Search Results (805)

Background/Objectives: Type 2 diabetes may impair anterior segment immune regulation. Because transforming growth factor-β2 maintains ocular immune privilege, while nuclear factor-κB is linked to inflammatory activation, we compared their aqueous humor levels in cataract patients with and without diabetes. Methods: In this prospective cross-sectional study, aqueous humor samples were collected from 90 patients (30 diabetic, 60 non-diabetic) via anterior chamber needle aspiration at the commencement of routine phacoemulsification, prior to viscoelastic injection, without additional intervention. Transforming growth factor-β2 and nuclear factor-κB levels were then measured using enzyme-linked immunosorbent assay (ELISA). Between-group comparisons and ROC curve analyses were performed to evaluate differences in biomarker levels and their discriminative ability in distinguishing diabetic status. Covariate-adjusted analysis (ANCOVA) was additionally performed. Results: Transforming growth factor-β2 levels were significantly lower in the diabetic group (p < 0.001), while nuclear factor-κB levels showed no significant difference (p = 0.285). The between-group difference in transforming growth factor-β2 remained significant after adjustment for cataract grade and hypertension duration (F(1,86) = 17.901, p < 0.001, partial η² = 0.172; Cohen’s d = 0.94). Transforming growth factor-β2 demonstrated high specificity (100%) but limited sensitivity (45%) for identifying diabetic status at a cut-off of <449.25 ng/L; however, given the small sample size and exploratory nature of the study, this specificity value should be interpreted with caution and requires validation in larger cohorts. Conclusions: Lower aqueous humor TGF-β2 levels in diabetic cataract patients, independent of cataract severity and hypertension duration, suggest that TGF-β2 suppression may represent an earlier molecular event in anterior segment immune dysregulation preceding overt inflammatory activation. While TGF-β2 shows exploratory biomarker potential, validation in larger, prospective, mechanistic studies is required before clinical application. Full article

Background/Objectives: Acute care use (ACU)—emergency department visits, inpatient hospitalizations, and observation stays—drives morbidity and costs among adults with diabetes. We developed and evaluated machine-learning models to predict 1-year ACU risk using electronic health record (EHR) data and neighborhood-level data. Methods: We performed a retrospective cohort study using de-identified EHR data from a large urban academic health center, including adults (≥18 years) with diabetes (N = 23,052). The index date was defined as one year before each patient’s last encounter, and ACU was assessed during the subsequent year. We modeled 180 predictors spanning demographics, Area Deprivation Index (ADI), prior healthcare utilization, vitals/BMI, comorbidities, medications, and laboratory results. Decision tree and gradient-boosted models (XGBoost, LightGBM, CatBoost) were tuned with Optuna using 8-fold stratified cross-validation, optimizing area under the receiver operating characteristic curve (AUC). To improve class-balanced classification performance under outcome imbalance, we selected post hoc probability thresholds that maximized Macro F1 and quantified interpretability with permutation feature importance. Results: ACU occurred in 30.53% of patients (7039/23,052). Boosted models achieved AUC ≈ 0.78, with LightGBM performing best (AUC = 0.7839). Macro F1–optimized thresholds (<0.5; typically 0.375–0.40) improved class-balanced performance versus a 0.5 cutoff. Across boosted models, prior utilization features dominated, followed by discharge-related factors and neighborhood deprivation; comorbidities and laboratory results contributed. Conclusions: In this single urban academic health-system cohort of adults with diabetes, EHRbased boosted models demonstrated moderate discrimination for predicting 1-year ACU and identified interpretable predictive signals. Threshold optimization improved class-balanced statistical performance. Prior utilization, care transitions, and neighborhood deprivation emerged as dominant predictive features. External and temporal validation are needed before broader application. Full article

