Reliable baseline biomarkers for progression toward rheumatoid arthritis in anti-citrullinated protein antibody-positive at-risk individuals remain insufficiently characterized. An exploratory leakage-safe machine learning framework combined with explainable artificial intelligence was developed to prioritize circulating proteomic signals associated with progression status in a small at-risk cohort. Baseline clinical and Olink proteomic data from 47 individuals (16 progressors and 31 non-progressors) were analyzed, although limited follow-up among non-progressors rendered the endpoint exploratory rather than prognostic. Of 1,472 quantified proteins, 1,449 were retained after application of a ≤20% missingness threshold. Fold-internal feature selection, including Cohen’s d-based ranking, correlation filtering (|r| < 0.85), and top-30 protein selection, was embedded within repeated stratified five-fold cross-validation. Predictive performance remained modest, with the primary support vector classifier achieving a mean Receiver Operating Characteristic Area Under the Curve (ROC-AUC) of 0.675 and Precision-Recall Area Under the Curve (PR-AUC) of 0.447, while calibration remained weak (Brier score = 0.231; calibration slope = 0.455). A 500-iteration permutation audit was not statistically significant (p = 0.164). Regularized logistic regression failed to improve discrimination, whereas incorporation of routine clinical covariates did not yield a reproducible advantage over proteomic features alone. Extreme gradient boosting demonstrated lower discriminative performance and was retained only for secondary interpretability analyses. Across Tree-based SHapley Additive exPlanations (TreeSHAP), Kernel SHapley Additive exPlanations (KernelSHAP) for the support vector classifier, and bootstrap perturbation analyses, trefoil factor 2 (TFF2), KIT proto-oncogene receptor tyrosine kinase (KIT), cadherin 3 (CDH3), angiopoietin-like 2 (ANGPTL2), interleukin-5 (IL5), and glypican-1 (GPC1) emerged as recurrent candidate proteins. Given the limited cohort size, weak calibration, and non-significant permutation testing, all findings should be regarded as exploratory. The primary contribution therefore lies in the establishment of a transparent, leakage-aware workflow for proteomic signal prioritization in severely underpowered p ≫ n settings, thereby supporting future longitudinal validation studies in preclinical rheumatoid arthritis.

Accurate classification of brain tumors from magnetic resonance imaging (MRI) is important for supporting timely diagnosis and subsequent clinical decision-making. In this study, EnDeC, an enhanced convolutional neural network, was developed for automated multiclass classification of brain MRI images. The Crystal Clean: Brain Tumors MRI Dataset, comprising 21,672 images categorized as glioma, meningioma, pituitary tumor, or normal, was used for model development and evaluation. Following data cleaning and class balancing, 12,264 images were retained for model training. Image preprocessing and augmentation procedures, including resizing, noise injection, and rotation, were applied. An efficient input pipeline was implemented using the TensorFlow tf.data application programming interface, with caching and prefetching incorporated to reduce input/output bottlenecks during training. The EnDeC architecture was constructed using successive convolutional and pooling layers for hierarchical feature extraction, followed by fully connected layers for multiclass classification. Model performance was evaluated using accuracy, precision, recall, F1-score, and specificity. Average values of 99.60%, 99.18%, 99.19%, 99.18%, and 99.74% were obtained for these metrics, respectively. Among the evaluated optimization configurations, the Adam optimizer yielded the highest test accuracy of 99.20%. These findings demonstrate that discriminative imaging features associated with multiple brain tumor categories can be effectively learned using the proposed convolutional neural network framework. Nevertheless, validation using independent, patient-level, multi-institutional datasets is required before clinical applicability can be established. The proposed approach provides a computational framework for automated brain MRI classification and may support the further development of computer-aided diagnostic systems for brain tumor assessment.

