Ren Fail. 2025 Dec;47(1):2540563. doi: 10.1080/0886022X.2025.2540563. Epub 2025 Aug 7.

ABSTRACT

Medications contribute to about a quarter of acute kidney injury (AKI) cases among patients in hospitals. The impact of AKI is substantial on both families and society, and it has become a worldwide public health concern. Recently, a new framework for drug-induced acute kidney injury (DI-AKI) classification has been proposed. According to this new framework, drugs are divided into four categories. Thus, we explain the mechanism thoroughly and give examples of drugs or drug categories linked to the classes in the new framework. Furthermore, a patient's condition may dynamically shift between categories. At the same time, we also took into account some susceptibility factors. These susceptibility factors may drive inter-class variation. The new classification system may shed new light on the mechanism of DI-AKI for clinicians and researchers.

PMID:40775804 | DOI:10.1080/0886022X.2025.2540563

Orphanet J Rare Dis. 2025 Aug 7;20(1):406. doi: 10.1186/s13023-025-03934-7.

ABSTRACT

OBJECTIVE: This study aims to evaluate the adverse drug reactions associated with imiglucerase in the treatment of Gaucher disease by analyzing data from the FDA Adverse Event Reporting System (FAERS) database.

METHODS: A comprehensive analysis was conducted on 166,800,135 adverse event reports from the FAERS database, covering the period from the first quarter of 2004 to the fourth quarter of 2023. The data were processed using R software and analyzed using multiple disproportionality methods, including Reporting Odds Ratio (ROR), Proportional Reporting Ratio (PRR), Bayesian Confidence Propagation Neural Network (BCPNN), and Multi-Item Gamma Poisson Shrinker (MGPS). These methodologies were applied to identify significant adverse reaction signals across various System Organ Classes (SOCs) and Preferred Terms (PTs).

RESULTS: The analysis revealed significant adverse reaction signals in multiple SOCs, including general disorders and administration site conditions, injury, poisoning and procedural complications, infections and infestations, and nervous system disorders. Notably, general disorders and injury-related conditions had the highest number of reports. At the PT level, the term "Gaucher disease" yielded the highest statistical signal. This was identified as a critical reporting artifact, likely representing perceived treatment failure or disease progression, rather than a true adverse reaction. After accounting for this artifact, other significant adverse event signals included increased chitotriosidase, elevated acid phosphatase, and bone infarction, with musculoskeletal and connective tissue disorders being a key area of concern. A comparative analysis against other Gaucher therapies suggests this strong skeletal signal likely reflects confounding by indication rather than a drug-specific risk.

CONCLUSION: The findings underscore the importance of ongoing pharmacovigilance to monitor the safety of imiglucerase, especially among vulnerable populations such as pregnant women, long-term users, and those with comorbid hepatobiliary or skeletal conditions.

PMID:40775785 | DOI:10.1186/s13023-025-03934-7

BMC Prim Care. 2025 Aug 7;26(1):248. doi: 10.1186/s12875-025-02926-7.

ABSTRACT

BACKGROUND: Community pharmacies (CPs) are key healthcare providers, playing a significant role in optimizing drug therapy and preventing drug-related problems (DRPs). This study aims to assess the prevalence, characteristics, and related factors of DRPs in Turkish patients in the community pharmacy setting.

METHODS: A cross-sectional, prospective study was conducted between December 2023 and December 2024 in a community pharmacy. A total of 100 patients were included after excluding those with incomplete data. DRPs were evaluated using the PCNE V9.1 classification system, while Medication Adherence Report Scale (MARS) and Medication Regimen Complexity Index (MRCI) were used to assess adherence and regimen complexity.

RESULTS: A total of 162 DRPs were identified, with an average of 1.6 DRPs per patient. DRPs were significantly associated with factors such as higher body mass index (p = 0.005), polypharmacy (p < 0.001), use of antidiabetic (p < 0.001) and antihypertensive medications (p = 0.005), and a higher number of comorbidities (p = 0.005). No significant relationship was observed between medication adherence and DRPs (p > 0.05).