Hydrothermal alteration mapping is a critical component of porphyry copper exploration because alteration assemblages provide important vectors toward mineralization. This study presents a systematic evaluation of supervised machine learning algorithms for delineating hydrothermal alteration zones using Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) short-wave infrared (SWIR) surface reflectance data (AST_07XT). The investigation focuses on the Nain region within the central Urumieh–Dokhtar Magmatic Arc (UDMA), Iran, a major metallogenic belt hosting numerous porphyry copper systems. Representative spectral endmembers corresponding to Al–OH-bearing and Mg–OH-bearing hydrothermal alteration minerals were extracted using Minimum Noise Fraction (MNF), Pixel Purity Index (PPI), and n-dimensional visualization techniques. These endmembers were subsequently used to train and evaluate a comprehensive suite of supervised machine learning classifiers, including linear, kernel-based, tree-based, ensemble, probabilistic, boosting, and neural-network algorithms for pixel-wise hydrothermal alteration mapping. Model performance was evaluated using multiple statistical metrics, including overall accuracy (OA), average accuracy (AA), precision, recall, F1-score, Cohen’s kappa coefficient, area under the ROC curve (AUC), spatial cross-validation accuracy, uncertainty analysis, and spatial agreement analysis. Among the evaluated classifiers, SVM_Linear, SVM_RBF, LDA, and MLP achieved the highest classification performance, with overall accuracies exceeding 94% and strong spatial consistency between classified maps. The resulting alteration maps display spatially coherent distributions of Al–OH and Mg–OH minerals that are consistent with established hydrothermal alteration zoning models in porphyry–epithermal systems. The mapped hydrothermal alteration zones show strong spatial correspondence with known mineralized areas and alteration patterns within the Urumieh–Dokhtar Magmatic Arc, confirming the geological reliability of the classification results. Uncertainty analysis further indicates high model confidence across most alteration zones, with higher uncertainty values mainly restricted to transitional and spectrally heterogeneous regions. The results demonstrate that integrating ASTER SWIR imagery with supervised machine learning algorithms provides a robust, scalable, and transferable framework for regional-scale hydrothermal alteration mapping and mineral exploration in porphyry copper provinces. Full article

Background/Objectives: Type 2 diabetes mellitus (T2DM) is a prevalent metabolic disorder associated with substantial long-term morbidity and mortality. Routinely collected anthropometric, biochemical, and hematological variables may contain useful discriminatory information for data-driven classification. This study aimed to compare the apparent classification performance of multiple machine learning algorithms for distinguishing individuals with and without T2DM using routinely obtained clinical parameters in a single-center dataset. Methods: This single-center observational study included 160 adults (95 females, 65 males) evaluated at the Endocrinology Outpatient Clinic of Gaziantep Islam Science and Technology University, Faculty of Medicine, Ersin Arslan Training and Research Hospital. The dataset comprised anthropometric measurements, biochemical markers, and complete blood count parameters. SMOTE was applied only within the training folds to address class imbalance and to avoid information leakage. Following fold-internal data preprocessing, which included imputing missing values and feature standardization where appropriate, the dataset was evaluated using stratified 5-fold cross-validation. SHAP analysis was performed to interpret the model predictions. A calibration curve was used to assess the model’s reliability. Eight supervised machine learning models were evaluated with and without HbA1c: Logistic Regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Decision Tree, Random Forest, Extra Trees, Gaussian Naive Bayes, and k-Nearest Neighbors. Model performance was evaluated using accuracy, sensitivity, specificity, and F1 score, and ROC curves were used as a diagnostic tool. Results: The models were evaluated in two different ways: with and without HbA1c. Random Forest demonstrated the best classification performance in the cross-validated evaluation; without HbA1c, it achieved 92.2% accuracy, 93.9% sensitivity, 97.9% specificity, and a 95.9% F1 score. When HbA1c was included, it achieved 98.0% accuracy, 97.9% sensitivity, 98.8% specificity, and a 99.0% F1 score. Decision Tree and Extra Trees demonstrated strong performance with accuracy rates of 87.6% and 92.8%, respectively, without HbA1c, and 90% and 93.5% when HbA1c was included; in contrast, KNN yielded the lowest accuracy rate (70.6%). Overall, tree-based models performed better than linear classifiers on this dataset. Conclusions: Machine learning models based on routine clinical and anthropometric variables demonstrated promising performance for T2DM classification in this single-center dataset; tree-based approaches yielded the most promising results. Including HbA1c improved the models’ ability to classify individuals with and without T2DM. However, since HbA1c was included both as a predictor and as part of the operational definition of the diabetes group, the findings should be interpreted with caution due to the risk of target leakage. Therefore, these results should be considered exploratory rather than evidence of clinically applicable predictive performance, and an independent external validation study should be conducted prior to clinical application. Full article

