Science Progress最新文献

{"title":"Clinicopathological characteristics, one-year survival, and predictors among patients with soft tissue sarcoma: A retrospective cohort study at a tertiary referral center in Tanzania.","authors":"Moses Sango, Furaha Serventi, Jay Lodhia, Samwel Chugulu, Alex Mremi","doi":"10.1177/00368504251381584","DOIUrl":"10.1177/00368504251381584","url":null,"abstract":"<p><p>ObjectiveSoft tissue sarcomas (STSs) are rare, heterogeneous tumors of mesenchymal origin that arise from muscle, fat, fibrous tissue, blood vessels, nerves, and connective tissue. They pose significant diagnostic and therapeutic challenges, and limited data exist on their epidemiology and outcomes in sub-Saharan Africa. This study assessed the clinicopathological characteristics and one-year survival of patients with STSs managed at a tertiary facility in Tanzania.MethodsA retrospective cohort review was conducted of medical records from January 2019 to April 2023. Data included patient demographics, tumor site, histological subtype, grade, stage at diagnosis, treatment modalities, and follow-up. Survival was estimated using Kaplan-Meier analysis, and Cox proportional hazards regression was applied to identify predictors of one-year survival.ResultsNinety-six cases were analyzed. Males constituted 54.2% of patients, and the majority (70.8%) were aged 15-64 years. Rhabdomyosarcoma was the most frequent histological type (34.4%), followed by sarcoma not otherwise specified (28.1%). Surgery was the predominant treatment modality. The overall one-year survival rate was 63.8% (95% CI: 48.0-71.7). Female sex (adjusted hazard ratio (HR): 3.36; 95% CI: 1.25-9.03; <i>p</i> = 0.016) and absence of surgery (adjusted HR: 5.57; 95% CI: 1.92-16.14; <i>p</i> = 0.002) were independent predictors of increased mortality. The advanced stage (Stage IV: HR = 9.37; unknown stage: HR 10.30) showed a trend toward poorer outcomes, although not statistically significant. Histological subtype was not clearly associated with mortality, though gastrointestinal stromal tumors (GISTs) trended toward improved survival (HR = 0.06; <i>p</i> = 0.057). Adjuvant chemotherapy was associated with increased mortality (HR = 4.39; <i>p</i> = 0.049), likely due to confounding by indication.ConclusionApproximately two-thirds of patients with STSs survive one year post-diagnosis. Prognosis is strongly influenced by sex, stage, and surgical management. These findings highlight the need for early diagnosis, appropriate surgery, and structured multidisciplinary care to improve survival outcomes in Tanzanian tertiary settings.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251381584"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12446794/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Influenza A and B virus infection status in Jinshan District, Shanghai.","authors":"Jing Chen, Shanshan Chen, Tao Xiao","doi":"10.1177/00368504251381111","DOIUrl":"10.1177/00368504251381111","url":null,"abstract":"<p><p>ObjectiveTo determine the prevalence of influenza A and B virus infection according to age, gender, and month in Jinshan District, Shanghai, and to set local prevention strategies.MethodsThe study was categorized as descriptive, involving patients having respiratory complaints at Tinglin Hospital in Jinshan District between January 2024 and December 2024. Analysis of nasopharyngeal samples was achieved by rapid diagnostic assessment of influenza A and B antigens. The results were analyzed according to age, gender, and the month of the testing. The chi-square test and Fisher's exact tests were used, with a statistical significance of <i>P</i> < 0.05.ResultsIn 12,450 specimens, 2664 were positive for influenza A or B virus, which is an overall rate of infection of 21.4%. Most states had experienced in the category of the age of 7-18 years of age (28.5%), whereas those not in the 60 and above (8.9%) were the least. They did not reveal important gender differences. Peak periods were during January (48.6%) and December (10.3%).ConclusionThe infection of influenza A and B viruses resulted in a significant seasonality and age-based regularity in Jinshan District, with school-going children and winter being the most affected. The results can be used to justify an age-specific preventive regime as well as improved implementation of prevention methods showcasing seasonality.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251381111"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12446802/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145088346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Which type of vaccine is more beneficial for reducing the risk of deep vein thrombosis, CoronaVac, BNT162b2, or TURKOVAC?","authors":"Süleyman Yazıcı, Osman Fehmi Beyazal, Hasan Tezcan","doi":"10.1177/00368504251366362","DOIUrl":"10.1177/00368504251366362","url":null,"abstract":"<p><p>ObjectiveThe aim of this study is to reveal the relationship between TURKOVAC, CoronaVac, and BNT162b2 and deep vein thrombosis.MethodsBetween 2022 and 2024, a case-control study was planned with 400 patients included (deep vein thrombosis group (<i>n</i> = 200) and control group (<i>n</i> = 200). Patients were divided into four groups according to their vaccine types. Group 1 (<i>n</i> = 54): those who received only CoronaVac, Group 2 (<i>n</i> = 233): those who received only BNT162b2, Group 3 (<i>n</i> = 49): those who received CoronaVac for the first dose, and then BNT162b2, Group 4 (<i>n</i> = 15): those who received BNT162b2 for the first dose and then TURKOVAC. First, the deep vein thrombosis and control groups were compared regarding basic characteristics. Then, patients in the four groups were compared in terms of deep vein thrombosis.ResultsNo difference was found in the frequency of COVID-19 disease in the deep vein thrombosis and control groups. The frequency of vaccination was lower in the deep vein thrombosis group (84%-91.5%). According to the multivariate regression test result, we found that COVID-19 vaccination was protective against deep vein thrombosis (<i>p</i> = 0.003, OR = 0.377 [95% CI, 0.197-0.722]). After being divided into four groups, the rates of deep vein thrombosis were 36 (66.7%), 96 (41.2%), 29 (59.2%), and 7 (46.7%), respectively. The frequency of deep vein thrombosis was significantly lower in Group 2 (<i>p</i> = 0.003). Although no statistically significant difference was found among other groups, the lowest deep vein thrombosis frequency was found in Group 4, Group 3, and Group 1, respectively.ConclusionThe frequency of COVID-19 vaccination was lower in patients with deep vein thrombosis than in those without. Deep vein thrombosis was least common in patients who received only BNT162b2. Although the frequency of deep vein thrombosis was similar in the groups, we found that the lowest rate of deep vein thrombosis was in the group that received TURKOVAC after BNT162b2.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251366362"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12340335/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144818386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable machine learning model for predicting myocardial injury in intensive care unit patients using SHapley Additive exPlanations analysis.","authors":"Xiaojiang Liu, Guanyang Chen, Chenxiao Hao, Youzhong An, Huiying Zhao","doi":"10.1177/00368504251370452","DOIUrl":"https://doi.org/10.1177/00368504251370452","url":null,"abstract":"<p><p>ObjectiveThe identification of myocardial injury in the intensive care unit (ICU) has received little attention from researchers. Therefore, this retrospective cohort study aimed to develop a machine-learning model to predict the occurrence of myocardial injury in the ICU.MethodsBased on the Clinical Research Data Platform of Peking University People's Hospital, we enrolled adult, non-cardiac surgical, and non-obstetric patients who were admitted to the ICU between 2012 and 2022. Logistic regression, random forest, LASSO regression, support vector machine and extreme gradient boosting (XGBoost) models were developed to predict myocardial injury.ResultsData from 7453 non-cardiac surgery adult patients in ICU were collected in the derivation cohort (myocardial injury group: 2161 [29%], non-myocardial injury group: 5292 [71%]). Among the five models, the XGBoost model (area under the curve = 0.779; accuracy = 0.781) exhibited the best predictive performance for myocardial injury and the results were explained by the SHapley Additive exPlanations analysis. The top six features of the XGBoost model were maximal heart rate, respiratory rate, temperature, minimal heart rate, age and plasma transfusion.ConclusionThis machine-learning model, developed using the XGBoost algorithm, could be a valuable tool for clinical decision-making and detecting myocardial injury in the ICU.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251370452"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12378537/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144979286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A convolutional neural network-long short-term memory (CNN-LSTM)-Attention model based on wavelet transform for predicting non-stationary wind pressure coefficients on the surface of terminal glass curtain wall.","authors":"Yuxuan Bao, Cheng Pei, Yuhao Mou, Mingjie Li, Xiaokang Cheng","doi":"10.1177/00368504251366365","DOIUrl":"10.1177/00368504251366365","url":null,"abstract":"<p><p>In this paper, a neural network model combining wavelet decomposition and attention mechanism is proposed for the accurate prediction of non-stationary wind pressure on the surface of the glass curtain wall of an airport terminal building under strong wind conditions. The traditional methods often prove difficult in capturing local features and time-frequency variations of non-smooth signals when dealing with them, resulting in limited prediction accuracy. The proposed methodology involves a two-step process. Initially, wavelet decomposition of the original wind pressure coefficient sequence is performed, resulting in the reconstruction of subsequences at high and low frequencies. Subsequently, a convolutional neural network-long short-term memory (CNN-LSTM) neural network model incorporating an attention mechanism is constructed, leading to the attainment of high-precision wind pressure predictions. The experimental results demonstrate that the model performs well in the task of predicting non-stationary wind pressure coefficient sequences, with significantly lower prediction errors compared to a single prediction model. Furthermore, in comparison with alternative models that do not incorporate wavelet decomposition, the wavelet transform-CNN-LSTM-Attention model proposed in this paper has the capacity to enhance the mean absolute error, root mean square error, and mean absolute percentage error metrics by 15% to 18%, 12% to 16%, and 26% to 46%, respectively. This study provides reliable technical support for the safety assessment of glass curtain wall structures of airport terminals under extreme weather conditions, and has important engineering application value.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251366365"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12322375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144786035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic impact of peripheral blood ratio in sinonasal squamous cell carcinoma.","authors":"Tian Wang, Qi Zhang, Li Wang, Jie Wang, Keqing Zhao, Xinmao Song","doi":"10.1177/00368504251364321","DOIUrl":"10.1177/00368504251364321","url":null,"abstract":"<p><p>ObjectiveSinonasal squamous cell carcinoma usually presents at an advanced stage at the time of diagnosis, and there is still a lack of indicators to predict the prognosis of sinonasal squamous cell carcinoma patients. We aim to investigate whether the peripheral blood ratios may be good options for predicting the progression in patients with sinonasal squamous cell carcinoma.MethodsWe performed a retrospective analysis of 198 patients with sinonasal squamous cell carcinoma between January 2010 and December 2022. The systemic inflammatory response index, platelet/lymphocyte ratio, neutrophil/lymphocyte ratio, and lymphocyte/monocyte ratio were calculated. We examined the predictive value for the prognosis of sinonasal squamous cell carcinoma patients.ResultsThe systemic inflammatory response index (1.21 vs. 0.79, <i>P</i> < 0.001), lymphocyte/monocyte ratio (3.51 vs. 5.01, <i>P</i> < 0.001), neutrophil/lymphocyte ratio (2.83 vs. 2.02, <i>P</i> < 0.001), and platelet/lymphocyte ratio (136.70 vs. 113.84, <i>P</i> = 0.0042) values were significantly different between T4 stage and T1-3 stage. Univariate analysis showed that using appropriate threshold values, systemic inflammatory response index (0.5), platelet/lymphocyte ratio (127.4), lymphocyte/monocyte ratio (4.9), and neutrophil/lymphocyte ratio (2.6) predicted overall survival, progression-free survival, and distant metastasis-free survival. Multivariate Cox regression showed that high lymphocyte/monocyte ratio was associated with poor prognosis.ConclusionsThe values of neutrophil/lymphocyte ratio, systemic inflammatory response index, lymphocyte/monocyte ratio, and platelet/lymphocyte ratio can be used as parameters for the prognosis of sinonasal squamous cell carcinoma. In sinonasal squamous cell carcinoma patients, lymphocyte/monocyte ratio is a sensitive factor in predicting overall survival and distant metastasis-free survival.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251364321"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12317209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144746131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating miRNA-driven DNA methylation: Statistical evidence of gene-specific modulation.","authors":"Seyeon Jeon, Ha Ra Jun, Ji-Young Lee, Chang Ohk Sung, Sung-Min Chun","doi":"10.1177/00368504251370988","DOIUrl":"10.1177/00368504251370988","url":null,"abstract":"<p><p>ObjectiveDNA methylation is a key regulator of gene expression and plays a crucial role in cancer development. However, the mechanisms driving gene-specific methylation remain unclear. This study investigates the role of microRNAs (miRNAs) in regulating promoter methylation of specific genes, aiming to uncover miRNA-driven modulation of gene methylation in cancer.MethodsWe analyzed data from the Cancer Cell Line Encyclopedia (CCLE) database, comprising 813 cell lines. Spearman's rank correlation was performed between the expression levels of 734 miRNAs and the methylation levels of 20,587 genes, focusing on CpG islands in promoter regions. Linear regression analysis was used to validate the relationship between selected miRNAs and gene clusters. Bioinformatics screening identified statistically significant miRNA-gene pairs involved in promoter methylation.ResultsThe analysis revealed 25 target genes whose promoter methylation was significantly associated with the expression of four miRNAs (hsa-miR-200a, hsa-miR-200b, hsa-miR-200c, and hsa-miR-141). These correlations were most pronounced in colorectal, gastric, lung, and ovarian cancers. Notably, cancer-related genes such as ST14, OVOL1, and EPCAM were identified as targets, supporting the hypothesis that miRNAs regulate promoter methylation in these genes.ConclusionOur findings suggest that specific miRNAs induce promoter methylation in cancer-related genes, thereby influencing gene expression. This study expands our understanding of the role of miRNAs in tumor development and highlights the potential of miRNA-based therapies in cancer treatment. As this is a computational study, further experimental validation is required to confirm the proposed regulatory mechanisms.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251370988"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12365458/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144876963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of a bio-hybrid solar quadricycle for sustainable urban delivery service.","authors":"Muhammad Khubaib, Muhammad Ali Ijaz Malik, Zain Ul Hassan","doi":"10.1177/00368504251359090","DOIUrl":"10.1177/00368504251359090","url":null,"abstract":"<p><p>The current study intends to provide a sustainable substitute for conventional motorbike-based delivery systems in Sydney, Australia, by designing a novel bio-hybrid solar quadricycle powered by plug-in, pedal, and solar energy. The current study exclusively integrates structural material analysis through ANSYS with powertrain simulation in Simulink to ascertain performance and feasibility. Among the tested materials, the low alloy steel AISI 4140 exhibits exceptional structural integrity with a minimal total deformation of 0.56116 mm, low equivalent strain (0.00073098 mm/mm), and the highest safety factor (4.3469). Modal analysis identifies aluminum 6061-T6 as effective in vibration damping, enhancing rider comfort, but other static structural results are not satisfactory. Simulink results confirm that a 1.8 kW DC motor coupled with a 3 kW lithium ion battery (LIB) permits effective operation over the New European Driving Cycle (NEDC) drive cycle, covering 3.3 km at a peak speed of 34 km/h, with only less than 1.5% drop in battery state of charge (SOC). Although the AISI 4140 shows the most effective results, it possesses higher hardness and lower ductility and is therefore less appropriate for parts that undergo exposure to cyclic loads, making it unsuitable for the whole chassis. AISI 4130 offers the best overall balance of strength, fatigue resistance, and ease of manufacturing. AISI 4130 also provides a superior blend of resilience, resistance to fatigue, and weldability. The outcomes portray AISI 4130 as the optimal frame material, offering a promising solution for eco-friendly and ergonomic urban delivery transport in Sydney, Australia.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251359090"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12277678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144676668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Atmospheric pressure plasma-assisted epichlorohydrin-grafting onto pineapple fiber and immobilization with polyethyleneimine for <i>p</i>-nitrophenol removal.","authors":"Sunan Saikrasun, Taweechai Amornsakchai, Onanong Cheerarot","doi":"10.1177/00368504251360317","DOIUrl":"10.1177/00368504251360317","url":null,"abstract":"<p><p>The cost-effective, eco-friendly, and easily available adsorbent prepared using atmospheric pressure plasma (APP)-induced epichlorohydrin-grafting onto alkali-treated pineapple leaf fiber (APF) and immobilization with polyethyleneimine (PEI) was investigated and applied for <i>p</i>-nitrophenol (PNP) removal. The results from main characterization methods such as morphological observation, Fourier transform infrared analysis, and x-ray photoelectron spectroscopy revealed the surface changes and confirmed the success of the surface modifications. According to the experimental data, APP pre-treated adsorbent following by PEI immobilization (t-APF-<i>e</i>-PEI) exhibited fast and efficient adsorption with the adsorption capacity up to 128 mg/g, whereas the adsorption capacities for APF-<i>e</i>-PEI and APF were 115 and 21 mg/g, respectively, at 30 °C. The adsorption process was exothermic whereas the adsorption behavior conformed to the pseudo-first-order kinetics, intra-particle diffusion, and Langmuir isotherm models. Electrostatic ion-dipole interaction between protonated amines of PEI and negative-charged sites of PNP was proposed as the main mechanism. The prepared adsorbents exhibited good adsorption efficiency with possessing high adsorption capacity for repeated uses. The modified adsorbent provided from agricultural waste had a great potential as low cost, eco-friendly, and easily available adsorbent material to adsorb PNP from aqueous solutions.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251360317"},"PeriodicalIF":2.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12268148/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144644248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Science progress distinguishing different types of airway stents under bronchoscopy by artificial intelligence.","authors":"Chongxiang Chen, Yingnan Zuo, Jingyu Liu, Mingyue Min, Jiangtao Ren, Huiping Qiu, Wenhua Jian, Ping Peng, Changhao Zhong, Shiyue Li","doi":"10.1177/00368504251362931","DOIUrl":"10.1177/00368504251362931","url":null,"abstract":"<p><p>ObjectiveIn prior research, we employed artificial intelligence (AI) to distinguish different anatomical positions in the airway under bronchoscopy. We aimed to leverage AI to identifying different types of airway stent.MethodsTo \"deep learn\" imaging data from patients who underwent bronchoscopy for implanting airway stents from January 2010 to June 2024, utilizing the Vision Transformer model (AI architecture). Eight percent of randomized clear images of the upper ends of stents from 662 patients were used to train for three main types of airway stent (T-shaped silicone, silicone, and metal-covered), and to determine if the stents were Y-shaped. The remaining 20% of clear images were utilized for validation.ResultsA total of 1254 bronchoscopic images of the upper ends and interiors of stents from 662 patients with different types of stents were analyzed. These types of stents were T-shaped silicone (70 patients), Y-shaped silicone stents (121), non-Y-shaped silicone stents (196), Y-shaped metal covered (67), and non-Y-shaped metal covered (208). A total of 662 bronchoscopic images depicting the upper ends of stents were utilized to identify three primary types of stents: T-shaped silicone, all silicone, and all metal covered. The mean accuracy for recognizing these three types was 98.5%, with individual accuracies of 93.3% for T-shaped silicone, 98.4% for all silicone, and 100% for all metal-covered stents. The area under the curve value for these three types was >0.99. Additionally, 592 images of stent interiors were employed for training and validation to determine if they were Y-shaped, and if they could be categorized further into Y-shaped silicone, non-Y-shaped silicone, Y-shaped metal-covered, or non-Y-shaped metal-covered stents. The accuracies for identifying Y-shaped silicone stents and Y-shaped metal-covered stents were 95.5% and 100%, respectively.ConclusionsArtificial intelligence technology can differentiate between various types of stent utilizing bronchoscopy images. The trained model holds potential to improve quality control in future clinical applications.</p>","PeriodicalId":56061,"journal":{"name":"Science Progress","volume":"108 3","pages":"368504251362931"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12319208/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144762449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}