Journal of Radiation Research and Applied Sciences最新文献

{"title":"Regulation of the LAMTOR5-AS1/miR-134-5p/ANGPTL4 axis by ING5 in non-small-cell lung cancer","authors":"Haihua Zhang ,&nbsp;Xueying Liu ,&nbsp;Xinli Liu ,&nbsp;Yifan Zhang ,&nbsp;Guizhou Gao ,&nbsp;Xiaodong Wang ,&nbsp;Lin Qu ,&nbsp;Gaofeng Liu ,&nbsp;Tao Zhang","doi":"10.1016/j.jrras.2025.102143","DOIUrl":"10.1016/j.jrras.2025.102143","url":null,"abstract":"<div><h3>Background</h3><div>The underlying mechanisms of non-small-cell lung cancer (NSCLC) are still not fully understood. Inhibitor of growth 5 (ING5) overexpression inhibit aggressiveness of NSCLC.</div></div><div><h3>Methods</h3><div>The analysis of differentially expressed mRNAs and lncRNAs was conducted using whole transcriptome sequencing. miRNA microarray revealed differentially expressed miRNAs. LncACTdb 3.0 and miRTarBase were used to construct ceRNA interaction network. qRT-PCR was performed to validate gene expression levels. Single-cell RNA sequencing analysis was performed to analysis tumor immune infiltration. Dual-luciferase reporter assay was used to verify the combination. Quantitative real-time PCR and Western blot were performed to validate LAMTOR5-AS1, miR-134-5p, and ANGPTL4 expression.</div></div><div><h3>Results</h3><div>1648 differentially expressed mRNAs (833 up- and 815 downregulated-) between the control and ING5 overexpression groups; further, 114 immune-related mRNAs were observed to be differentially expressed. Overall, 110 lncRNAs were found to interact with 15 differential miRNAs, resulting in 230 potential interactions. Survival and expression analyses led to the identification of the LAMTOR5-AS1/miR-134-5p/ANGPTL4 axis as a potential regulatory pathway. Upregulated ANGPTL4 expression was associated with poor prognosis with increased numbers of fibroblasts and decreased numbers of T cells. miR-134-5p was the target gene of LAMTOR5-AS1. Furthermore, the decrease in miR-134-5p expression partially reversed the inhibitory impact of LAMTOR5-AS1 depletion on cell proliferation, migration, and invasion.</div></div><div><h3>Conclusion</h3><div>To conclude, the novel LAMTOR5-AS1/miR-134-5p/ANGPTL4 axis inhibits NSCLC progression by regulating immune infiltration in ING5 overexpression cells.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102143"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation value of ultrasonic shear wave elastic imaging, MRI combined with ADC value in liver fibrosis degree of nonalcoholic fatty liver","authors":"Yang Liu,&nbsp;Fei Teng,&nbsp;Yan Ding,&nbsp;Jian Zhou,&nbsp;Qibo Cai,&nbsp;Yang Shi,&nbsp;Qi Liu","doi":"10.1016/j.jrras.2025.102135","DOIUrl":"10.1016/j.jrras.2025.102135","url":null,"abstract":"<div><div>To investigate the value of ultrasonic shear wave elastography (SWE), magnetic resonance imaging (MRI) and apparent diffusion coefficient (ADC) in evaluating the degree of liver fibrosis in nonalcoholic fatty liver disease (NAFLD).</div><div>150 patients with NAFLD were selected as the observation group, another 150 healthy subjects were selected as the control group. According to METAVIR score, the degree of liver fibrosis was divided into F0 stage, F1 stage, F2 stage, F3 stage and F4 stage. SWE, MRI and ADC values were detected in all subjects. Spearman correlation coefficient was used to analyze the correlation between each parameter and the stage of liver fibrosis.</div><div>The results of liver puncture pathology were the gold standard. Young's modulus and MRI-PDFF (Proton density fat fraction) in observation group were higher than those in control group, ADC was lower than those in control group (<em>P</em> &lt; 0.05). Young's modulus and MRI-PDFF in F4 group were higher than those in F3, F2, F1 and F0 groups (<em>P</em> &lt; 0.05), and ADC in F4 group was lower than that in F3, F2, F1 and F0 groups (<em>P</em> &lt; 0.05), and the differences among all groups were statistically significant (<em>P</em> &lt; 0.05). Young's modulus and MRI-PDFF were positively correlated with the degree of NAFLD liver fibrosis, while ADC was negatively correlated (<em>r</em> = 0.662, 0.542, −0.571, <em>P</em> &lt; 0.05). The <em>AUC</em> value of Young's modulus, MRI-PDFF and ADC values in the evaluation of the degree of NAFLD liver fibrosis was higher than that of single detection (<em>Z</em> = 3.283, 3.276, 4.038, <em>P</em> &lt; 0.05). The calibration curve and receiver operating characteristic curve (<em>ROC</em>) showed that the model had better predictive value, and the plotted decision curve (DCA) also showed obvious positive net benefit.