Glioblastoma has a high recurrence rate, yet conventional single-time-point imaging fails to capture the dynamic tumor evolution before and after surgery. This study aims to develop a deep learning model based on preoperative and postoperative longitudinal MRI to predict postoperative recurrence risk by capturing imaging dynamics. We propose MambaDiff-Net, which employs a dual-stream encoder to extract multi-scale features from preoperative and postoperative T2WI. It also includes a feature discrepancy computation module to model longitudinal imaging changes, outputting individualized recurrence risk probabilities. We included 139 patients with glioblastoma (59 training, 40 internal validation, 40 external test), with recurrence within 6 months post-surgery as the prediction target. Performance was evaluated using AUC, accuracy, and F1. MambaDiff-Net achieved AUCs of 0.887 and 0.762 in internal and external validation, respectively, significantly outperforming single-time-point models. Kaplan-Meier analysis demonstrated effective risk stratification, and decision curve analysis confirmed superior clinical net benefit. Grad-CAM visualization showed the model’s focus shifting from preoperative tumor parenchyma to postoperative resection cavity margins, consistent with clinical knowledge. A deep learning model based on preoperative-postoperative longitudinal MRI can accurately predict postoperative recurrence risk in glioblastoma. By modeling dynamic imaging changes before and after surgery, it supports individualized treatment decisions. Full article

Distributed seismic sensor networks integrated into the Internet of Things (IoT) infrastructure enable continuous condition monitoring of large-scale engineering structures. During long-term operation, however, measurement channels are subject to sensitivity drift, increased noise, and pulse artifacts that statistically mimic real vibration events. Related deep-learning techniques for noisy and ill-posed inverse problems have demonstrated the value of combining principled physical priors with deep models. Although the application domain differs, the underlying methodological insight—that constrained, physics-aware feature mappings can stabilize learning under noisy and partially observed conditions—directly motivates the use of a parameterized quantum circuit as a nonlinear feature transformer in the present work, where Hilbert space mapping serves as an analogous structural prior for the latent representation. Three principal fault modes are considered in this work, corresponding to the dominant degradation mechanisms observed in long-term seismic instrumentation: sensor drift, increased noise, and sensor failure. Each fault mode produces a distinct signature in the windowed feature space; the proposed model is trained to discriminate between them based on the latent CNN-LSTM-VQC representation. We propose a hybrid quantum-inspired deep-learning model (QC-DL) for the detection and diagnosis of channel-degradation anomalies. The architecture combines a 1D-CNN+LSTM feature extractor with a parameterized variational quantum circuit (VQC) used as a nonlinear feature transformer. All quantum experiments were performed on the QPanda3 CPUQVM simulator. The data were split chronologically prior to windowing to avoid information leakage. On real-world labeled accelerometric data with four operating modes (normal/drift/high-noise/failure), the QC-DL model achieved a macro-averaged F1 score of approximately 0.69 and per-class AUC values in the range 0.88–0.99. The mean early-detection latency was 1.6 s versus 2.1 s for the CNN-LSTM baseline (~24% reduction). An ablation study against a parameter-matched classical MLP showed that the gain is modest and not solely attributable to additional nonlinearity. The reported p-values (p = 0.70, p = 0.29) do not establish statistical significance. The results support the feasibility of hybrid quantum-inspired deep learning for sensor-channel verification, while highlighting the need for evaluation on real NISQ hardware. This paper proposes a hybrid quantum-inspired approach for detecting and diagnosing such anomalies in the time series of distributed seismic networks. The architecture combines a classical temporal feature extraction module based on one-dimensional convolutional layers and a recurrent long short-term memory (LSTM) network, which generates a latent window representation of the signal, with a parameterized variational quantum circuit used as a nonlinear feature processor in a hybrid computational circuit. Experimental validation was performed on real-world labeled data with multiple sensor degradation modes. The evaluation was organized in a scoring framework aligned with autonomous operation through window ranking and threshold alarm generation. In the experiments, the proposed model provided a macro-averaged F1 score of approximately 0.69 and area under the receiver operating characteristic (AUC) curve values in the range of 0.88–0.99 across classes, outperforming baseline deep models. The average early detection latency was 1.6 s versus 2.1 s for the baseline recurrent model (a 24% reduction). An ablative comparison with a control model based on a classical multilayer perceptron of comparable dimension confirmed that the improvement is not limited to the addition of additional nonlinearity. The obtained results indicate the potential of quantum-supported deep learning for improving the reliability of long-term vibration monitoring and verifying the correctness of sensor channels in distributed seismic networks. Full article

