Browse Articles

Incidence and risk factors of malaria with hematological and immunological evaluation and integrable analysis of a fractional mathematical model

Simultaneous multi-controller fusion via genetic algorithm-optimized weighted summation for variable-speed wind turbine control

An optimized gradient boosting framework for IoT intrusion detection: a comprehensive evaluation on the CICIoT2023 dataset

Using causal machine learning and real world data to improve dose response decision making for secukinumab in psoriatic arthritis

Abstract Personalized treatment in psoriatic arthritis (PsA) remains challenging, particularly in guiding dose escalation decisions. We applied a causal machine learning framework to real-world data from the AQUILA study to evaluate the impact of secukinumab dose escalation (150 mg to 300 mg) on disease activity and health-related quality of life (HR-QoL). Using double machine learning, we estimated both average and patient-level conditional treatment effects (CATEs) based on 42 baseline variables, including demographics, laboratory values, disease activity, HR-QoL, comorbidities, and prior treatments. 41.4% of patients receiving the higher dose showed greater improvement in Psoriatic Arthritis Impact of Disease (PsAID) scores compared to the lower dose (mean reduction: 1.81 vs. 1.44). Subgroup analysis revealed a 28% HR-QoL gain in patients with elevated body mass index (BMI) or C-reactive protein (CRP). The model predicted that approximately 75% of patients would benefit from dose escalation. These findings demonstrate the utility and scalability of causal machine learning for quantifying individualized treatment effects and guiding personalized treatment decisions in PsA. The approach is transferable to other chronic conditions, supporting more precise, data-driven care in real-world clinical settings.

Multimodal deep feature fusion with transformer for brain tumor classification from magnetic resonance imaging

Abstract Brain tumors (BTs) arise due to abnormal cell growth, which has a high mortality rate globally. Millions of lives can be saved through the timely identification of BT. Precise identification and segmentation of BTs are essential to enhance the precision of analysis and the efficiency of therapeutic strategies. Magnetic resonance imaging (MRI) is a broadly utilized analytical tool. Furthermore, deep learning (DL) has recently shown efficiency in addressing several computer vision tasks. Several DL-driven methods are implemented for BT segmentation and attained impressive outcomes. This study presents a Multimodal Deep Feature Fusion Framework for Automated Brain Tumor Detection and Segmentation (MDFF-ABTDS) model. This objective is to develop a multimodal DL that integrates feature fusion and transformer networks for the precise detection and segmentation of BTs from medical images. Initially, image pre-processing is performed using Contrast Limited Adaptive Histogram Equalization (CLAHE) and image normalization. Feature extraction is carried out through fusion models such as CapsNet, ResNet-50, and AlexNet. These extracted features are then passed to a bi-directional convolutional long short-term memory combined with transformer (TBConvL-Net) models to classify tumors and non-tumors effectively. Finally, the tumor is classified to identify its location using the nnUNet model for a precise segmentation process. A series of experimental analyses of the MDFF-ABTDS method portrayed a superior accuracy value of 98.91% over existing models under the BT MRI dataset.

Impact of black garlic and its encapsulated form on the physicochemical properties, antioxidant potential, and aroma-active profile of wheat bread

Optimization of polyhydroxyalkanoate biopolymer production from lignocellulosic wood waste using statistical experimental designs

Rapid detection of airborne fungal contamination using a molecularly imprinted polymer approach for ergosterol

Base editing restores CDKL5 expression and rescues neuronal deficits in a patient-derived model of CDKL5 deficiency disorder

Abstract Cyclin-dependent kinase like 5 (CDKL5) deficiency disorder (CDD) is a rare monogenic neurodevelopmental disorder caused by pathogenic mutations in the CDKL5 gene, with approximately 50% of reported variants being point mutations. Base editing presents a promising therapeutic strategy to correct such mutations, restore endogenous CDKL5 expression, and pave the way for novel treatments for CDD. To assess the therapeutic potential of base editing for CDD, we applied adenine base editing (ABE) to correct a CDKL5 -R550* (c.1648 C > T) mutation in induced pluripotent stem cells (iPSCs) derived from a CDD patient. Isogenic control, CDKL5 -R550* mutant, and ABE-corrected iPSCs were differentiated into neurons and the restoration of CDKL5-related and functional recovery were assessed. In this study, we demonstrated that ABE successfully restored CDKL5 protein levels and CDKL5-dependent signalling pathways in edited iPSC-differentiated neurons to levels comparable to the isogenic control. Morphological deficits, and genes expression were normalized in the ABE-corrected neurons. This study provides evidence that ABE can precisely correct pathogenic mutation and functionally rescue some CDD-associated neuronal phenotypes in patient-derived cells, supporting its potential as a valuable gene therapy for CDD. Moreover, these findings underscore the broader applicability of base editing for treating other monogenic neurodevelopmental disorders caused by point mutations.

