals of mining equipment by integrating economic efficiency and reliability criteria. A review of existing maintenance strategies revealed their limitations, and a mathematical model was developed that incorporates both projected financial expenditures and the probability of equipment failures, enabling more accurate prediction of the optimal repair timing. This study introduces a novel integration of the Weibull reliability distribution with a cost-convolution optimization model, explicitly capturing the trade-off between economic efficiency and failure risk. Unlike traditional fixed-schedule approaches, the proposed model provides analytically optimized repair intervals derived from observed degradation trends. Statistical analysis demonstrates that unplanned repairs are, on average, 56% more costly than scheduled ones, highlighting the need to revise current preventive maintenance practices. The cost comparison is based on 34 restoration records collected from publicly available supplier price lists and field maintenance logs, converted into a unified currency. Based on operational data and reliability parameter estimation, the optimal repair interval was determined to be 5129 machine hours, which minimizes both the probability of failure and total maintenance-related financial losses, while reducing unplanned downtime. Unlike traditional fixed-schedule approaches, the proposed model allows adaptive adjustment of maintenance intervals according to the actual degradation characteristics of the equipment. The practical significance of the research lies in its ability to help mining enterprises reduce expenditures on corrective repairs, extend the service life of machinery, and improve overall operational efficiency. The findings contribute to advancing maintenance optimization in the mining industry, supporting more sustainable and cost-effective equipment management. Full article