Early identification of septic shock in children with sepsis remains challenging, particularly in resource-limited and geographically disadvantaged settings. The predictive performance of C-reactive protein, procalcitonin, and blood lactate for septic shock was evaluated in a multicenter retrospective study involving 245 children aged <10 years who were diagnosed with sepsis at six provincial hospitals in northern mountainous Vietnam between 2022 and 2025. Patients were classified into septic shock (n = 82) and non-septic shock (n = 163) groups. Clinical characteristics and C-reactive protein, procalcitonin, and blood lactate concentrations measured within 24 hours of hospital admission were evaluated. Biomarker discrimination was assessed using receiver operating characteristic curve analysis. The median age of the study population was 35 months (interquartile range, 18.0–54.0 months), and septic shock was identified in 82 children (33.5%). Fever >38.5 °C (adjusted odds ratio, 3.91; 95% confidence interval, 1.62–9.43), cardiovascular dysfunction (adjusted odds ratio, 10.94; 95% confidence interval, 5.19–23.08), and neurological dysfunction (adjusted odds ratio, 6.07; 95% confidence interval, 2.80–13.16) were independently associated with septic shock. Among the three biomarkers evaluated, blood lactate showed the greatest discriminatory ability, with an area under the receiver operating characteristic curve (AUC) of 0.713 (95% confidence interval, 0.640–0.785) and an optimal cutoff of 3.93 mmol/L. Procalcitonin showed lower discriminatory performance (AUC, 0.652; 95% confidence interval, 0.577–0.727), whereas C-reactive protein did not discriminate between patients with and without septic shock (AUC, 0.485; p = 0.711). These findings suggest that, among the biomarkers evaluated, blood lactate provides the greatest discriminatory value for septic shock in children with sepsis. Procalcitonin may provide complementary information, whereas C-reactive protein appears to have limited discriminatory utility for this purpose. Blood lactate, potentially supplemented by procalcitonin and readily assessed clinical indicators, may therefore contribute to early risk stratification for septic shock in pediatric sepsis, particularly in resource-limited healthcare settings.

Maternal health forms a pivotal public health concern since poor pregnancy outcomes often arise from delayed detection of physiological abnormalities. Recent advances in Internet of Things (IoT)-based maternal health monitoring devices have enabled automated risk assessment of real-time clinical data. This study developed a Machine Learning (ML) framework to categorize maternal health risk into High, Medium, and Low Levels using a dataset of 1,014 records collected from maternal health centres. Six physiological indices, including body temperature, heart rate, systolic, and diastolic blood pressure, blood glucose level, and age were analyzed via five-fold cross validation. Logistic Regression (LR), Decision Tree (DT), and Random Forest (RF) models were trained and evaluated. RF model achieved the best performance of 0.88 accuracy and F1-score of 0.88. Taken together, recall of 0.91 for high-risk cases, area under the curve (AUC) of 0.973, log loss of 0.449, mean squared error (MSE) of 0.228, root mean squared error (RMSE) of 0.478, and mean absolute error (MAE) of 0.157 demonstrated reliable prenatal risk prediction despite limited resources in healthcare settings.

Traditional cross-sectional methods could not adequately capture time-to-event dynamics among HIV patients on antiretroviral therapy (ART). Survival analysis provides a more appropriate framework for examining predictors of clinical outcomes. This study applied a multivariable Cox proportional hazards model to examine socio-demographic and clinical factors associated with time to treatment interruption or death among 2,887 HIV patients on ART at Specialist Hospital Yola, Adamawa State, Nigeria. The outcome was time to treatment interruption or death, with Current ART Status serving as the failure indicator (1 = interruption in treatment (IIT) or dead; 0 = censored). Independent variables were age group, sex, marital status, and viral load status (suppressed <1000 copies/ml versus unsuppressed ≥1000 copies/ml). Kaplan-Meier curves, Log-rank tests, and Cox regression models were employed in the investigation. The proportional hazards assumption was assessed using log-minus-log plots, Schoenfeld residuals, and the global Schoenfeld test. Most participants were females (70.1%) and had suppressed viral load (95%). Unsuppressed viral load was significantly associated with treatment interruption or death in both univariate (hazard ratio (HR) = 1.98; 95% confidence interval (CI): 1.44–2.73; p < 0.001) and multivariate analyses (adjusted HR = 1.96; 95% CI: 1.42–2.70; p < 0.001). Age group, sex, and marital status were not significant predictors. The proportional hazards assumption was satisfied (global Schoenfeld test p = 0.669). Unsuppressed viral load was therefore the only independent predictor of treatment interruption or death. Strengthening viral load monitoring and adherence support should be prioritized to improve treatment outcomes.

Malignant mesothelioma remains a diagnostic challenge due to the phenotypic overlap with benign pleural diseases and the reliance on invasive procedures for definitive confirmation. To address these limitations, a leakage-aware, explainable machine learning framework was developed and applied to a publicly available mesothelioma dataset comprising 324 cases (96 mesothelioma, 228 symptomatic non-mesothelioma). Variables prone to target leakage or unavailable at the point of diagnosis—such as diagnosis method, cytology results, mesothelioma subtype, and survival status—were systematically excluded. The remaining features were stratified into initial clinical presentation, post-imaging, and post-pleural-fluid analysis stages prior to model development. The dataset was partitioned into a development cohort (n = 226) and an independent hold-out cohort (n = 98). Multiple classifiers, including logistic regression, support vector machine, k-nearest neighbors, and light gradient boosting machine, were optimized via grid search and evaluated using repeated stratified 5-fold cross-validation. The diagnosis method was identified as a perfect inverse surrogate of the target variable and consequently removed. The light gradient boosting machine exhibited superior performance, achieving the highest average precision (0.543) and Matthews correlation coefficient (0.306) during cross-validation. On the unseen hold-out cohort, light gradient boosting machine yielded an area under the receiver operating characteristic curve of 0.660, average precision of 0.483, balanced accuracy of 0.615, and Matthews correlation coefficient of 0.233. At the conventional 0.50 threshold, sensitivity was 0.448, specificity 0.783, and negative predictive value 0.771; lowering the threshold to 0.30 increased sensitivity to 0.690 at the expense of specificity reduction to 0.493. SHapley Additive exPlanations (SHAP) identified age, platelet count, lung side, white blood cell count, and duration of asbestos exposure as the most influential predictors. This leakage-aware, explainable light gradient boosting machine model delivers clinically interpretable diagnostic predictions while mitigating target leakage, demonstrating moderate discrimination and potential utility in real-world clinical settings. These findings warrant further external validation and prospective evaluation to confirm generalizability and clinical impact.

Metformin remains the cornerstone of pharmacological management for Type 2 diabetes mellitus (T2DM); however, its long-term use has been associated with impaired vitamin B12 absorption and macrocytosis. The prevalence and independent determinants of macrocytosis in metformin-treated populations remain insufficiently characterized. A cross-sectional observational study was conducted at Saidu Teaching Hospital, Swat, between July 2024 and August 2025. A total of 236 adults with T2DM receiving metformin therapy for at least six months were enrolled. Macrocytosis was defined as a mean corpuscular volume (MCV) exceeding 100 fL. Demographic characteristics, clinical parameters, and concomitant medication use were systematically recorded. Univariate analyses were initially performed, followed by multivariate logistic regression to identify independent predictors of macrocytosis. The overall prevalence of macrocytosis was 16.1% (95% confidence interval (CI): 11.7–21.4%). Multivariate analysis demonstrated that metformin therapy duration >4 years (odds ratio (OR): 3.42, p = 0.002), daily metformin dose ≥1500 mg (OR: 2.89, p = 0.006), concomitant proton pump inhibitor (PPI) use (OR: 4.15, p < 0.001), and age ≥60 years (OR: 2.26, p = 0.030) were independently associated with macrocytosis, with concurrent PPI use emerging as the strongest predictor. These findings indicate that macrocytosis is a relatively common hematologic abnormality in metformin-treated adults with T2DM and is strongly influenced by treatment duration, dosage intensity, age, and concurrent PPI therapy. Risk-stratified surveillance strategies incorporating periodic assessment of MCV and serum vitamin B12 levels may therefore be warranted, particularly in high-risk patients, to enhance patient safety and optimize the long-term clinical management of T2DM.