DISCUSSION: This study is among the first in Türkiye to evaluate DRPs in chronic disease management within a community pharmacy setting. The findings highlight the importance of clinical pharmacists in identifying and managing DRPs and suggest the need for integrated interventions in healthcare teams to improve patient outcomes and medication safety.

PMID:40775745 | DOI:10.1186/s12875-025-02926-7

BMC Gastroenterol. 2025 Aug 7;25(1):560. doi: 10.1186/s12876-025-04154-w.

ABSTRACT

BACKGROUND: The incidence of pediatric inflammatory bowel disease (IBD) significantly increased recently. Infliximab (IFX) and adalimumab (ADA), both TNF-α inhibitors, are the only FDA-approved treatments for pediatric IBD. Due to the unique physiological and developmental characteristics of children, postmarketing pharmacovigilance requires ongoing attention. We aimed to evaluate the safety of IFX and ADA in pediatric IBD using FAERS database data from Q1 2004 to Q1 2024.

METHODS: Reporting Odds Ratio (ROR) and Proportional Reporting Ratio (PRR) algorithms were used to identify drug-related adverse events (AEs).

RESULTS: In total, we retrieved 10,905 IFX-related reports and 5,446 ADA-related reports in pediatric IBD. Common AEs associated with IFX were infusion reactions; for ADA, they were injection site reactions. While most AEs align with approved labeling, continued vigilant monitoring appears important for specific postmarketing AEs observed with IFX, including suicide attempts, weight increased, and psoriasis. The median onset (TTO) for IFX-related AEs was 579 days (interquartile range [IQR]: 159.25-1357 days), occurring mostly after 360 days. For ADA, TTO was 79 days (IQR: 21.75-295 days), with most within 90 days of treatment initiation.

CONCLUSION: Our study revealed that although most AEs matched labeled information, rigorous post-marketing monitoring of severe AEs remains important for IFX and ADA in pediatric IBD, with additional confirmatory research warranted.

PMID:40775680 | DOI:10.1186/s12876-025-04154-w

Sci Rep. 2025 Aug 7;15(1):28962. doi: 10.1038/s41598-025-14963-4.

ABSTRACT

Skin cancer, especially melanoma, has become one of the most widespread and deadly diseases today. The chances of successful treatment are greatly reduced if the melanoma is not treated in its early stages because it could spread aggressively. Hence, the diagnosis of skin cancer is very challenging as skin lesions are highly subjective to analyze and that type of expertise is exceedingly specialized. While there is an increase in the prevalence of skin cancer across the globe, there is an increase need of automated diagnostic systems that could aid medical personnel in making appropriate decisions within the requisite timelines. This study proposes construction of a deep learning model built on the MobileNetV2 architecture that has been memetic optimized for hyperparameter tuning. The memetic algorithm employs both global and localized search techniques to fine-tune the model parameters that include learning rate, batch size, and number of epochs to boost the efficacy of the model. This makes it possible for the proposed model to achieve high performance while remaining economical on resources. This makes the model suitable for real world clinical settings. The model achieved exceptional results, with 98.48% accuracy, 97.67% precision, and 100% recall, highlighting its strong ability to detect malignant lesions. The ROC AUC score of 99.79% further demonstrates its outstanding capability to differentiate between benign and malignant lesions. Notably, visualizations such as the Grad-CAM heatmap and Superimposed Image were crucial in providing interpretability to the model's decision-making process. The Grad-CAM heatmap highlighted the regions of interest in the lesions, showing how the model focused on key structural features. The Superimposed Image combined these heatmaps with the original lesion images, making it clear which parts of the lesions influenced the model's classification. These results underscore the potential of deep learning models, optimized with the memetic algorithm, to significantly improve skin cancer detection. By offering both high accuracy and interpretability, this model presents a valuable tool for dermatologists, facilitating faster and more reliable early diagnosis and ultimately improving patient outcomes.

PMID:40775513 | DOI:10.1038/s41598-025-14963-4

Discov Oncol. 2025 Aug 7;16(1):1489. doi: 10.1007/s12672-025-03324-2.

ABSTRACT

OBJECTIVES: This study charted how investigations of tumour-microenvironment (TME) dynamics have shaped global thinking on drug resistance in breast cancer over the past three decades.