Breast cancer remains one of the most frequently diagnosed cancers worldwide, and improving the accuracy and transparency of automated diagnostic tools is an ongoing clinical priority. This study examines whether three established machine-learning classifiers achieve comparable performance on a standard breast cancer benchmark and whether their SHAP-based feature explanations converge on the same predictive signals across model architectures. Logistic Regression (LR), Support Vector Machines (SVM), and XGBoost were trained and tested on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset using a shared preprocessing pipeline to ensure fair comparison. Hyperparameters were selected through grid search with 5-fold stratified cross-validation, and model performance was estimated using 10-fold stratified cross-validation. Paired t-tests and Wilcoxon signed-rank tests were used to determine whether performance differences between models were statistically meaningful. Shapley Additive explanations (SHAP) values were computed separately for XGBoost using TreeExplainer and for Logistic Regression using LinearExplainer, and Spearman’s rank correlation was used to quantify the agreement between the two models’ feature importance rankings. All three classifiers achieved Receiver Operating Characteristic–Area Under the Curve (ROC-AUCs) above 0.994, with SVM achieving the highest accuracy (0.9737) and F1-score (0.9630). No statistically significant difference was found between any model pair (p > 0.05). The cross-model SHAP analysis yielded a Spearman correlation of r = 0.578 (p = 0.0008), with seven of the ten most important features ranked consistently across both architectures. The agreement between two structurally different models on which features matter most provides evidence that these features carry a consistent predictive signal that goes beyond what any single model’s architecture alone would produce. Cross-model explainability analysis of this kind offers a stronger basis for feature interpretation than the output of any single model. Full article

US egg production is undergoing a transition to cage-free (CF) housing systems. This transition has increased the need for automated monitoring tools to support welfare management and reduce production costs. While CF houses allow hens to perform natural behaviors such as dust bathing and foraging, a persistent challenge is severe feather pecking. Pecking block enrichment is used as a managemental approach to control severe feather pecking. However, manual quantification of such behavior is subjective and labor-intensive. This study evaluated the performance of small and large variants of both YOLOv10 and YOLO11 models for automatic detection of enrichment block pecking behavior in CF research environment. A total of 1061 color images were used to train and evaluate the models using 70:20:10 split for training, validation, and testing. Performance was assessed using precision, recall, mean average precision at 50% intersection over union (mAP50), confusion matrices, and F1–confidence curve. All models demonstrated robust performance, with precision, recall and mAP50 values greater than 0.94. YOLO11l achieved the highest precision with 0.969 and mAP50 with 0.988, while YOLOv10s achieved the highest recall of 0.962. Evaluation on test datasets showed robust generalization capability of the model, with high confidence detections. Overall, the findings show that YOLO models provide a consistent, objective, and scalable method for automatic quantification of pecking enrichment block related pecking behavior in a CF system. It offers potential as an automated monitoring tool for poultry researchers and may support future development of tools for commercial CF system. Full article

Background/Objectives: To evaluate the diagnostic potential of apparent diffusion coefficient (ADC) values for classifying lymph nodes as benign or malignant in breast cancer patients undergoing [¹⁸F]FDG-PET/MRI staging. Methods: Mean ADC values and short-axis diameters (±standard deviation) of 199 thoracic lymph nodes in 113 newly diagnosed breast cancer patients were retrospectively analyzed. All patients underwent [¹⁸F]FDG-PET/MRI staging, between July 2017 and June 2021. A node-by-node comparison was performed with respect to pathological node status. Nodal FDG uptake in whole-body [¹⁸F]FDG-PET/MRI served as reference standard for nodal malignancy. Group comparison using Mann–Whitney U test, receiver operating characteristic curve (ROC) analysis and diagnostic performance were calculated. p values below 0.05 were defined as statistically significant. Confidence intervals (CI; 95%) were calculated. Results: Ninety-three lymph nodes were FDG-negative while 106 lymph nodes were FDG-positive. FDG-negative lymph nodes had significantly lower short-axis diameters ((5.1 ± 1.5 mm versus 12.3 ± 5.3 mm); p < 0.01; U: 405.50; Z: −11.24). ADC values were significantly lower in FDG-positive lymph nodes (0.72 ± 0.14 × 10⁻³ mm²/s) than in FDG-negative lymph nodes ((1.18 ± 0.18 × 10⁻³ mm²/s); p < 0.01; U: 173.00; Z: −11.80). ROC analysis and Youden’s index revealed an ADC cut-off of 0.95 × 10⁻³ mm²/s (AUC: 0.98; p < 0.01; 95% CI: 0.96–1.01). According to the calculated cut-off, sensitivity, specificity, and accuracy of ADC values for differentiating FDG-negative from FDG-positive lymph nodes were 98%, 97% and 97%, respectively. Conclusions: ADC values derived from MRI were significantly associated with FDG uptake in this retrospective cohort and may serve as a complementary imaging biomarker for lymph node characterization. Full article

This study examines non-Newtonian electromagnetohydrodynamic (EMHD) blood flow via a diseased curved artery with minor stenosis and an aneurysm, adding a no-slip boundary condition, using targeted medication delivery of nanoparticles. The non-Newtonian behavior of blood flow is accounted for by the Casson fluid model. Using Corcione’s model, we have calculated the effective viscosity and thermal conductivity of nanofluids. The interaction of the nanofluid with physical phenomena such as viscous dissipation, electro-osmosis, radially applied uniform magnetic field and Joule heating can change the hemodynamic parameters of the fluid. The Crank–Nicolson approach has been used to calculate the velocity, temperature, and concentration patterns within the Debye–Huckel linearization approximation. Streamlines are delineated to analyze flow patterns across distinct physical factors. This study supports the design of magnetically guided $F{e}_3{O}_4$ nanoparticle–based targeted drug delivery systems for treating vascular diseases such as stenosis and aneurysm, improving site-specific therapeutic efficiency. The numerical insights into thermal effects and arterial geometry help to optimize nanoparticle transport, enhancing treatment precision while minimizing systemic side effects. Full article

Discontinuity-controlled rock masses in underground caverns are prone to block formation and instabilities during construction, motivating rapid tools for stability feedback analysis. Fast screening of discontinuity-controlled block hazards in underground caverns is addressed through a physics-consistent machine learning framework for identifying block formation and assessing instability conditional on formation. Cavern geometry, rock mass properties, and multiple joint sets are parametrically encoded, and physically and geometrically consistent data augmentation is performed. Three-dimensional discrete element batch simulations provide automated labels for block formation (y_B) and instability (y_U) (FoS < 1), forming a training dataset. Twenty-three raw features with a 66-dimensional engineered feature set are compared and multiple classifiers using PR/ROC curves, confusion matrices, and a BAcc-based threshold strategy are evaluated. Compared with raw inputs, the engineered features generally improve AUC-based ranking and balanced discrimination, especially for the RF model, although threshold-dependent recall and F1 trade-offs are observed for some learners. Random forests show consistently robust results. Benchmarking against an independent engineering reference based on stereographic projection and limit-equilibrium analysis gives 91% agreement for block-formation identification and 85.2% agreement for conditional instability identification. The trained model is integrated into an engineering platform to support batch screening of three- and four-plane combinations with 3D visualization outputs. Full article

