1.Comparison of preoperative ocular biometry between Pentacam AXL and IOL Master 700 in cataract patients
Jinfen WEI ; Simin TAN ; Lin DING ; Qiuli ZHANG
International Eye Science 2026;26(1):148-151
AIM: To compare the preoperative ocular biometry between Pentacam AXL and IOL Master 700 in cataract patients.METHODS:Prospective study. A total of 150 patients(150 eyes)with cataracts who were treated in our hospital from May to December 2024 were selected. The IOL Master 700 and Pentacam AXL were preoperatively used to measure axial length(AL), corneal curvature(K1, K2 and Km), anterior chamber depth(ACD), and white-to-white(WTW). The difference and consistency of the results of the two instruments were compared.RESULTS: There was no significant difference between the two instruments in the AL, K1, K2, Km, ACD, and WTW(all P>0.05). The Spearman correlation analysis showed that the two instruments positively correlated with the AL, K1, K2, Km, ACD and WTW of the operated eye(all P<0.001). The Bland-Altman analysis showed that for the Pentacam AXL and IOL Master 700, there were 5/150(3.3%), 7/150(4.7%), 4/150(2.7%), 5/150(3.3%), and 0 points outside the 95%LoA for the AL, K1, K2, Km, ACD, and WTW of the examined eyes, respectively, with all of these values less than 5%, indicating good consistency.CONCLUSION:The AL, K1, K2, Km, ACD and WTW of Pentacam AXL and IOL Master 700 in cataract patients before cataract phacoemulsification combined with IOL implantation show no significant differences, and have good correlation and consistency. The two instruments can be used interchangeably.
2.Target of neohesperidin in treatment of osteoporosis and its effect on osteogenic differentiation of bone marrow mesenchymal stem cells
Zhenyu ZHANG ; Qiujian LIANG ; Jun YANG ; Xiangyu WEI ; Jie JIANG ; Linke HUANG ; Zhen TAN
Chinese Journal of Tissue Engineering Research 2025;29(7):1437-1447
BACKGROUND:Previous studies have found that neohesperidin can delay bone loss in ovariectomized mice and has the potential to treat osteoporosis,but its specific mechanism of action remains to be explored. OBJECTIVE:To explore the key targets and possible mechanisms of neohesperidin in the treatment of osteoporosis based on bioinformatics and cell experiments in vitro. METHODS:The gene expression dataset related to osteoporosis was obtained from GEO database,and the differentially expressed genes were screened and analyzed in R language.The osteoporosis-related targets were screened from GeneCards and DisGeNET databases,and the neohesperidin-related targets were screened from ChEMBL and PubChem databases,and the common targets were obtained by intersection of the three.The String database was used to construct the PPI network of intersection genes,and the key targets were screened.The DAVID database was used for GO and KEGG enrichment analysis.The AutoDock software was used to verify the molecular docking between the neohesperidin and the target protein.The effect of neohesperidin on osteogenic differentiation of C57 mouse bone marrow mesenchymal stem cells was detected.Complete medium was used as blank control group;osteogenic induction medium was used as the control group;and osteogenic induction medium containing different concentrations of neohesperidin(25,50 μmol/L)was used as experimental group.The expression of alkaline phosphatase,the degree of mineralization,the expression of osteogenic-related genes and target genes during osteogenic differentiation of cells were measured at corresponding time points. RESULTS AND CONCLUSION:(1)9 253 differentially expressed genes,2 161 osteoporosis-related targets,and 326 neohesperidin-related targets were screened.There were 53 common targets among the three.All 53 genes were up-regulated in osteoporosis samples.The PPI network screened the target gene PRKACA of research significance.GO function and KEGG pathway enrichment analysis showed that neohesperidin's treatment of osteoporosis through PRKACA target mainly depended on biological processes such as protein phosphorylation and protein autophosphorylation,acting on endocrine resistance,proteoglycan in cancer,and estrogen signaling pathway to play a therapeutic role.Molecular docking results showed that neohesperidin had a certain binding ability to the protein corresponding to the target PRKACA.(2)The results of alkaline phosphatase staining showed that neohesperidin could promote the expression of alkaline phosphatase in the early stage of osteogenic differentiation of mesenchymal stem cells.Alizarin red staining showed that neohesperidin could promote the mineralization of osteogenic differentiation of mesenchymal stem cells.RT-qPCR results showed that neohesperidin could increase the mRNA expression of alkaline phosphatase,PRKACA,and osteocalcin.(3)These results indicate that neohesperidin may promote osteogenic differentiation through PRKACA target on the estrogen signaling pathway to prevent and treat osteoporosis.
3.Treadmill training activates endogenous neural stem cells to promote spinal cord injury repair in mice
Chanjuan CHEN ; Zeyu SHANGGUAN ; Qizhe LI ; Wei TAN ; Qing LI
Chinese Journal of Tissue Engineering Research 2025;29(19):3976-3982
BACKGROUND:Treadmill training is one of the effective ways to promote the recovery of motor function after spinal cord injury.Treadmill training can promote neurogenesis,but the effect of different intensities of treadmill training on the activation of endogenous stem cells is still unclear. OBJECTIVE:To analyze the activation effect of different intensities of treadmill training on endogenous neural stem cells in the spinal cord of mice after spinal cord injury. METHODS:Fifty female C57BL/6J mice were divided into control group,spinal cord injury group,low-,moderate-,and high-intensity exercise groups with 10 mice in each group by random number table method.T10 segment spinal cord injury model was constructed by the clamp method in spinal cord injury group,low-,moderate-,and high-intensity exercise groups.On day 7 after spinal cord injury,mice in the low-,moderate-,and high-intensity exercise groups were respectively trained on the treadmill with corresponding intensity,3 times/d,10 min/times,6 times a week for 28 consecutive days.At 3,7,14,21,and 28 days after treadmill training,the hind limb motor function was evaluated by BMS score.At 28 days after treadmill training,the spinal cord tissue of the injured area was obtained,and the expression of epidermal growth factor receptor,glial fibrillary acidic protein,and 5-Ethynyl-2'-deoxyuridine(EdU),a proliferative marker,was detected.Hematoxylin-eosin staining was used to observe the morphology of spinal cord. RESULTS AND CONCLUSION:(1)The BMS score of mice in the spinal cord injury group was lower than that in the control group(P<0.05).With the extension of treadmill training time,the BMS scores of mice with spinal cord injury gradually increased,and the BMS scores of mice in moderate-intensity exercise group on days 14 and 21 after treadmill training were higher than those in spinal cord injury group and low-and high-intensity exercise groups(P<0.05).The BMS score of mice in moderate-and high-intensity exercise group was higher than that in spinal cord injury group and low-intensity exercise group at 28 days after treadmill training(P<0.05).(2)Compared with the control group,the proportion of epidermal growth factor receptor and EdU positive cells was increased in spinal cord injury group(P<0.05).Compared with spinal cord injury group,the proportion of epidermal growth factor receptor and EdU positive cells was increased in low-,moderate-,and high-intensity exercise groups(P<0.05),and the highest was found in moderate-intensity exercise group.Compared with control group,the proportion of glial fibrillary acidic protein positive cells was increased in spinal cord injury group(P<0.05).Compared with spinal cord injury group,the proportion of glial fibrillary acidic protein positive cells was lower in low-,moderate-,and high-intensity exercise groups(P<0.05),and the moderate-intensity exercise group was the lowest.(3)Hematoxylin-eosin staining showed that a large cavity was formed in the injured area of mice with spinal cord injury,and the cavity in the injured area of mice with spinal cord injury decreased after different intensities of treadmill training,and the decrease was most obvious in the moderate-intensity exercise group.(4)These results indicate that low-,moderate-,and high-intensity treadmill training can promote the recovery of motor function of mice with spinal cord injury by activating endogenous neural stem cells,and the effect of moderate-intensity exercise training is the most obvious.
4.Principles, technical specifications, and clinical application of lung watershed topography map 2.0: A thoracic surgery expert consensus (2024 version)
Wenzhao ZHONG ; Fan YANG ; Jian HU ; Fengwei TAN ; Xuening YANG ; Qiang PU ; Wei JIANG ; Deping ZHAO ; Hecheng LI ; Xiaolong YAN ; Lijie TAN ; Junqiang FAN ; Guibin QIAO ; Qiang NIE ; Mingqiang KANG ; Weibing WU ; Hao ZHANG ; Zhigang LI ; Zihao CHEN ; Shugeng GAO ; Yilong WU
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2025;32(02):141-152
With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.
5.Role of SPINK in Dermatologic Diseases and Potential Therapeutic Targets
Yong-Hang XIA ; Hao DENG ; Li-Ling HU ; Wei LIU ; Xiao TAN
Progress in Biochemistry and Biophysics 2025;52(2):417-424
Serine protease inhibitor Kazal-type (SPINK) is a skin keratinizing protease inhibitor, which was initially found in animal serum and is widely present in plants, animals, bacteria, and viruses, and they act as key regulators of skin keratinizing proteases and are involved in the regulation of keratinocyte proliferation and inflammation, primarily through the inhibition of deregulated tissue kinin-releasing enzymes (KLKs) in skin response. This process plays a crucial role in alleviating various skin problems caused by hyperkeratinization and inflammation, and can greatly improve the overall condition of the skin. Specifically, the different members of the SPINK family, such as SPINK5, SPINK6, SPINK7, and SPINK9, each have unique biological functions and mechanisms of action. The existence of these members demonstrates the diversity and complexity of skin health and disease. First, SPINK5 mutations are closely associated with the development of various skin diseases, such as Netherton’s syndrome and atopic dermatitis, and SPINK5 is able to inhibit the activation of the STAT3 signaling pathway, thereby effectively preventing the metastasis of melanoma cells, which is important in preventing the invasion and migration of malignant tumors. Secondly, SPINK6 is mainly distributed in the epidermis and contains lysine and glutamate residues, which can act as a substrate for epidermal transglutaminase to maintain the normal structure and function of the skin. In addition, SPINK6 can activate the intracellular ERK1/2 and AKT signaling pathways through the activation of epidermal growth factor receptor and protease receptor-2 (EphA2), which can promote the migration of melanoma cells, and SPINK6 further deepens its role in stimulating the migration of malignant tumor cells by inhibiting the activation of STAT3 signaling pathway. This process further deepens its potential impact in stimulating tumor invasive migration. Furthermore, SPINK7 plays a role in the pathology of some inflammatory skin diseases, and is likely to be an important factor contributing to the exacerbation of skin diseases by promoting aberrant proliferation of keratinocytes and local inflammatory responses. Finally, SPINK9 can induce cell migration and promote skin wound healing by activating purinergic receptor 2 (P2R) to induce phosphorylation of epidermal growth factor and further activating the downstream ERK1/2 signaling pathway. In addition, SPINK9 also plays an antimicrobial role, preventing the interference of some pathogenic microorganisms. Taken as a whole, some members of the SPINK family may be potential targets for the treatment of dermatological disorders by regulating multiple biological processes such as keratinization metabolism and immuno-inflammatory processes in the skin. The development of drugs such as small molecule inhibitors and monoclonal antibodies has great potential for the treatment of dermatologic diseases, and future research on SPINK will help to gain a deeper understanding of the physiopathologic processes of the skin. Through its functions and regulatory mechanisms, the formation and maintenance of the skin barrier and the occurrence and development of inflammatory responses can be better understood, which will provide novel ideas and methods for the prevention and treatment of skin diseases.
6.Genetic Correlation and Mendelian Randomization Analysis Revealed an Unidirectional Causal Relationship Between Left Caudal Middle Frontal Surface Area and Cigarette Consumption
Hongcheng XIE ; