Search Results (5,329)

Background: Electrocardiograms (EKGs) are essential tools in emergency medicine, often used to evaluate chest pain, dyspnea, and other symptoms suggestive of cardiac dysfunction. Yet, EKGs are not universally administered to all emergency department (ED) patients. Understanding and predicting which patients receive an EKG may offer insights into clinical decision making, resource allocation, and potential disparities in care. This study examines whether integrating structured clinical data with free-text patient narratives can improve prediction of EKG utilization in the ED. Methods: We conducted a retrospective observational study to predict electrocardiogram (EKG) utilization using data from 13,115 adult emergency department (ED) visits in the nationally representative 2021 National Hospital Ambulatory Medical Care Survey–Emergency Department (NHAMCS-ED), leveraging both structured features—demographics, vital signs, comorbidities, arrival mode, and triage acuity, with the most influential selected via Lasso regression—and unstructured patient narratives transformed into numerical embeddings using Clinical-BERT. Four supervised learning models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF) and Extreme Gradient Boosting (XGB)—were trained on three inputs (structured data only, text embeddings only, and a late-fusion combined model); hyperparameters were optimized by grid search with 5-fold cross-validation; performance was evaluated via AUROC, accuracy, sensitivity, specificity and precision; and interpretability was assessed using SHAP values and Permutation Feature Importance. Results: EKGs were administered in 30.6% of adult ED visits. Patients who received EKGs were more likely to be older, White, Medicare-insured, and to present with abnormal vital signs or higher triage severity. Across all models, the combined data approach yielded superior predictive performance. The SVM and LR achieved the highest area under the ROC curve (AUC = 0.860 and 0.861) when using both structured and unstructured data, compared to 0.772 with structured data alone and 0.823 and 0.822 with unstructured data alone. Similar improvements were observed in accuracy, sensitivity, and specificity. Conclusions: Integrating structured clinical data with patient narratives significantly enhances the ability to predict EKG utilization in the emergency department. These findings support a personalized medicine framework by demonstrating how multimodal data integration can enable individualized, real-time decision support in the ED. Full article

Background: HIV-associated neurocognitive disorders (HANDs) continue to be a significant concern, despite the advancements in prognosis achieved through Combination Antiretroviral Therapy (cART). Neuropsychological assessment, recommended by international guidelines for HANDs diagnosis, can be resource-intensive. Brief screening tools, like the International HIV Dementia Scale (IHDS) and the Montreal Cognitive Assessment (MoCA), are crucial in facilitating initial evaluations. This study aims to assess the Italian IHDS (IHDS-IT) and evaluate its sensitivity and specificity in detecting cognitive impairment in HIV patients. Methods: This cross-sectional study involved 294 patients aged ≥30 years, evaluated at the Immunology Unit of the University of Cagliari. Cognitive function was assessed using the MoCA and IHDS. Laboratory parameters, such as CD4 nadir, current CD4 count, and HIV-RNA levels, were also collected. Statistical analyses included Spearman’s correlation, Receiver Operating Characteristic analysis, and the Youden J statistic to identify the optimal IHDS-IT cut-off for cognitive impairment detection. Results: The IHDS and MoCA scores showed a moderate positive correlation (Spearman’s rho = 0.411, p < 0.0001). ROC analysis identified an IHDS-IT cut-off of ≤9, yielding an Area Under the Curve (AUC) of 0.76, sensitivity of 71.7%, and specificity of 67.2%. At this threshold, 73.1% of patients with MoCA scores below 23 also presented abnormal IHDS scores, highlighting the complementary utility of both cognitive assessment instruments. Conclusions: The IHDS-IT exhibited fair diagnostic accuracy for intercepting cognitive impairment, with a lower optimal cut-off than previously reported. The observed differences may reflect this study cohort’s demographic and clinical characteristics, including advanced age and long-lasting HIV infection. Further, longitudinal studies are necessary to validate these findings and to confirm the proposed IHDS cut-off over extended periods. Full article