The identification of liver tumors on computed tomography (CT) scans is hindered by myriad factors, including tumor heterogeneity, anatomical variability, and the limited interpretability of deep learning models in clinical settings. The present research introduces a deep learning-based framework, referred to as the ‘form of the Transformer’, in combination with Global Context (GC) fused with Transformer (Tf) and the Quantitative Attribution (QA) module, for a first reliable, explainable liver tumor detection framework. Moving away from traditional opaque classification systems, this framework uses gradient-based attribution with a localization module and evaluates its spatial alignment with tumor annotations without requiring segmentation supervision during model training. The framework accounts for long-range spacing and leverages Tf-Encoders, which substantially improve the system’s tumor-detection performance. Integrating the Attribution, this framework significantly enhances Qualitative Evidence (QE) in clinical settings. The experimental study has shown strong classification performance with the following metrics: accuracy 96.9%, precision 96.2%, recall 95.8%, F1-score 96.0%, area under the receiver operating characteristic curve 97.6%, and Matthews correlation coefficient 0.93. The classification-based localization of the system achieves an Intersection over Union (IoU) of 71.6% and a Dice coefficient of 83.5%, underscoring the alignment of tumor regions with their attributions. The results indicated significant improvements over existing CNN- and TF-based systems. Full article

Background/Objectives: Epiretinal membrane (ERM) is a common vitreoretinal disorder characterized by fibrocellular proliferation on the inner retinal surface, often leading to progressive visual impairment. Accurate grading of ERM severity using optical coherence tomography (OCT) is critical for treatment planning and surgical decision-making; however, manual grading is labor-intensive and subjective. This study aims to develop an automated and reliable deep learning-based method for ERM severity classification. Methods: We propose DenseViT-OCT, a hybrid deep learning model that integrates dense convolutional neural networks (CNN) and vision transformers (ViT). The model introduces three key modules: Multi-Scale Dense Feature Aggregation (MDFA) for capturing hierarchical features across multiple spatial scales, Adaptive Feature Calibration (AFC) for enhancing feature discrimination through channel and spatial attention, and Cross-Attention Feature Fusion (CAFF) for enabling bidirectional interaction between convolutional and transformer representations. The model was trained and evaluated on 2195 OCT B-scan images obtained from 397 patients. Results: DenseViT-OCT achieved an overall accuracy of 94.76% on the internal four-class test set, outperforming 19 benchmark models, including ConvNeXt, EfficientNet, ViT, and Swin Transformers. The model demonstrated balanced performance with a macro-averaged precision of 93.76%, recall of 93.22%, F1-score of 93.47%, Cohen’s kappa of 92.62%, and macro-Area Under the Curve (AUC) of 98.95%. Ablation experiments confirmed the contribution of the proposed MDFA, AFC, CAFF, and deep supervision components, with the full model consistently outperforming reduced variants and standalone DenseNet121 and ViT-B/16 backbones. In repeated experiments across five random seeds, DenseViT-OCT also achieved the best mean accuracy (0.9399 ± 0.0052). External validation on the public multicenter OCTDL dataset, performed as binary ERM-versus-normal classification because of label availability, yielded 90.76% accuracy and 97.61% AUC, indicating promising generalization beyond the development cohort. Conclusions: DenseViT-OCT provides a robust framework for automated ERM severity classification from OCT B-scans. The combination of local CNN features, global transformer context, and dedicated fusion modules improves classification performance and yields clinically meaningful error patterns. Although further stage-wise multicenter validation, volumetric OCT analysis, and prospective clinical assessment are required, the proposed method shows promise as a research-oriented decision-support framework for B-scan-level ERM assessment. Full article