Microplastics, commonly defined as plastic particles smaller than 5 mm, have emerged as pervasive contaminants across natural and anthropogenic systems, constituting a complex global stressor with environmental, economic, and public health implications. Since the term microplastic was first introduced in 2004, an expanding body of research has revealed the extensive diversity and abundance of these particles, which originate from both the fragmentation of larger plastic debris (secondary microplastics) and the intentional production of microscopic polymers (primary microplastics) for use in cosmetics, industrial abrasives, and synthetic textiles. Despite substantial scientific attention, the absence of a universally accepted classification framework–particularly with respect to size ranges, polymer composition, and source attribution–continues to hinder harmonized monitoring and regulatory action. Microplastics have been detected in marine and freshwater environments, terrestrial soils, atmospheric fallout, and remote regions, demonstrating their capacity for long-range transport through hydrological, atmospheric, and biogeochemical processes. Ecologically, exposure has been shown to impair feeding behavior, induce physical obstruction, and compromise reproductive success across multiple trophic levels, from planktonic organisms to higher vertebrates. Chemically, microplastics function as dynamic carriers for persistent organic pollutants, heavy metals, and microbial assemblages. Human exposure has been increasingly documented through dietary intake, drinking water consumption, and inhalation of airborne particles. Effective mitigation of microplastic pollution will require coordinated international policy frameworks, advances in materials innovation and waste management, standardized analytical methodologies, and sustained public engagement to address both sources and impacts of microplastic contamination.

Drug-therapy problems (DTPs) are a major concern in cardiovascular disease (CVD) management, particularly among older adults exposed to polypharmacy, drug-drug interactions (DDIs), non-adherence, unnecessary drug therapy, and adverse drug reactions (ADRs). This prospective observational study, conducted in the cardiology unit of Saidu Group of Teaching Hospital (SGTH), Swat, Pakistan, evaluated 350 inpatients admitted from January to March 2022. Data were analyzed using SPSS v26 and GraphPad Prism v5.01, employing chi-square tests, t-tests, and binary logistic regression (p < 0.05). A total of 323 patients (92.29%) experienced at least one DTP, accounting for 1,252 events. DDIs were the most common DTP, followed by unnecessary drug therapy and ADRs. Age was a significant predictor, with the highest odds of DTPs observed in patients aged 61–70 years; a slight, non-significant increase was noted among females and those with polypharmacy (>5 medications). DTP frequency correlated positively with age and the number of prescribed medications, particularly among individuals aged 31–70 years. The findings indicate a high burden of preventable DTPs in CVD management, dominated by DDIs and unnecessary drug therapy. The incorporation of multidisciplinary medication-review teams, strengthened clinical decision support systems (CDSS), and routine prescription audits is recommended to mitigate DTPs and enhance the safety and precision of cardiovascular pharmacotherapy.

Diabetic foot infections (DFIs) are a major cause of morbidity and lower-limb amputations among individuals with diabetes mellitus. Inappropriate empirical antibiotic use contributes to treatment failure and elevated amputation risk. This observational study, conducted across six hospitals in Khyber Pakhtunkhwa (KP), Pakistan, involved 341 patients with clinically diagnosed DFIs. The objectives were to evaluate antibiotic efficacy, treatment outcomes, and risk factors for amputation, and to develop a visual risk stratification model correlating antibiotic response with amputation risk. The cohort exhibited a significant male predominance (64.5%, p = 0.003), with the highest prevalence among patients aged 41–50 years (36.7%). Most participants were insulin-independent (92.7%, p < 0.0001). Infection severity was mild in 28.7%, moderate in 47.8%, and severe in 23.5% of cases. Clinical outcomes included complete recovery (39.3%), improvement (31.7%), progression (19.9%), and amputation (9.1%). High-efficacy antibiotics included Levofloxacin (Levaquin, 100%), Colistin (100%), and Linezolid (Zyvox, 86.6%), whereas Ceftriaxone (Cefzone, 33.3%), Ampicillin/Sulbactam (Penro, 38.3%), and Clindamycin (Cleocin HCl, 26.6%) demonstrated limited therapeutic benefit. The visual stratification model showed that exposure to low-efficacy antibiotics significantly increased amputation risk. Logistic regression identified severe baseline infection (odds ratio (OR) ≈3.2), poor glycemic control (OR ≈ 1.9), and treatment with low-efficacy antibiotics (OR ≈ 2.8) as independent predictors of unfavorable outcomes. This study highlights the need for region-specific antibiotic stewardship, continuous resistance surveillance, and evidence-based treatment protocols. The proposed visual model offers a practical framework for guiding empirical therapy and reducing amputation rates in DFI management.