Search Results (355)

Background: Early and accurate differentiation between melanomas and benign nevi is essential for making proper clinical decisions. This study aimed to identify clinical, morphological, and histopathological variables most strongly associated with melanoma, using both statistical and machine learning approaches. Methods: This study evaluated 184 melanocytic lesions using clinical, morphological, and histopathological parameters. Univariable analyses were performed in XLStat statistical software, version 2014.5.03, while multivariable machine learning models were developed in Jamovi (version 2.4). Five supervised algorithms (random forest, partial least squares, elastic net regression, conditional inference trees, and k-nearest neighbors) were compared using repeated cross-validation, with performance evaluated by accuracy, Kappa, sensitivity, specificity, F1 score, and calibration. Results: Univariable analysis identified significant differences between melanomas and nevi in age, horizontal diameter, gender, lesion location, and selected histopathological features (cytological and extracellular matrix changes, epidermal interactions). However, several associations weakened in multivariable analysis due to collinearity and overlapping effects. Using glmnet, the most influential independent predictors were cytological changes, horizontal diameter, epidermal interactions, and extracellular matrix features, alongside age, gender, and lesion location. The model achieved high discrimination (AUC = 0.97, 95% CI: 0.93–0.99) and accuracy (training: 95.3%; test: 92.6%), confirming robustness. Conclusions: Structured demographic, morphological, and histopathological data—particularly age, lesion size, cytological and extracellular matrix changes, and epidermal interactions—can effectively support classification of melanocytic lesions. Machine learning approaches (the glmnet model in our study) provide a reliable framework to evaluate such predictors and offer practical diagnostic support in dermatopathology. Full article

Bone and bone marrow Metastasis (BBM) are life-threatening complications of advanced malignancies, frequently requiring intensive care and associated with high short-term mortality. However, prognostic tools specifically tailored to critically ill BBM patients are limited. This multicenter cohort study aimed to develop and validate deep learning models for predicting 30-day mortality using ICU data from MIMIC-IV, eICU-CRD, and the First Affiliated Hospital of Xinjiang Medical University. After univariate screening, XGBoost-Boruta and Lasso regression identified 11 key clinical features within 24 h of ICU admission. Thirteen deep learning models were trained using five-fold cross-validation, and their performance was evaluated through AUC, average precision, calibration, and decision curves. TabNet achieved the best internal performance (AUC 0.878; AP 0.940) and maintained strong discrimination in both same-region (eICU: AUC 0.840; AP 0.932) and cross-regional (Xinjiang: AUC 0.831; Accuracy 80.5%) validation. SHAP and attention-based interpretability analyses consistently identified SOFA, serum calcium, and albumin as dominant predictors. A TabNet-based online calculator was subsequently deployed to enable bedside mortality risk estimation. In conclusion, TabNet demonstrates potential as an accurate and interpretable tool for early mortality risk stratification in critically ill BBM patients, offering support for more timely and individualized decision-making in BBM-related critical care. Full article

Head and neck squamous cell carcinoma (HNSCC) is often diagnosed at advanced stages. Due to pronounced intratumoral heterogeneity (ITH), reliable risk stratification and prediction of treatment response remain challenging. This study aimed to identify peptide signatures in HNSCC tissue that are associated with treatment outcomes in HPV-negative, advanced-stage HNSCC patients undergoing 5-fluorouracil/platinum-based chemoradiotherapy (CDDP-CRT). We integrated matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) of tryptic peptides with univariate statistics and machine learning approaches to uncover potential prognostic patterns. Formalin-fixed, paraffin-embedded whole tumor sections from 31 treatment-naive, HPV-negative HNSCC patients were digested in situ with trypsin, and the generated peptides were analyzed using MALDI-MSI. Clinical follow-up revealed recurrence or progression (RecPro) in 20 patients, while 11 patients showed no evidence of disease (NED). Classification models were developed based on the recorded peptide profiles using both unrestricted and feature-restricted approaches, employing either the full set of m/z features or a subset of the most discriminatory m/z features, respectively. The unrestricted model achieved a balanced accuracy of 71% at the patient level (75% sensitivity, 66% specificity), whereas the feature-restricted model reached a balanced accuracy of 72%, showing increased specificity (92%) but reduced sensitivity (52%) in the CDDP-CRT cohort. In order to assess treatment specificity, models trained on the CDDP-CRT cohort were tested on an independent patient cohort treated with mitomycin C-based CRT (MMC-CRT). Neither model demonstrated prognostic performance in the MMC-CRT patient cohort, suggesting specificity for platinum-based therapy. Presented findings highlight the potential of MALDI-MSI–based proteomic profiling to identify patients at elevated risk of recurrence following CDDP-CRT. This approach may support more personalized risk assessment and treatment planning, ultimately contributing to improved therapeutic outcomes in HPV-negative HNSCC. Full article

Background: Disasters, although predictable, often occur unexpectedly, and efforts must be directed towards reducing their impact. Emergency healthcare workers, key players in disaster response, should maintain a high level of preparedness to act in catastrophic situations. Data on knowledge, attitude, and disaster preparedness among emergency healthcare workers is scarce, particularly for developed countries in Europe. This study aimed to measure the perceived preparedness of various health practitioners in emergency care in Iași county (Romania) and identify factors that influence it. Materials and methods: A self-assessment web-based questionnaire was developed to measure knowledge (K), attitude (A), and preparedness (P). Nonparametric tests compared measurements between demographic groups. Spearman correlation, linear univariate, and multivariate regression models were used to test the effect of perceived knowledge, attitude, and other work-related factors (such as experience, training, and leadership) on disaster preparedness. Results: 211 valid entries were recorded (114 female and 97 male), of which 33.6% were doctors, 25.1% were nurses, and 23.7% were paramedics. There were differences in exposure to training across health professions for disasters and trauma management (p = 0.03 and p = 0.009). The sample’s overall scores for the three primary domains assessed were moderate. Univariate analyses identified a significant effect of knowledge and attitude on preparedness (B = 0.9, 95% CI: 0.79–1.01, p < 0.001, and B = 0.81, 95% CI: 0.66–0.97, p < 0.001, respectively), which was maintained in multivariate regression. Workplace factors (disaster plans and institutional collaboration), along with experience in disaster management and emergency care, were determinants of preparedness, while the effect of training was insignificant. Conclusions: Most healthcare workers displayed moderate preparedness for disasters, while exposure to training and practice was found to be inadequate. Focus should be placed on identifying barriers and enhancing training delivery, strengthening institutional involvement in staff preparedness, and improving inter-professional collaborations. Adequate training methods must be developed and validated in further studies. Full article

Mine water hazards represent one of the principal threats to safe coal mine operations; therefore, accurately predicting mine water inflow is critical for drainage system design and water hazard mitigation. Because mine water inflow is governed by the combined influence of multiple hydrogeological factors and thus exhibits pronounced non-linear characteristics, conventional approaches are inadequate in terms of forecasting accuracy and medium- to long-term predictive capability. To address this issue, this study proposes a Chaos-Autoformer-based method for predicting mine water inflow. First, the univariate inflow series is mapped into an m-dimensional phase space by means of phase-space reconstruction from chaos theory, thereby fully preserving its non-linear features; the reconstructed vectors are then used to train and forecast inflow with an improved Chaos-Autoformer model. On top of the original Autoformer architecture, the proposed model incorporates a Chaos-Attention mechanism and a Lyap-Dropout scheme, which enhance sensitivity to small perturbations in initial conditions and complex non-linear propagation paths while improving stability in long-horizon forecasting. In addition, the loss function integrates the maximum Lyapunov exponent error and earth mode decomposition (EMD) indices so as to jointly evaluate dynamical consistency and predictive performance. An empirical analysis based on monitoring data from the Liangshuijing Coal Mine for 2022–2025 demonstrates that the trained model delivers high accuracy and stable performance. Ablation experiments further confirm the significant contribution of the chaos-aware components: when these modules are removed, forecasting accuracy declines to only 76.5%. Using the trained model to predict mine water inflow for the period from June 2024 to June 2025 yields a root mean square error (RMSE) of 30.73 m³/h and a coefficient of determination (R²) of 0.895 against observed data, indicating excellent fitting and predictive capability for medium- to long-term tasks. Extending the forecast to July 2025–November 2027 reveals a pronounced annual cyclical pattern in future mine water inflow, with markedly higher inflow in summer than in winter and an overall slowly declining trend. These findings show that the Chaos-Autoformer can achieve high-precision medium- and long-term predictions of mine water inflow, thereby providing technical support for proactive deployment and refined management of mine water hazard prevention. Full article

Objective: Sarcopenic obesity (SO) is a combination of depleted skeletal muscle mass and obesity, with a high prevalence, undetected onset, challenging diagnosis, and poor prognosis. However, studies on SO in cancer settings are limited. We aimed to explore the association between SO and mortality and to investigate potential predictors involved in the development of SO, with a further objective of constructing a model to detect its occurrence in cancer patients. Methods: The data of 1432 cancer patients from the National Health and Nutrition Examination Survey (NHANES) from the years 1999 to 2006 and 2011 to 2016 were included. For survival analysis, univariable and multivariable Cox proportional hazard models were used to examine the associations of SO with overall survival, adjusting for potential confounders. For machine learning, six algorithms, including logistic regression, stepwise logistic regression, least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were utilized to build models to predict the presence of SO. The predictive performances of each model were evaluated. Results: From six machine learning algorithms, cancer patients with SO were significantly associated with a higher risk of all-cause mortality (adjusted HR 1.368, 95%CI 1.107–1.690) compared with individuals without SO. Among the six machine learning algorithms, the optimal LASSO model achieved the highest area under the curve (AUC) of 0.891 on the training set and 0.873 on the test set, outperforming the other five machine learning algorithms. Conclusions: SO is a significant risk factor for the prognosis of cancer patients. Our constructed LASSO model to predict the presence of SO is an effective tool for clinical practice. This study is the first to utilize machine learning to explore the predictors of SO among cancer populations, providing valuable insights for future research. Full article

The bond strength at the interface between fiber-reinforced polymer (FRP) composites and concrete is a critical factor affecting the mechanical performance of strengthened structures. To investigate this behavior, a comprehensive database of 1032 single-shear test results was compiled. A genetic algorithm-optimized backpropagation (GA-BP) neural network was developed using six input parameters: concrete width and compressive strength, and the FRP plate’s width, elastic modulus, thickness, and effective bond length. The optimized network, with a 6-13-1 architecture, achieved the highest prediction accuracy, with R² = 0.93 and MAPE as low as 15.96%, outperforming all benchmark models. Eight existing bond strength prediction models were evaluated against the experimental data, revealing that models incorporating effective bond length achieved up to 35% lower prediction error than those that did not. A univariate sensitivity analysis showed that concrete compressive strength was the most influential parameter, with a normalized sensitivity coefficient of 0.325. The final trained weights and biases can be directly applied to similar prediction tasks without retraining. These results demonstrate the proposed model’s high accuracy, generalizability, and interpretability, offering a practical and efficient tool for evaluating FRP–concrete bond performance and supporting the design and rehabilitation of strengthened structures. Full article

The uncertainty and confrontational nature of war itself pose significant challenges to the collection and storage of aerial battlefield temporal data. To address the issue of insufficient training of intelligent models caused by the scarcity of air battlefield situation data, this paper designs an air battlefield time series data augmentation model based on a lightweight denoising diffusion probabilistic model (LDMKD-DA). Considering the advantages of a denoising diffusion probabilistic model (DDPM) in processing images, this paper transforms 1D time series data into image data. 1D univariate time series data, such as High-resolution Range Profile dataset, are transformed by Gramian angular fields and Markov transition fields. Multivariate time series data, such as the air target intention dataset, are transformed by matrix expansion. Then, the data augmentation model is constructed based on the denoising diffusion probabilistic model. Considering the need for miniaturization and intelligence in future combat platforms, the depthwise separable convolution is introduced to lighten the DDPM, and, at the same time, the improved knowledge distillation method is introduced to accelerate the sampling process. The experimental results show that LDMKD-DA is capable of generating synthetic data similar to real data with high quality while significantly reducing FLOPs and params, while having significant advantages in univariate and multivariate time series data amplification. Full article

This study aimed to validate the 9-point body condition score (BCS) system in sled dogs by assessing its reliability and by comparing it with objective measures including real-time ultrasonography, plicometry, and anthropometry. Twenty-seven Siberian Huskies (11 females, 16 males) from three sled dog teams were assessed for BCS by three trained veterinarians and their respective mushers. Intra-observer reliability was substantial (Krippendorff’s α = 0.734), while agreement between expert raters (Kα = 0.580) and between the expert rater and mushers (Kα = 0.691) was moderate, with mushers tending to overestimate the BCS of their own dogs (median difference = −0.5). BCS showed positive correlations with body mass index (BMI) and subcutaneous fat at the chest and flank via plicometry (for all: p < 0.05). Ultrasonography showed weak correlations with BCS, likely due to the different anatomical layers evaluated and the distinctively high muscle-to-fat ratio typical of sled dogs. Both univariate and multivariate analyses revealed sex- and neutering-related differences in body composition, with males generally presenting larger skeletal dimensions and neutering influencing patterns of fat distribution. These findings support the reliability and field applicability of the BCS system when used by trained evaluators, highlighting the importance of considering sex and anatomical site when assessing body condition in athletic dogs. The 9-point BCS, combined with accessible objective tools, represents a consistent, cost-effective method for monitoring body condition in long-distance performance sled dogs. Full article

Background: It is difficult to make a definite diagnosis of borderline epithelial ovarian tumors before surgery. In order to avoid incorrectly classifying tumors as benign, a differential diagnosis model was developed to distinguish between benign and borderline epithelial tumors utilizing multimodal information. Method: A multicenter study was conducted. A retrospective analysis of the transvaginal ultrasonography and clinical data of patients who underwent surgery and received pathological diagnoses of borderline and benign epithelial ovarian tumors was conducted. Both Univariate and multivariate logistic regression analyses were used to develop a diagnostic model for borderline epithelial tumors. The efficacy and feasibility of this model were assessed through examination of training, internal validation, and external test sets. Results: There was a significant difference in D-dimer levels between borderline and benign epithelial tumors. Abnormal CA125, D-dimer, maximum mass diameter > 10 cm, regular and irregular solid portions, and blood flow in the mass were independent risk factors for borderline epithelial ovarian tumors. The diagnostic model was evaluated by the Hosmer–Lemeshow test and demonstrated strong fitting capabilities. ROC curve analysis of the training set, verification set, and external test set confirmed the model’s predictive ability. Conclusions: These independent risk factors may be combined to assess the risk of borderline epithelial ovarian tumors. Our findings will assist novice gynecologic sonographers in distinguishing between benign and borderline epithelial tumors. Full article

The black-box nature of deep machine learning hinders the extraction of knowledge in science. To address this issue, a proposal for a neural network (k-net) based on the Kolmogorov–Arnold Representation Theorem is presented, pursuing to be an alternative to the traditional Multilayer Perceptron. In its core, the algorithmic nature of neural networks lies in the fundamental symmetry between forward-mode and reverse-mode accumulation techniques, both of which rely on the chain rule of partial derivatives. These methods are essential for computing gradients of functions, an operation that is at the core of the training process of neural networks. Automatic differentiation addresses the need for accurate and efficient calculation of derivative values in scientific computing; procedural programs are thus transformed into the computation of the required derivatives at the same numerical arguments. This work formalizes the algebraic structure of neural network computations by framing the training process within the domain of hyperdual numbers. Specifically, it defines a Kolmogorov–Arnold-inspired neural network (k-net) using dual numbers by extending the univariate functions and their compositions that appear in the representation theorem. This approach focuses on computation of the Jacobian and the ability to implement such procedures algorithmically, without sacrificing accuracy and mathematical rigor, while exploiting the inherent symmetry of the dual number formalism. Full article

Objectives: Migrants are at greater risk of psychiatric hospitalization. This study aims to improve care for migrants hospitalized in psychiatric wards in Morocco by studying comprehensive clinical and epidemiological characteristics, focusing on potential risk factors to guide mental health intervention efforts. Methods: The present retrospective multicenter study retrieved sociodemographic, clinical data, and patient records of migrants admitted to a large Moroccan psychiatric hospital in the Rabat region between 2013 and 2023 in order to delineate characteristics and risk factors for psychiatric hospitalizations. Descriptive and univariable analyses were conducted using chi-square, Fisher’s exact, and Mann–Whitney tests, and multivariable logistic regression analyses were performed by Jamovi 2.3.28.0 software to predict rehospitalization. Results: A total of 102 patient files were analyzed. Of these, 72.5% were single men, 27.5% had mental health problems prior to migration, 23.5% had attempted suicide, and 88.2% had negative insight. Some 94.86% were hospitalized against their will, 73.5% were diagnosed with psychosis, and only 2 were diagnosed with a stress-related disorder. Some 34.3% were hospitalized. Factors significantly associated with hospitalized were divorced family status, presence of psychotic pathology, and number of family members between five and nine with OR = 5.28, CI [1.04–26.68], p = 0.044; OR = 5.95, CI [2.02–17.44], p = 0.001; and OR = 6.02, CI [1.71–21.11], p = 0.005, respectively. Shorter length of stay in Morocco, unemployment, asylum seekers, and use of restraints were more frequent in hospitalized patients. Conclusions: Identifying at-risk migrants and setting up culturally appropriate, trauma-informed services can reduce the number of hospital admissions and boost the training and awareness of healthcare professionals in this area. Full article

Posterior capsule opacification (PCO), a frequent complication of cataract surgery, arises from dysregulated wound healing and fibrotic transformation of residual lens epithelial cells. While transcriptomic and machine learning (ML) approaches have elucidated fibrosis-related pathways in other tissues, the molecular divergence between regenerative and fibrotic outcomes in the lens remains unclear. Here, we used an ex vivo chick lens injury model to simulate post-surgical conditions, collecting RNA from lenses undergoing either regenerative wound healing or fibrosis between days 1–3 post-injury. Bulk RNA sequencing data were normalized, log-transformed, and subjected to univariate filtering prior to training LASSO, SVM, and RF ML models to identify discriminatory gene signatures. Each model was independently validated using a held-out test set. Distinct gene sets were identified, including fibrosis-associated genes (VGLL3, CEBPD, MXRA7, LMNA, gga-miR-143, RF00072) and wound-healing-associated genes (HS3ST2, ID1), with several achieving perfect classification. Gene Set Enrichment Analysis revealed divergent pathway activation, including extracellular matrix remodeling, DNA replication, and spliceosome associated with fibrosis. RT-PCR in independent explants confirmed key differential expression levels. These findings demonstrate the utility of supervised ML for discovering lens-specific fibrotic and regenerative gene features and nominate biomarkers for targeted intervention to mitigate PCO. Full article

Objective: Shoulder dystocia (ShD) is a rare but serious obstetric emergency associated with significant neonatal morbidity. This study aimed to evaluate the predictive performance of machine learning (ML) models based on fetal biometric ratios and clinical characteristics for the identification of ShD in pregnancies without clinical suspicion of macrosomia. Methods: We conducted a retrospective case-control study including 284 women (84 ShD cases and 200 controls) who underwent spontaneous vaginal delivery between 37 and 42 weeks of gestation. All participants had an estimated fetal weight (EFW) below the 90th percentile according to Hadlock reference curves. Univariate and multivariate logistic regression analyses were performed on maternal and neonatal parameters, and statistically significant variables (p < 0.05) were used to construct adjusted odds ratio (aOR) models. Supervised ML models—Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGB)—were trained and tested to assess predictive accuracy. Performance metrics included AUC-ROC, sensitivity, specificity, accuracy, and F1-score. Results: The BPD/AC ratio and AC/FL ratio markedly enhanced the prediction of ShD. When added to other features in RF models, the BPD/AC ratio got an AUC of 0.884 (95% CI: 0.802–0.957), a sensitivity of 68%, and a specificity of 83%. On the other hand, the AC/FL ratio, along with other factors, led to an AUC of 0.896 (95% CI: 0.805–0.972), 68% sensitivity, and 90% specificity. Conclusions: In pregnancies without clinical suspicion of macrosomia, ML models integrating fetal biometric ratios with maternal and labor-related factors significantly improved the prediction of ShD. These models may support clinical decision-making in low-risk deliveries where ShD is often unexpected. Full article

Regulatory T cells (Tregs) have multiple roles in the tumor microenvironment (TME), which maintain a balance between autoimmunity and immunosuppression. This research aimed to investigate the interaction between cancer stemness and Regulatory T cells (Tregs) in the breast cancer tumor immune microenvironment. Breast cancer stemness was calculated using one-class logistic regression. Twelve main cell clusters were identified, and the subsequent three subsets of Regulatory T cells with different differentiation states were identified as being closely related to immune regulation and metabolic pathways. A prognostic risk model including MEA1, MTFP1, PASK, PSENEN, PSME2, RCC2, and SH2D2A was generated through the intersection between Regulatory T cell differentiation-related genes and stemness-related genes using LASSO and univariate Cox regression. The patient’s total survival times were predicted and validated with AUC of 0.96 and 0.831 in both training and validation sets, respectively; the immunotherapeutic predication efficacy of prognostic signature was confirmed in four ICI RNA-Seq cohorts. Seven drugs, including Ethinyl Estradiol, Epigallocatechin gallate, Cyclosporine, Gentamicin, Doxorubicin, Ivermectin, and Dronabinol for prognostic signature, were screened through molecular docking and found a synergistic effect among drugs with deep learning. Our prognostic signature potentially paves the way for overcoming immune resistance, and blocking the interaction between cancer stemness and Tregs may be a new approach in the treatment of breast cancer. Full article