METHODS: Web of Science Core Collection records (1995–2024) were harvested on 15 May 2025 with a three-block Boolean string integrating disease, microenvironmental, and resistance terms. After duplicate removal, document-type filtering, language restriction, and natural-language adjudication, 1 303 original articles and reviews remained. Bibliometrix (R 4.3.2) generated annual output, citation kinetics, and growth rates; VOSviewer (fractional counting, resolution = 1.0) mapped co-authorship, co-citation, and keyword networks.

RESULTS: Publication volume expanded at a compound annual rate of 18.7%, progressing through formative (1995–2004), consolidation (2005–2012), and expansionary (2013–2024) epochs. Keyword drift traced a pivot from endocrine-centric lexicons (“tamoxifen”, “estrogen receptor”) to TME-immune discourse (“extracellular vesicles”, “tumour-associated macrophages”, “nanoparticles”); “microenvironment”, “hypoxia”, and “multidrug resistance” emerged as high-betweenness semantic bridges. The United States–China dyad accounted for 56.1% of output and anchored 24.4% of internationally co-authored papers, funnelling methodological innovation into an increasingly multipolar network, here defined as a collaboration graph containing at least four countries that each contribute ≥ 5% of total node-level betweenness centrality. Institutional overlays revealed late-decade ascendancy of East-Asian medical universities, while legacy North-American and European centres maintained brokerage dominance.

CONCLUSION: Bibliometric cartography documents a decisive ecological re-framing of breast-cancer drug-resistance research, with immune-stromal crosstalk supplanting receptor-centric models. Cross-border, multi-omics consortia that fuse East-Asian clinical scale with Western technological depth appear best poised to convert TME insights into resistance-reversing interventions.

PMID:40772981 | PMC:PMC12332156 | DOI:10.1007/s12672-025-03324-2

Sci Rep. 2025 Aug 7;15(1):28895. doi: 10.1038/s41598-025-13636-6.

ABSTRACT

In the pathological diagnosis of colorectal cancer, the precise segmentation of glandular and cellular contours serves as the fundamental basis for achieving accurate clinical diagnosis. However, this task presents significant challenges due to complex phenomena such as nuclear staining heterogeneity, variations in nuclear size, boundary overlap, and nuclear clustering. With the continuous advancement of deep learning techniques-particularly encoder-decoder architectures-and the emergence of various high-performance functional modules, multi module collaborative fusion has become an effective approach to enhance segmentation performance. To this end, this study proposes the RPAU-Net++ model, which integrates the ResNet-50 encoder (R), the Joint Pyramid Fusion Module (P), and the Convolutional Block Attention Module (A) into the UNet++ framework, forming a multi-module-enhanced segmentation architecture. Specifically, ResNet-50 mitigates gradient vanishing and degradation issues in deep network training through residual skip connections, thereby improving model convergence stability and feature representation depth. JPFM achieves progressive fusion of cross-layer features via a multi-scale feature pyramid, enhancing the encoding capability for complex tissue structures and fine boundary information. CBAM employs adaptive weight allocation in both spatial and channel dimensions to focus on target region features while effectively suppressing irrelevant background noise, thereby improving feature discriminability. Comparative experiments on the GlaS and CoNIC colorectal cancer pathology datasets, as well as the more challenging PanNuke dataset, demonstrate that RPAU-Net++ significantly outperforms mainstream models in key segmentation metrics such as IoU and Dice, providing a more accurate solution for pathological image segmentation in colorectal cancer.

PMID:40775016 | DOI:10.1038/s41598-025-13636-6

Sci Rep. 2025 Aug 7;15(1):28904. doi: 10.1038/s41598-025-13680-2.

ABSTRACT

Although Transformers perform well in time series prediction, they struggle when dealing with real-world data where the joint distribution changes over time. Previous studies have focused on reducing the non-stationarity of sequences through smoothing, but this approach strips the sequences of their inherent non-stationarity, which may lack predictive guidance for sudden events in the real world. To address the contradiction between sequence predictability and model capability, this paper proposes an efficient model design for multivariate non-stationary time series based on Transformers. This design is based on two core components: (1)Low-cost non-stationary attention mechanism, which restores intrinsic non-stationary information to time-dependent relationships at a lower computational cost by approximating the distinguishable attention learned in the original sequence.; (2) dual-data-stream Progressively learning, which designs an auxiliary output stream to improve information aggregation mechanisms, enabling the model to learn residuals of supervised signals layer by layer.The proposed model outperforms the mainstream Tranformer with an average improvement of 5.3% on multiple datasets, which provides theoretical support for the analysis of non-stationary engineering data.