Background/Objectives: Metabolic dysfunction-associated steatotic liver disease (MASLD) is now the leading cause of chronic liver disease globally, mirroring the increasing prevalence of obesity, insulin resistance, and type 2 diabetes. Early detection of hepatic steatosis is vital for cardiometabolic risk assessment; however, conventional imaging is costly and impractical for population screening. This study aimed to develop interpretable machine-learning models to predict ultrasound-detected hepatic steatosis within the MASLD spectrum using routinely available clinical and biochemical data. Methods: We analyzed data from 644 adults, 50% of whom had ultrasound-detected hepatic steatosis. Preprocessing, imputation, and feature selection were implemented within a single scikit-learn pipeline to avoid information leakage. An Elastic Net-regularized logistic regression identified the top 20 predictors, which were subsequently used across nine supervised machine learning (ML) classifiers. Model performance was evaluated via repeated stratified 5-fold cross-validation (25 resamples) using accuracy, F1 score, sensitivity, specificity, Youden’s J, balanced accuracy, and Area Under the Receiver Operating Characteristic Curve (AUROC). Interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: Participants with ultrasound-detected hepatic steatosis exhibited greater adiposity, insulin resistance, and dyslipidemia compared with controls [p < 0.05 for body mass index (BMI), waist circumference, glucose, glycated hemoglobin (HbA1c), triglycerides]. Elastic Net selection highlighted Weight, Ponderal Index, Fibrosis-4 Index (FIB-4), blood urea nitrogen (BUN)/Creatinine ratio, Aspartate Aminotransferase to Platelet Ratio Index (APRI), and Visceral Adiposity Index as the strongest predictors. Logistic Regression and Gradient Boosting achieved the best performance (accuracy = 0.65 ± 0.03; AUROC = 0.71 ± 0.04; balanced accuracy = 0.66 ± 0.06), outperforming rule-based indices such as Fatty Liver Index (FLI) and Hepatic Steatosis Index (HSI) reported in the literature. SHAP analysis confirmed clinically coherent feature effects, with higher anthropometric and hepatic injury indices increasing the predicted probability of ultrasound-detected hepatic steatosis. Conclusions: Routinely available clinical and biochemical parameters can predict hepatic steatosis with moderate accuracy using transparent, interpretable ML models. Logistic Regression and Gradient Boosting provided best discrimination and robust internal performance, offering a pragmatic, low-cost approach for early identification of ultrasound-detected hepatic steatosis within the MASLD spectrum in primary and metabolic care settings. Full article

One of the major determinants of crop productivity and sustainable agricultural practices is soil fertility. Proper soil assessment helps farmers make informed decisions about nutrients and fertilizers. This study utilizes 16 machine learning classifiers for soil fertility prediction, including learner-based, ensemble-based, instance-based, and probabilistic-based models. The model’s performance is assessed using accuracy, precision, recall, and F1-score. This paper presents a machine learning model for predicting soil fertility based on soil physicochemical characteristics. The data used in the research comprise vital soil parameters: nitrogen, phosphorus, potassium, pH, organic carbon, electrical conductivity, and micronutrients. Missing-value imputation, label encoding, and feature standardization are among the data preprocessing methods used to enhance data quality. Correlation analysis, ANOVA F-score, and mutual information were used to assess feature importance and determine the most significant soil characteristics. The experimental observation reveals that the RF model achieves an accuracy of 90.91% compared to the other models. Additional assessment using multi-class Receiver Operating Characteristic (ROC) and Precision–Recall (PR) curves showed excellent discriminative ability across the dominant soil fertility, which was of high quality. The findings show that machine learning models, especially ensemble-based models, are effective at estimating soil fertility levels. The proposed framework provides a data-driven, reliable decision-support system to assess soil fertility, enabling farmers and agricultural experts to enhance nutrient management and crop production. Full article