</div><div>The combined determination of SWE, MRI and ADC has higher value in evaluating the degree of liver fibrosis in NAFLD. The nomogram model established by this method has good predictive value.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102135"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic value of bronchoalveolar lavage fluid testing combined with high-resolution computed tomography of patients with invasive pulmonary fungal disease","authors":"Xiaojin Zheng ,&nbsp;Kaili Xu","doi":"10.1016/j.jrras.2026.102171","DOIUrl":"10.1016/j.jrras.2026.102171","url":null,"abstract":"<div><h3>Objective</h3><div>This study was aimed to evaluate the diagnostic value of bronchoalveolar lavage fluid (BALF) testing plus high-resolution computed tomography (HRCT) of patients with invasive pulmonary fungal infection (IPFI).</div></div><div><h3>Methods</h3><div>Two hundred and thirty patients with invasive pulmonary fungal disease were rolled into invasive group (n = 104) and non-invasive group (n = 126) under the diagnostic criteria for IPFI. All patients underwent BALF testing and HRCT imaging. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of BALF testing, HRCT imaging, and their combination were calculated. Seven fungal species were identified in invasive group, with <em>Aspergillus fumigatus</em> exhibiting the highest isolation rate of 61 cases (58.65 %). BALF testing detected fungi in 87 patients, including 57 cases of <em>Aspergillus fumigatus</em>, demonstrating a concordance rate of 93.44 %.</div></div><div><h3>Results</h3><div>The prevalence of IPFI was 45.22 % (104/230). HRCT findings revealed that invasive fungal infections predominantly affected the left upper lobe (51 cases, 25.89 %). Radiological features included cavities (36.54 %), solitary nodules or masses (25.96 %), aspergillomas (16.35 %), and patchy or consolidative opacities (21.15 %). 1,3-β-D-glucan in serum and galactomannan (GM) in BALF in the invasive group was relatively higher than non-invasive group (<em>P</em> &lt; 0.05). BALF testing demonstrated a sensitivity of 73.08 %, specificity of 91.27 %, PPV of 87.36 %, NPV of 80.42 %, and an area under the ROC curve (AUC) of 0.591. HRCT imaging showed a sensitivity of 65.38 %, specificity of 92.06 %, PPV of 87.18 %, NPV of 76.32 %, and an AUC of 0.724. Combined testing (BALF + HRCT) exhibited superior performance, achieving a sensitivity of 84.62 %, specificity of 93.65 %, PPV of 91.67 %, NPV of 88.06 %, and an AUC of 0.807.</div></div><div><h3>Conclusion</h3><div>The combination of BALF testing and chest HRCT demonstrates high diagnostic value for IPFI, greatly improving sensitivity and specificity. This integrated approach shows promising diagnostic value and may provide a useful basis for clinical decision-making, though findings require validation in larger, prospective, multi-center studies.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102171"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated functional and metabolomic profiling reveals coordinated roles of CDK1 and FUT2 in lung adenocarcinoma progression","authors":"Yongjian Tian ,&nbsp;Wenfeng Zhang ,&nbsp;Xue Li ,&nbsp;Shunshun Cui ,&nbsp;Hao Wu ,&nbsp;Pengjuan Liu ,&nbsp;Wei Wang","doi":"10.1016/j.jrras.2025.102157","DOIUrl":"10.1016/j.jrras.2025.102157","url":null,"abstract":"<div><h3>Background</h3><div>Lung adenocarcinoma (LUAD) exhibits uncontrolled proliferation and metabolic reprogramming. Cyclin-dependent kinase 1 (CDK1) drives the G2/M transition, while fucosyltransferase 2 (FUT2) catalyzes α1,2-fucosylation, which broadly influences receptor signaling and stress responses. The mechanism by which these two proteins interact to shape LUAD metabolism remains unclear.</div></div><div><h3>Methods</h3><div>We employed structural modeling, transcriptomics, functional assays, and untargeted metabolomics to elucidate the roles of CDK1 and FUT2 in LUAD. A549 cells, a well-characterized lung adenocarcinoma model commonly used for studies of proliferation and metabolic rewiring, were selected for functional assays and untargeted metabolomics.