PMID:40775010 | DOI:10.1038/s41598-025-13680-2

Sci Data. 2025 Aug 7;12(1):1383. doi: 10.1038/s41597-025-05692-4.

ABSTRACT

This dataset presents multiaxial vibration signals collected from a multirotor unmanned aerial vehicle (UAV) operating in hover mode for the purpose of blade fault diagnosis. Vibration measurements were recorded at the geometric center of the UAV, where the centerlines of the four rotor arms intersect, using a triaxial accelerometer. The dataset captures variations across the X, Y, and Z axes under different blade fault conditions, including healthy, minor imbalance, severe imbalance, and screw loosening scenarios. Each flight scenario was repeated under controlled conditions to ensure consistency and high-quality labeling. The resulting soft-labeled dataset includes time-domain signals from numerous test flights and has been used in multiple prior studies involving classical and deep learning-based fault classification techniques. This curated data collection provides a valuable resource for researchers in UAV health monitoring, vibration analysis, and machine learning-based fault diagnosis. The dataset is particularly useful for the development and benchmarking of signal processing pipelines and classification models aimed at identifying blade-level faults in multirotor UAV systems.

PMID:40774972 | DOI:10.1038/s41597-025-05692-4

J Nucl Cardiol. 2025 Aug 5:102449. doi: 10.1016/j.nuclcard.2025.102449. Online ahead of print.

ABSTRACT

BACKGROUND: The REgistry of Flow and Perfusion Imaging for Artificial Intelligence with PET (REFINE PET) was established to collect multicenter PET and associated computed tomography (CT) images, together with clinical data and outcomes, into a comprehensive research resource. REFINE PET will enable validation and development of both standard and novel cardiac PET/CT processing methods.

METHODS: REFINE PET is a multicenter, international registry that contains both clinical and imaging data. The PET scans were processed using QPET software (Cedars-Sinai Medical Center, Los Angeles, CA), while the CT scans were processed using deep learning (DL) to detect coronary artery calcium (CAC). Patients were followed up for the occurrence of major adverse cardiovascular events (MACE), which include death, myocardial infarction, unstable angina, and late revascularization (>90 days from PET).

RESULTS: The REFINE PET registry currently contains data for 35,588 patients from 14 sites, with additional patient data and sites anticipated. Comprehensive clinical data (including demographics, medical history, and stress test results) were integrated with more than 2200 imaging variables across 42 categories. The registry is poised to address a broad range of clinical questions, supported by correlating invasive angiography (within 6 months of MPI) in 5972 patients and a total of 9252 major adverse cardiovascular events during a median follow-up of 4.2 years.

CONCLUSION: The REFINE PET registry leverages the integration of clinical, multimodality imaging, and novel quantitative and AI tools to advance the role of PET/CT MPI in diagnosis and risk stratification.

PMID:40774620 | DOI:10.1016/j.nuclcard.2025.102449

Int J Cardiol. 2025 Aug 5:133649. doi: 10.1016/j.ijcard.2025.133649. Online ahead of print.

ABSTRACT

Early identification of patients with acute myocardial infarction (AMI) at high risk of in-hospital mortality is crucial for optimizing treatment strategies. However, the urgent nature of these clinical scenarios often limits the ability to gather the comprehensive data necessary for accurate risk assessment. Missing data presents a substantial challenge to timely and effective risk evaluation METHODS: We developed MortiGen, an end-to-end model designed to address the dual challenges of missing data imputation and mortality risk prediction in patients with AMI. The model was trained using data from 9163 admissions in the eICU collaborative research database and externally tested on 12,166 admissions from the medical information Mart for intensive care and 2142 admissions from the Chongqing University central hospital. The performance of the MortiGen was compared with other ten models using multiple evaluation metrics RESULTS: MortiGen demonstrated robust performance in predicting in-hospital mortality using data available at 3 h, 12 h, 24 h, and throughout the entire hospital stay (ranging from 47.2 % to 89.5 % of the data available), with receiver operating characteristic curve ranging from 0.794 to 0.855. MortiGen outperformed other ten models. Notably, when relying solely on data available within the first 3 h of admission, MortiGen achieving performance better than some comparison models, which used data from the entire hospitalization CONCLUSIONS: MortiGen effectively predicts in-hospital mortality among patients with AMI, even in the early stages of hospital admission, overcoming challenges related to limited data availability due to time constraints and variability in laboratory testing conditions.

PMID:40774461 | DOI:10.1016/j.ijcard.2025.133649

J Orthop Surg Res. 2025 Aug 7;20(1):742. doi: 10.1186/s13018-025-06171-7.

ABSTRACT

The limited understanding of the prognostic implications of immune checkpoint molecules in osteosarcoma (OS) poses significant challenges for improving patient outcomes. There is a gap in the identification of reliable biomarkers that can predict treatment response and prognosis in OS patients. This study focused on investigating the prognostic value of immune checkpoints, specifically BTN3A1, SIRPA, and TDO2, using data from the TARGET database and clinical follow-up data from our hospitals. By conducting univariate Cox regression and least absolute shrinkage and selection operator (LASSO) analyses, we identified these immune checkpoints as significant prognostic indicators. A three-immune-checkpoint genetic prognostic risk model was developed, which demonstrated different prognostic implications across different clinical subgroups. Drug sensitivity analysis revealed that BTN3A1, SIRPA, and TDO2 were correlated with the efficacy of several antineoplastic agents, including hydroxyurea and docetaxel. Validation in our clinical cohort highlighted the significant prognostic value of SIRPA, suggesting its potential as a target for immunotherapy. These findings established a framework for using immune checkpoints as prognostic biomarkers, highlighting their important role in enhancing personalized treatment strategies for OS patients.

PMID:40775344 | DOI:10.1186/s13018-025-06171-7

J Transl Med. 2025 Aug 7;23(1):884. doi: 10.1186/s12967-025-06720-y.

ABSTRACT

Metformin, a widely prescribed treatment for type 2 diabetes mellitus (T2DM), demonstrates significant inter-individual variability in its therapeutic response. This variability is potentially driven by genetic differences in drug transporters. Among these transporters, the organic cation transporter 2 (OCT2) plays a critical role in the pharmacokinetics of metformin by mediating its uptake into renal epithelial cells for excretion. This review explores the potential impact of genetic variations in OCT2 gene (SLC22A2) on the pharmacokinetics and pharmacodynamics of metformin. These genetic variations can alter metformin accumulation in the kidneys, impacting its overall clearance and therapeutic effectiveness. Furthermore, the interactions of metformin with other drugs, especially in T2DM patients, can compromise its pharmacokinetics. Thus, it is important to consider the influence of genetic variability and potential drug interactions when prescribing metformin. Incorporating genetic testing into clinical decision-making could help optimize dosing strategies and improve treatment outcomes, particularly when managing patients with complex comorbid conditions.

PMID:40775340 | DOI:10.1186/s12967-025-06720-y

Drug Metab Dispos. 2025 Jul 7;53(8):100119. doi: 10.1016/j.dmd.2025.100119. Online ahead of print.