Background/Objectives: To simplify the decision-making process in radiomics by employing RadiomiX, an algorithm designed to automatically identify the best model combination and validate them across multiple environments was developed, thus enhancing the reliability of results. Methods: RadiomiX systematically tests classifier and feature selection method combinations known to be suitable for radiomic datasets to determine the best-performing configuration across multiple train–test splits and K-fold cross-validation. The framework was validated on four public retrospective radiomics datasets including lung nodules, metastatic breast cancer, and hepatic encephalopathy using CT, PET/CT, and MRI modalities. Model performance was assessed using the area under the receiver-operating-characteristic curve (AUC) and accuracy metrics. Results: RadiomiX achieved superior performance across four datasets: LLN (AUC = 0.850 and accuracy = 0.785), SLN (AUC = 0.845 and accuracy = 0.754), MBC (AUC = 0.889 and accuracy = 0.833), and CHE (AUC = 0.837 and accuracy = 0.730), significantly outperforming original published models (p < 0.001 for LLN/SLN and p = 0.023 for MBC accuracy). When original published models were re-evaluated using ten-fold cross-validation, their performance decreased substantially: LLN (AUC = 0.783 and accuracy = 0.731), SLN (AUC = 0.748 and accuracy = 0.714), MBC (AUC = 0.764 and accuracy = 0.711), and CHE (AUC = 0.755 and accuracy = 0.677), further highlighting RadiomiX’s methodological advantages. Conclusions: Systematically testing model combinations using RadiomiX has led to significant improvements in performance. This emphasizes the potential of automated ML as a step towards better-performing and more reliable radiomic models. Full article

Background: Plantar fasciitis (PF) is a common enthesopathy in patients with ankylosing spondylitis (AS). Shear wave elastography (SWE) and the Belgrade ultrasound enthesitis score (BUSES) may detect PF, but their comparative diagnostic performance is unclear. Objective: To compare SWE with the BUSES for identifying PF in individuals with and without AS. Methods: In this cross-sectional study, 96 participants were stratified into AS and non-AS populations, each further divided based on the presence or absence of clinical PF. Demographic data, the American Orthopedic Foot and Ankle Society Score (AOFAS), and the BASDAI score were recorded. All subjects underwent grayscale ultrasonography, the BUSES scoring, and SWE assessment of the plantar fascia. Logistic regression models were constructed for each population, controlling for age, body mass index (BMI), and fascia–skin distance. ROC curve analyses were performed to evaluate diagnostic accuracy. Results: In both AS and non-AS groups, SWE and the BUSES were significant predictors of PF (p < 0.05). SWE demonstrated slightly higher diagnostic accuracy, with area under the curve (AUC) values of 0.845 (AS) and 0.837 (non-AS), compared to the BUSES with AUCs of 0.785 and 0.831, respectively. SWE also showed stronger adjusted odds ratios in regression models. The interobserver agreement was good to excellent for both modalities. Conclusions: Both SWE and the BUSES are effective for PF detection, with SWE offering marginally superior diagnostic performance, particularly in AS patients. SWE may enhance the early identification of biomechanical changes in the plantar fascia. Full article

Monitoring cardiovascular health enables continuous and real-time risk assessment. This study utilized the Framingham Heart Study dataset to develop and evaluate machine-learning models for predicting mortality risk based on key cardiovascular parameters. Some machine-learning algorithms were applied to multiple machine-learning models. Among these, XGBoost achieved the highest predictive performance, each with an area under the curve (AUC) value of 0.83. Feature importance analysis revealed that coronary artery disease, glucose levels, and diastolic blood pressure (DIABP) were the most significant risk factors associated with mortality. The primary contribution of this research lies in its implications for public health and preventive medicine. By identifying key risk factors, it becomes possible to calculate individual and population-level risk scores and to design targeted early intervention strategies aimed at reducing cardiovascular-related mortality. Full article

Background/Objectives: Feigning spectrum behavior (FSB) is the exaggeration, fabrication, or false imputation of symptoms. It occurs in compensable injury with great cost to society by way of loss of productivity and excessive costs. The aim of this study is to identify feigning by developing cut scores on the long and short forms (SF) of the Orebro Musculoskeletal Pain Screening Questionnaire (OMPSQ and OMPSQ-SF) and the Perceived Stress Scale (PSS and PSS-4). Methods: As part of pre-screening for a support program, 40 injured workers who had been certified unfit for work for more than 2 weeks were screened once with the OMPSQ and PSS by telephone by a mental health professional. A control sample comprised of 40 non-injured community members were screened by a mental health professional on four occasions under different aliases, twice responding genuinely and twice simulating an injury. Results: Differences between the workplace injured people and the community sample were compared using ANCOVA with age and gender as covariates, and then receiver operator characteristics (ROCs) were calculated. The OMPSQ and OMPSQ-SF discriminated (ρ < 0.001) between all conditions. All measures discriminated between the simulation condition and workplace injured people (ρ < 0.001). Intraclass correlation demonstrated the PSS, PSS-4, OMPSQ, and OMPSQ-SF were reliable (ρ < 0.001). Area Under the Curve (AUC) was 0.750 for OMPSQ and 0.835 for OMPSQ-SF for work-injured versus simulators. Conclusions: The measures discriminated between injured and non-injured people and non-injured people instructed to simulate injury. Non-injured simulators produced similar scores when they had multiple exposures to the test materials, showing the uniformity of feigning spectrum behavior on these measures. The OMPSQ-SF has adequate discriminant validity and sensitivity to feigning spectrum behavior, making it optimal for telephone screening in clinical practice. Full article

Background/Objectives: Platelet activity contributes to myocardial infarction; inadequate inhibition is a risk factor for stent thrombosis and mortality. Inadequate platelet inhibition during treatment is an important risk factor for stent thrombosis and may be associated with increased mortality. This study assessed platelet and coagulation activity in post-MI patients, identifying parameters associated with adverse ST-elevation myocardial infarction (STEMI) outcomes over 3 years, to identify patients needing intensive secondary prevention. Methods: From 57 admitted patients, 19 STEMI patients were analyzed. Thromboelastography (TEG) and Total Thrombus Formation Analysis System (T-TAS) were used to assess hemostasis and coagulation. Selected laboratory parameters were measured for correlations. Major adverse cardiovascular events (MACEs) were defined as ischemic stroke, myocardial infarction, ischemic heart disease, thrombosis, and death from cardiovascular causes. Results: The group with MACEs was characterized by a faster time to initial clot formation and greater reflection of clot strength. T-TAS parameters, such as area under the curve at 10 min (T-TAS AUC10), showed lower values in the same group of patients. A moderate positive correlation suggested that as white blood cell count increases, T-TAS AUC10 values also tend to increase. A strong negative correlation (rho = −1.000, p < 0.01) was observed between low-density lipoprotein and kinetics in the TEG using the kaolin test at baseline in patients with MACEs. Conclusions: Some of the parameters suggest they are associated with adverse outcomes of STEMI, indicate the existence of an inflammatory state, and may contribute to risk stratification of STEMI patients and identify who will require ongoing monitoring. Full article

This article presents a comprehensive assessment of mudflow risk in the Talgar River basin through the application of Multi-Criteria Decision Analysis (MCDA) methods and numerical modeling using the Rapid Mass Movement Simulation (RAMMS) environment. The first part of the study involves a spatial assessment of mudflow hazard and susceptibility using GIS technologies and MCDA. The key condition for evaluating mudflow hazard is the identification of factors influencing the formation of mudflows. The susceptibility assessment was based on viewing the area as an object of spatial and functional analysis, enabling determination of its susceptibility to mudflow impacts across geomorphological zones: initiation, transformation, and accumulation. Relevant criteria were selected for analysis, each assigned weights based on expert judgment and the Analytic Hierarchy Process (AHP). The results include maps of potential mudflow hazard and susceptibility, showing areas of hazard occurrence and risk impact zones within the Talgar River basin. According to the mudflow hazard map, more than 50% of the basin area is classified as having a moderate hazard level, while 28.4% is subject to high hazard, and only 1.8% falls under the very high hazard category. The remaining areas are categorized as very low (4.1%) and low (14.7%) hazard zones. In terms of susceptibility to mudflows, 40.1% of the territory is exposed to a high level of susceptibility, 35.6% to a moderate level, and 5.5% to a very high level. The remaining areas are classified as very low (1.8%) and low (15.6%) susceptibility zones. The predictive performance was evaluated through Receiver Operating Characteristic (ROC) curves, and the Area Under the Curve (AUC) value of the mudflow hazard assessment is 0.86, which indicates good adaptability and relatively high accuracy, while the AUC value for assessing the susceptibility of the territory is 0.71, which means that the accuracy of assessing the susceptibility of territories to mudflows is within the acceptable level of model accuracy. To refine the spatial risk assessment, mudflow modeling was conducted under three scenarios of glacial-moraine lake outburst using the RAMMS model. For each scenario, key flow parameters—height and velocity—were identified, forming the basis for classification of zones by impact intensity. The integration of MCDA and RAMMS results produced a final mudflow risk map reflecting both the likelihood of occurrence and the extent of potential damage. The presented approach demonstrates the effectiveness of combining GIS analysis, MCDA, and physically-based modeling for comprehensive natural hazard assessment and can be applied to other mountainous regions with high mudflow activity. Full article

Simulated data created in silico using a previously reported method were sampled by bootstrapping to generate data sets for training multiple copies of an ensemble learner (i.e., a machine learning (ML) method). The posterior probabilities of class membership obtained by applying the ensemble of ML models to previously unseen validation data were fitted to a beta distribution. The shape parameters for the fitted distribution were used to calculate the subjective opinion of sample membership into one of two mutually exclusive classes. The subjective opinion consists of belief, disbelief and uncertainty masses. A subjective opinion for each validation sample allows identification of high-uncertainty predictions. The projected probabilities of the validation opinions were used to calculate log-likelihood ratio scores and generate receiver operating characteristic (ROC) curves from which an opinion-supported decision can be made. Three very different ML models, linear discriminant analysis (LDA), random forest (RF), and support vector machines (SVM) were applied to the two-state classification problem in the analysis of forensic fire debris samples. For each ML method, a set of 100 ML models was trained on data sets bootstrapped from 60,000 in silico samples. The impact of training data set size on opinion uncertainty and ROC area under the curve (AUC) were studied. The median uncertainty for the validation data was smallest for LDA ML and largest for the SVM ML. The median uncertainty continually decreased as the size of the training data set increased for all ML.The AUC for ROC curves based on projected probabilities was largest for the RF model and smallest for the LDA method. The ROC AUC was statistically unchanged for LDA at training data sets exceeding 200 samples; however, the AUC increased with increasing sample size for the RF and SVM methods. The SVM method, the slowest to train, was limited to a maximum of 20,000 training samples. All three ML methods showed increasing performance when the validation data was limited to higher ignitable liquid contributions. An ensemble of 100 RF ML models, each trained on 60,000 in silico samples, performed the best with a median uncertainty of 1.39x${10}^{-2}$ and ROC AUC of 0.849 for all validation samples. Full article

Slope stability assessment is a critical component of engineering safety. Conventional analytical methods frequently struggle to integrate heterogeneous slope data and model intricate failure mechanisms, thereby constraining their efficacy in practical engineering scenarios. To tackle these issues, this study presents a novel slope stability classification model grounded in the Optuna-TPE-CatBoost framework. By leveraging the Tree-structured Parzen Estimator (TPE) within the Optuna framework, the model adaptively optimizes CatBoost hyperparameters, thus enhancing prediction accuracy and robustness. It incorporates six key features—slope height, slope angle, unit weight, cohesion, internal friction angle, and the pore pressure ratio—to establish a comprehensive and intelligent assessment system. Utilizing a dataset of 272 slope cases, the model was trained with k-fold cross-validation and dynamic class imbalance strategies to ensure its generalizability. The optimized model achieved impressive performance metrics: an area under the receiver operating characteristic curve (AUC) of 0.926, an accuracy of 0.901, a recall of 0.874, and an F1-score of 0.881, outperforming benchmark algorithms such as XGBoost, LightGBM, and the unoptimized CatBoost. Validation via engineering case studies confirms that the model accurately evaluates slope stability across diverse scenarios and effectively captures the complex interactions between key parameters. This model offers a reliable and interpretable solution for slope stability assessment under complex failure mechanisms. Full article

Landslide susceptibility modelling represents an efficient approach to enhance disaster management and mitigation strategies. The focus of this paper lies in the development of a landslide susceptibility evaluation in northwestern Tunisia using the Analytical Hierarchy Process (AHP) and Artificial Neural Network (ANN) approaches. The used database covers 286 landslides, including ten landslide factor maps: rainfall, slope, aspect, topographic roughness index, lithology, land use and land cover, distance from streams, drainage density, lineament density, and distance from roads. The AHP and ANN approaches were applied to classify the factors by analyzing the correlation relationship between landslide distribution and the significance of associated factors. The Landslide Susceptibility Index result reveals five susceptible zones organized from very low to very high risk, where the zones with the highest risks are associated with the combination of extreme amounts of rainfall and steep slope. The performance of the models was confirmed utilizing the area under the Relative Operating Characteristic (ROC) curves. The computed ROC curve (AUC) values (0.720 for ANN and 0.651 for AHP) convey the advantage of the ANN method compared to the AHP method. The overlay of the landslide inventory data locations of historical landslides and susceptibility maps shows the concordance of the results, which is in favor of the established model reliability. Full article

Background: Accurate and timely prediction of mortality in intensive care unit (ICU) patients, particularly those with COVID-19, remains clinically challenging due to complex immune responses. Proteomic cytokine profiling holds promise for refining mortality risk assessment. Methods: Serum samples from 89 ICU patients (55 discharged, 34 deceased) were analyzed using a multiplex 21-cytokine panel. Samples were stratified into three groups based on time from collection to outcome: ≤48 h (Group 1: Early), >48 h to ≤7 days (Group 2: Intermediate), and >7 days to ≤14 days (Group 3: Late). Cytokine levels, simple cytokine ratios, and previously unexplored complex ratios between pro- and anti-inflammatory cytokines were evaluated. Machine learning-based feature selection identified the most predictive ratios, with performance evaluated by area under the curve (AUC), sensitivity, and specificity. Results: Complex cytokine ratios demonstrated superior predictive accuracy compared to traditional severity markers (APACHE II, SAPS II, SOFA), individual cytokines, and simple ratios, effectively distinguishing discharged from deceased patients across all groups (AUC: 0.918–1.000; sensitivity: 0.826–1.000; specificity: 0.775–0.900). Conclusions: Multiplex cytokine profiling enhanced by computationally derived complex ratios may offer robust predictive capabilities for ICU mortality risk stratification, serving as a valuable tool for personalized prognosis in critical care. Full article

Background: Pancreatic cystic lesions (PCLs), including intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), pose a diagnostic challenge due to their variable malignant potential. Current guidelines, such as Fukuoka and American Gastroenterological Association (AGA), have moderate predictive accuracy and may lead to overtreatment or missed malignancies. Artificial intelligence (AI), incorporating machine learning (ML) and deep learning (DL), offers the potential to improve risk stratification, diagnosis, and management of PCLs by integrating clinical, radiological, and molecular data. This is the first systematic review to evaluate the application, performance, and clinical utility of AI models in the diagnosis, classification, prognosis, and management of pancreatic cysts. Methods: A systematic review was conducted in accordance with PRISMA guidelines and registered on PROSPERO (CRD420251008593). Databases searched included PubMed, EMBASE, Scopus, and Cochrane Library up to March 2025. The inclusion criteria encompassed original studies employing AI, ML, or DL in human subjects with pancreatic cysts, evaluating diagnostic, classification, or prognostic outcomes. Data were extracted on the study design, imaging modality, model type, sample size, performance metrics (accuracy, sensitivity, specificity, and area under the curve (AUC)), and validation methods. Study quality and bias were assessed using the PROBAST and adherence to TRIPOD reporting guidelines. Results: From 847 records, 31 studies met the inclusion criteria. Most were retrospective observational (n = 27, 87%) and focused on preoperative diagnostic applications (n = 30, 97%), with only one addressing prognosis. Imaging modalities included Computed Tomography (CT) (48%), endoscopic ultrasound (EUS) (26%), and Magnetic Resonance Imaging (MRI) (9.7%). Neural networks, particularly convolutional neural networks (CNNs), were the most common AI models (n = 16), followed by logistic regression (n = 4) and support vector machines (n = 3). The median reported AUC across studies was 0.912, with 55% of models achieving AUC ≥ 0.80. The models outperformed clinicians or existing guidelines in 11 studies. IPMN stratification and subtype classification were common focuses, with CNN-based EUS models achieving accuracies of up to 99.6%. Only 10 studies (32%) performed external validation. The risk of bias was high in 93.5% of studies, and TRIPOD adherence averaged 48%. Conclusions: AI demonstrates strong potential in improving the diagnosis and risk stratification of pancreatic cysts, with several models outperforming current clinical guidelines and human readers. However, widespread clinical adoption is hindered by high risk of bias, lack of external validation, and limited interpretability of complex models. Future work should prioritise multicentre prospective studies, standardised model reporting, and development of interpretable, externally validated tools to support clinical integration. Full article

Background: Septic arthritis is an orthopedic emergency. However, optimal biomarkers and diagnostic criteria remain unclear. The study aimed to evaluate the diagnostic performance of routinely used and novel biomarkers, including serum C-reactive protein (CRP), synovial white blood cells (WBC), pentraxin-3 (PTX3), interleukin-6 (IL-6), and presepsin, in distinguishing septic from non-septic arthritis. Methods: Thirty-one patients undergoing arthrocentesis were included. Patients were categorized into septic and non-septic arthritis groups. Synovial fluid and serum samples were analyzed for five biomarkers. Diagnostic performance was assessed by calculating the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: Synovial WBC demonstrated the highest diagnostic performance among single biomarkers (AUC = 0.837, p = 0.012). Among novel biomarkers, PTX3 showed the highest accuracy and sensitivity. The serum CRP and synovial WBC combination yielded an AUC of 0.853, with 100% sensitivity, 68.0% specificity, 42.9% PPV, and 100% NPV. Adding all three novel biomarkers to this combination increased the AUC to 0.887 (p = 0.004), maintaining 100% sensitivity and NPV. When individually added, PTX3 achieved 100% sensitivity and NPV, while presepsin showed the highest specificity (96.0%), PPV (75.0%), and accuracy (87.1%). Conclusions: Serum CRP and synovial WBC remain essential biomarkers for diagnosing septic arthritis; however, combining them with PTX3, IL-6, and presepsin improved diagnostic accuracy. PTX3 is best suited for ruling out septic arthritis due to its high sensitivity and NPV, whereas presepsin is more useful for confirmation, given its specificity and PPV. These results support a tailored biomarker approach aligned with diagnostic intent. Full article

Xi’an, China, has a complex geological environment, with geological hazards seriously hindering urban development and safety. This study analyzed the conditions leading to disaster formation and screened 12 evaluation factors (e.g., slope and slope direction) using Spearman’s correlation. Furthermore, it also introduced an innovative combined weighting method, integrating subjective weights from the hierarchical analysis method and objective weights from the entropy method, as well as an information value model for susceptibility assessment. The main results are as follows: (1) There are 787 hazard points—landslides/collapses are concentrated in loess areas and Qinling foothills, while subsidence/fissures are concentrated in plains. (2) The combined weighting method effectively overcame the limitations of single methods. (3) Validation using hazard density and ROC curves showed that the combined weighting information value model achieved the highest accuracy (AUC = 0.872). (4) The model was applied to classify the disaster susceptibility of Xi’an into high (12.31%), medium (18.68%), low (7.88%), and non-susceptible (61.14%) zones. The results are consistent with the actual distribution of disasters, thus providing a scientific basis for disaster prevention. Full article