</div></div><div><h3>Results</h3><div>Overexpressing CDK1 or FUT2 in A549 cells significantly altered cell viability and induced distinct metabolic shifts. CDK1 overexpression was associated with enrichment of oxidative phosphorylation and AMPK signaling pathways, thereby elevating key metabolites such as NAD⁺ and taurocholic acid. FUT2 overexpression perturbed tryptophan metabolism and Wnt signaling, resulting in increased levels of L-kynurenine, pyridoxine, and xanthurenic acid. Functionally, CDK1 inhibition using RO-3306 suppressed A549 cell proliferation and disrupted energy metabolism, whereas FUT2 promoted proliferation, potentially through antioxidant defense and lipid biosynthesis pathways.</div></div><div><h3>Conclusions</h3><div>CDK1 and FUT2 regulate complementary metabolic programs in LUAD, linking cell-cycle control and glycosylation to metabolic adaptation. These results provide a rationale for combined targeting of CDK1- and FUT2-linked pathways and support further preclinical evaluation of combination regimens.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102157"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Medical and radiation science analysis using a probability U-Net with a GRU model","authors":"Ahmed I. Taloba,&nbsp;Rayan Alanazi","doi":"10.1016/j.jrras.2025.102134","DOIUrl":"10.1016/j.jrras.2025.102134","url":null,"abstract":"<div><div>Accurate and interpretable segmentation of CT images of the lungs is critical for early diagnosis and treatment planning in pulmonary diseases. The current deep learning (DL) models tend to lack uncertainty quantification, lack consistency over time, and do not extrapolate into ambiguous areas. To solve these problems, this study suggests a hybrid DL model that combines U-Net with Gated Recurrent Units (GRUs) and a probabilistic latent space to segment based on uncertainty. The encoder learns both spatial and temporal features using GRU-enhanced convolutional blocks, and the probabilistic module of the bottleneck addresses aleatory and epistemic uncertainty via Monte Carlo sampling. This joint temporal modeling and probabilistic representation allows the system to perform temporally consistent segmentation with only one lightweight architecture. The experiments on the IQ-OTH/NCCD lung CT dataset (1295 annotated images) demonstrate that the proposed model achieves 98.9 % accuracy and a 91.5 % Dice coefficient, which is 7–15 % higher than state-of-the-art models, including ResNet18 with MC Dropout and SkinSAM. The model also achieves an Expected Calibration Error of just 2.8 % which justifies its validity in the clinic. Uncertainty maps can also aid decision-making regarding tumor boundaries. Compared with previous applications such as Probabilistic U-Net and GRU-Net, which operate independently, the suggested U-Net-GRU-Probabilistic framework offers an integrated, confident, and understandable method for segmenting lung CT. Demonstrates potential for real-time diagnostic deployment.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102134"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145787137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in MRI clinical practice: From historical innovation to emerging trends","authors":"Shrooq T. Aldahery","doi":"10.1016/j.jrras.2026.102158","DOIUrl":"10.1016/j.jrras.2026.102158","url":null,"abstract":"","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102158"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145920842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Meta-analysis of diffusion-weighted imaging in detecting postoperative ischemic brain injury in patients with carotid artery stenosis","authors":"Lisha Fan,&nbsp;Feng Chen","doi":"10.1016/j.jrras.2026.102177","DOIUrl":"10.1016/j.jrras.2026.102177","url":null,"abstract":"<div><h3>Objective</h3><div>This work systematically evaluated the incidence and influencing factors of new ischemic brain lesions detected by diffusion-weighted imaging (DWI) following carotid endarterectomy (CEA) or carotid artery stenting (CAS) in patients with CA stenosis through a systematic review and meta-analysis.</div></div><div><h3>Methods</h3><div>Relevant studies on new ischemic brain lesions detected by DWI after CEA or CAS were retrieved from multiple databases. After literature screening and quality assessment, eleven eligible studies were included. Meta-analysis of key indicators, including the incidence of DWI-detected ischemic lesions and the postoperative DWI-positive rate, was performed using <em>Stata MP18.0</em> and <em>RevMan5.3</em>.