The role of outpatients’ medical history on current herbal medicines use: a cross-sectional multicenter study

A data-parsimonious model for long-term risk assessments of West Nile virus spillover

A novel NFR-based conceptual quality framework for modern API industry

Hybrid feature selection for IoMT based intrusion detection system for integrating mutual information filtering with deep learning based accelerated metaheuristic optimization

Val109 and Ile170 contribute to channel function in Guillardia theta-derived anion channelrhodopsins

Tear fluid as a novel specimen for detection of alpha-synuclein seeding activity in Parkinson’s disease

Similarity study on lateral impact model of CFST column under high temperature

Abstract This paper develops a finite element model of circular concrete-filled steel tube (CFST) columns subjected to combined high temperature and lateral impact using ABAQUS through sequential thermal-stress coupling analysis, static analysis, and explicit dynamic methods, and validates it with existing experimental data from fire resistance tests and impact tests. Subsequently, based on the similarity theory of temperature fields, the heating curves for the reduced-scale circular CFST column models were designed. Meanwhile, using the dimensional system consisting of impact velocity, dynamic stress, and impact mass ( V – σ d – G ), an impact similarity criterion was established, and the scaling factors for key physical quantities that are closely related to the impact response were derived. After that, numerical simulations of lateral impact on the reduced-scale models were conducted at different temperatures to design reduced-scale models whose thermal–mechanical coupling response characteristics closely approximate those of the prototype structure under strain rates below the transition strain rate. Furthermore, based on the simulation results, the response differences between the reduced-scale models and the prototype, as well as the reasons for these differences, were analyzed in detail. Finally, the velocity scaling factor was derived using the strain rate-dependent constitutive equations of steel and concrete to modify the reduced-scale models, which effectively reduced the error of the reduced-scale model in predicting the prototype response.

The role of emotions, stress, learning stage, and cognitive load on learning in emergency events: a mixed methods study

Chitosan-EDTA-cellulose functionalized with β-cyclodextrin as a pH-sensitive bio-based nanocarrier for curcumin drug delivery

Tripleknock: predicting lethal effect of three-gene knockout in bacteria by deep learning

Benchmarking MedViT and hybrid CNN–ViT architectures for multi-label thoracic disease classification

Abstract Computer-aided diagnosis relies heavily on the automatic classification of thoracic diseases from chest X-ray (CXR) images, yet this task remains challenging due to class imbalance, overlapping radiological features, and high inter-class similarity. In this study, two architectures MedViT and Hybrid CNN–ViT are adapted and evaluated, which are a scalable Vision Transformer (ViT)-based architecture designed for multi-label thoracic disease classification. MedViT is enhanced with transfer learning, domain-specific augmentations, and self-attention mechanisms to capture subtle pathological patterns across diverse conditions. The Hybrid CNN–ViT is the combination of strength of CNN and ViT which is admirable in capturing local patterns. Both models are trained and validated on two benchmark datasets, NIH ChestX-ray14 and CheXpert, and compared against state-of-the-art baselines. On the NIH ChestX-ray14 dataset, MedViT showed strong performance with 93.34% accuracy and a macro AUROC of 94.17%, while the Hybrid CNN–ViT model reached 85.81% accuracy and 72.28% macro AUROC. On the CheXpert dataset, MedViT achieved 79.22% accuracy and a macro AUROC of 75.11%, whereas Hybrid CNN–ViT achieved 76.15% accuracy and 71.68% macro AUROC. These results show that MedViT performs well and generalizes effectively across different datasets. Per-label analysis demonstrated robust precision and recall even for under-represented conditions such as fibrosis and hernia, where existing models typically show significant performance drops. Unlike earlier methods that often struggle with generalization, MedViT maintains a balanced trade-off between sensitivity and specificity across all categories. These findings highlight the effectiveness of Transformer-based feature encoding in capturing subtle spatial correlations in medical imaging, while also setting new benchmarks for automated thoracic disease classification. The MedViT model outperformed the state-of-the-art methods and shows strong potential to support radiologists in decision-making and improve diagnostic workflows in clinical practice.