ABSTRACT

Thiopurine-induced leucopenia (TIL) affects more than 20% of Asians despite dose optimization via NUDT15 and TPMT genotyping. Elevated levels of DNA-thioguanine nucleotide (DNA-TG) have been implicated in the development of TIL. This study aimed to identify genetic polymorphisms influencing TIL through the DNA-TG metabolic pathway and construct a predictive model in Chinese inflammatory bowel disease patients. A prospective cohort of inflammatory bowel disease patients receiving thiopurines from December 2018 to December 2019 was analyzed. A total of 294 single-nucleotide polymorphisms across 29 genes were screened using the MassARRAY system. Candidate single-nucleotide polymorphisms associated with DNA-TG exposure or TIL (P < .1) were selected for validation. Independent risk factors were identified through multivariate logistic regression and incorporated into a predictive nomogram. Thiopurine metabolites, including DNA-TG and 6TGN, were quantified. DNA-TG, but not 6TGN, exposure was significantly associated with TIL (P = 8.3 × 10-7, P = .41). Sex, along with variants in NUDT15 (rs116855232 c.415C > T), TPMT (rs9465102), MOCOS (rs73430958), and RRM1 (rs1735053), were identified as independent predictors of TIL. The resulting nomogram demonstrated good discriminative performance (area under the curve = 0.72, 95% confidence interval: 0.65-0.78). Individuals stratified into low-, medium-, and high-risk groups based on total point thresholds (25.0 and 196.8), showed significant differences in TIL incidence in both NUDT15 variants and nonvariants (P = 1.8×10-5, P = .045). Our findings indicate that in addition to NUDT15, novel genetic variants in TPMT, MOCOS, and RRM1 are potential predictive markers of TIL. The new nomogram enables more accurate identification of individuals at high risk of TIL, allowing for the proactive adjustment of thiopurine therapy. SIGNIFICANCE STATEMENT: Compared with prior studies limited to NUDT15 and TPMT variants, it was the first pharmacogenomic study to investigate genetic polymorphisms affecting thiopurine-induced leucopenia (TIL) and DNA-thioguanine nucleotide metabolism, constructing a clinically actionable TIL prediction model. We identified novel associations of TPMT, MOCOS, and RRM1 variants with TIL risk, offering key insights for precision dosing in Asian populations. The validated nomogram integrates these biomarkers to stratify patients into distinct risk groups, facilitating tailored thiopurine therapy.

PMID:40774024 | DOI:10.1016/j.dmd.2025.100119

Pathology. 2025 Jul 10:S0031-3025(25)00219-3. doi: 10.1016/j.pathol.2025.05.006. Online ahead of print.

NO ABSTRACT

PMID:40774858 | DOI:10.1016/j.pathol.2025.05.006

Chronic Obstr Pulm Dis. 2025 Aug 1. doi: 10.15326/jcopdf.2025.0611. Online ahead of print.

NO ABSTRACT

PMID:40774292 | DOI:10.15326/jcopdf.2025.0611

Comp Biochem Physiol Part D Genomics Proteomics. 2025 Aug 6;56:101595. doi: 10.1016/j.cbd.2025.101595. Online ahead of print.

ABSTRACT

Soil salinization is an increasingly critical global issue for which fishery-based utilization has emerged as a promising mitigation strategy. Penaeus vannamei is an ideal species for aquaculture in saline-alkali waters; however, the differences in alkali tolerance among various families and their underlying mechanisms remain largely unexplored. In this study, alkali-tolerant families were identified through median lethal time (LT50) assays under high alkalinity and elevated pH. Comparative analyses with wild-type family revealed that alkali-tolerant families showed significant differences in energy metabolism and ion transport (Na+/K+-ATPase (NKA), carbonic anhydrase (CA), and cystic fibrosis transmembrane conductance regulator (CFTR)) Transcriptomic analysis showed that alkali-tolerant families had pathways related to cytoskeletal remodeling, including actin cytoskeleton organization (GO:0030029) and myosin complex (GO:0016459). KEGG analysis further revealed enrichment in cardiac muscle contraction (ko04260) and adrenergic signaling in cardiomyocytes (ko04261). We propose that CaCO3 precipitation reduces extracellular Ca2+ levels and disrupts the carbonate buffering system under high pH and alkalinity. In response, alkali-tolerant families mitigate pH and alkalinity stress by enhancing ion regulation and energy efficiency while simultaneously downregulating high-energy Ca2+ regulatory pathways and remodeling gill microstructures. Collectively, these findings provide novel insights into the alkali adaptation mechanisms of P. vannamei and support selective breeding strategies to improve stress resilience in saline-alkali aquaculture.

PMID:40774072 | DOI:10.1016/j.cbd.2025.101595

Sci Rep. 2025 Aug 7;15(1):28860. doi: 10.1038/s41598-025-14408-y.

ABSTRACT

Complex artificial intelligence models, like deep neural networks, have shown exceptional capabilities to detect early-stage polyps and tumors in the gastrointestinal tract. These technologies are already beginning to assist gastroenterologists in the endoscopy suite. To understand how these complex models work and their limitations, model explanations can be useful. Moreover, medical doctors specialized in gastroenterology can provide valuable feedback on the model explanations. This study explores three different explainable artificial intelligence methods for explaining a deep neural network detecting gastrointestinal abnormalities. The model explanations are presented to gastroenterologists. Furthermore, the clinical applicability of the explanation methods from the healthcare personnel's perspective is discussed. Our findings indicate that the explanation methods are not meeting the requirements for clinical use, but that they can provide valuable information to researchers and model developers. Higher quality datasets and careful considerations regarding how the explanations are presented might lead to solutions that are more welcome in the clinic.

PMID:40775463 | DOI:10.1038/s41598-025-14408-y

Sci Rep. 2025 Aug 7;15(1):28961. doi: 10.1038/s41598-025-14886-0.

ABSTRACT

To enhance user interaction experience in furniture customization, this study optimizes an Internet of Things (IoT)-driven Artificial Intelligence (AI)-assisted design system. First, the study analyzes human-computer interaction theories in IoT environments. Second, a personalized furniture design model based on a Generative Adversarial Network (GAN) is constructed. This enhances the AI-assisted design system's ability to generate diverse design solutions while avoiding the limitations of traditional systems. Compared to other deep learning architectures (e.g., encoder-decoder networks), GAN excels in generating realistic and creative furniture design solutions. Finally, virtual reality (VR) technology is integrated to enable real-time interaction between users and customized furniture. The Kano model is used to evaluate the interactive features of the furniture. The results show that in the proposed interactive furniture customization system, female users prioritize comfort, convenient control functions, and safety. They also expect a smooth and intuitive interaction experience. Male users focus more on convenient control functions, visualization features, and safety, with Proportion of Attractive Quality (PA) scores of 60.80%, 56.32%, and 73.18%, respectively. Younger users significantly value visualization features and convenient control functions while also emphasizing safety. Middle-aged and elderly users prioritize operational functionality and comfort, with relatively lower demand for social and entertainment features. In terms of income levels, low-income users mainly focus on comfort, operational functionality, and safety, with PA values of 60.12%, 66.21%, and 72.35%, respectively. Middle-income users show higher demand for visualization features, with a PA value of 55.21%. High-income users emphasize safety and comfort more. The designed system effectively highlights the preferences of users across different genders, age groups, and income levels, enabling flexible design adjustments based on user characteristics. This method better meets the personalized needs of diverse users while addressing the limitations of traditional AI-assisted design systems in generating diverse solutions. It provides new insights for smart furniture design, enhancing adaptability and flexibility, and promoting technological innovation and interdisciplinary integration. This study holds significant academic value and practical application prospects.

PMID:40775453 | DOI:10.1038/s41598-025-14886-0

Sci Rep. 2025 Aug 7;15(1):28949. doi: 10.1038/s41598-025-14320-5.

ABSTRACT

With the growing demand for English language teaching, the efficient and accurate evaluation of students' writing ability has become a key focus in English education. This study introduces a Hybrid Feature-based Cross-Prompt Automated Essay Scoring (HFC-AES) model that leverages deep learning for intelligent text analysis. Building on traditional deep neural networks (DNNs), the model incorporates text structure features and attention mechanisms, while adversarial training is employed to optimize feature extraction and enhance cross-prompt adaptability. In the topic-independent stage, statistical methods and DNNs extract shared features for preliminary scoring. In the topic-specific stage, topic information is integrated into a hierarchical neural network to improve semantic understanding and topic alignment. Compared with existing Transformer-based scoring models, HFC-AES demonstrates superior robustness and semantic modeling capabilities. Experimental results show that HFC-AES achieves strong cross-prompt scoring performance, with an average Quadratic Weighted Kappa (QWK) of 0.856, outperforming mainstream models. Ablation studies further highlight the critical role of text structure features and attention mechanisms, particularly in improving argumentative writing assessment. Overall, HFC-AES offers effective technical support for automated essay grading, contributing to more reliable and efficient evaluation in English language teaching.

PMID:40775439 | DOI:10.1038/s41598-025-14320-5