</div></div><div><h3>Results</h3><div>The pooled estimate of the detection rate of new DWI lesions per post-operative scan was 58.64 % (95 % CI: 44.30 %–72.98 %) under the fixed-effect model, with moderate heterogeneity among studies (<em>I</em>^<em>2</em> = 49.0 %, <em>P</em> = 0.047). Subgroup analysis showed that the incidence of DWI lesions after CAS was 37.84 % (95 % CI: 24.68 %–51.01 %), while after CEA it was 27.05 % (95 % CI: 25.10 %–28.99 %). Among CAS studies reporting the use of embolic protection devices (EPD), the pooled risk difference was 93.82 (95 % CI: 45.34–142.31), with no heterogeneity (<em>I</em>^<em>2</em> = 0.0 %). The pooled effect size for the analysis of DWI lesion characteristics was 58.50 (95 % CI: 28.59–88.40), also with no heterogeneity among studies (<em>I</em>^<em>2</em> = 0.0 %).</div></div><div><h3>Conclusion</h3><div>This meta-analysis confirmed that new DWI ischemic lesions are common after carotid revascularization, with incidence varying by surgical method (higher in CAS than in CEA). Despite considerable heterogeneity, DWI appears effective for detecting acute postoperative cerebral ischemic injury. Its routine inclusion in assessment protocols should be considered alongside standardization efforts to reduce variability in imaging and procedural protocols.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102177"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Weifuchun alleviates MNNG-induced gastric epithelial cell injury via TGF-β1/PI3K/Akt pathway","authors":"Niansong Kang ,&nbsp;Haijun Fang ,&nbsp;Sihui Zheng","doi":"10.1016/j.jrras.2025.102111","DOIUrl":"10.1016/j.jrras.2025.102111","url":null,"abstract":"<div><h3>Background</h3><div>Chronic atrophic gastritis (CAG), a chronic form of gastritis, is critical in the early stages of stomach precancerous lesions. Delving into the origins of chronic atrophic gastritis and conducting drug screenings is crucial. However, the precise mechanisms by which Weifuchun protects gastric mucosal epithelial cells remain incompletely understood. This project's objective is to investigate the potential mechanisms by which Weifuchun safeguards gastric mucosal epithelial cells from harm.</div></div><div><h3>Methods</h3><div>We mimicked the CAG process by MNNG-induced injury of gastric mucosal epithelial cells (GES-1) and detected changes in cell activity, apoptosis, cell cycle and migration and invasion. Changes in cellular epithelial-mesenchymal transition (EMT), PI3K/AKT pathway proteins and inflammatory factors were detected. Exploring how Weifuchun influences the biological actions of GES-1 induced by MNNG. Then, pharmacological rescue experiments were performed by treatment with TGF-β1/PI3K/AKT inhibitors.</div></div><div><h3>Results</h3><div>MNNG induced GES-1 to undergo cellular aggressive transformation, including proliferation, invasion, and EMT. Weifuchun significantly ameliorated MNNG-induced damage to GES-1, with the effects of this treatment being regulated by the TGF-β1 and PI3K/Akt pathways.</div></div><div><h3>Conclusion</h3><div>The results demonstrated that Weifuchun has the potential to mitigate MNNG-induced inflammatory injury and aggressive transformation of gastric epithelial cells by modulating the TGF-β1/PI3K/AKT pathway. This suggests potential new perspectives and approaches for future research into the prevention and management of gastric cancer.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102111"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive identification and experimental validation of programmed cell death-anoikis genes in oral squamous cell carcinoma through machine learning approaches","authors":"Ning Li,&nbsp;Ruoxi Du","doi":"10.1016/j.jrras.2025.102138","DOIUrl":"10.1016/j.jrras.2025.102138","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to identify anoikis-related genes (ARGs) associated with Oral squamous cell carcinoma (OSCC) progression and prognosis.</div></div><div><h3>Methods</h3><div>We obtained RNA-sequencing data from TCGA (268 OSCC samples and 19 normal samples) and GEO validation cohort (GSE41613, 97 patients). Candidate anoikis-related genes were identified at the intersection of differentially expressed genes, WGCNA modules, and 338 known ARGs from literature. A comprehensive machine learning framework incorporating 117 algorithm combinations was developed to construct a prognostic risk model, with performance evaluated using concordance index and time-dependent ROC curves. Immune infiltration analysis was performed using the xCell algorithm. Functional validation was conducted through siRNA-mediated knockdown of risk genes and overexpression of protective genes in CAL27 cells, with transfection efficiency confirmed by qRT-PCR and cell viability assessed using CCK-8 assays.</div></div><div><h3>Results</h3><div>Through integrated bioinformatic analysis of TCGA and GEO datasets, we identified 53 candidate genes at the intersection of differentially expressed genes, weighted gene co-expression network analysis modules, and known ARGs. Functional enrichment analysis revealed significant involvement in biological processes related to anoikis regulation, cell-matrix adhesion, and cancer-related pathways. Using 117 machine learning algorithm combinations, we established a prognostic risk model based on eight ARGs (CTTN, PLAU, ITGA5, MET, TNFRSF12A, PLK1, PDK4, and SESN1), which effectively stratified OSCC patients into high and low-risk groups with significantly different survival outcomes in both training and validation cohorts. Multivariate Cox regression confirmed the risk score as an independent prognostic factor alongside T and N stages. In vitro experiments demonstrated that knockdown of risk genes and overexpression of protective genes significantly reduced cell viability in CAL27 cells.</div></div><div><h3>Conclusion</h3><div>This study provides novel insights into the molecular mechanisms of anoikis resistance in OSCC and potential therapeutic targets for improving patient outcomes.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102138"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence-based ensemble models for prediction of gender-based management competencies in an electromagnetic radiation digitally enhanced learning environments among secondary schools principals","authors":"Abdullahi Usman Jalingo ,&nbsp;Hisham M. Almongy ,&nbsp;Engin Baysen ,&nbsp;Nusaiba Ahmed Abdullahi","doi":"10.1016/j.jrras.2025.102106","DOIUrl":"10.1016/j.jrras.2025.102106","url":null,"abstract":"<div><div>Research indicates that women executives, particularly in industrialized countries, are more involved and dedicated to accomplishing organizational goals than men in schools and other organizations. The increasing adoption of digitized education in secondary schools also introduces new environmental factors, including electromagnetic fields (EMFs) which potentially contributes to increased cognitive load. While, the potential impact of these factors on leadership, especially women remain a growing global concern. Also, Gender-based adaptability and its effects on core management competencies in this increasingly digitized context remain underexplored. Nonetheless, the lack of educational possibilities in most African nations hinders women's advancement, and even if they do receive an education, they are sometimes denied the opportunity to demonstrate their abilities like men. This study investigates the impact of gender on school principals' managerial competencies by employing four artificial intelligence-based algorithms: AdaBoost, Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Utilizing 1082 data samples from the study region, the four AI models were trained and validated, each achieving strong predictive performance in assessing the gender-based variation in school principals' managerial skills. The accuracy scores were highest for Random Forest (&gt;0.97), followed by AdaBoost (&gt;0.95), SVM (&gt;0.93), and KNN (&gt;0.92). Results indicated that gender does not significantly influence principals' ability to cultivate a positive school culture, apply robust assessment methods, or promote instructional effectiveness. Additionally, the results revealed that the most crucial managerial abilities required of a school principal were instructional and curriculum development, communication, supervision, and motivational skills. However, the results found financial management skills to have little impact on principals' managerial abilities compared to other parameters. To solve the problems of gender disparity, the research suggests that principals receive specialized managerial skills training and be chosen based on their abilities rather than their gender, and suggest direction for further research.</div></div>","PeriodicalId":16920,"journal":{"name":"Journal of Radiation Research and Applied Sciences","volume":"19 1","pages":"Article 102106"},"PeriodicalIF":2.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145734388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}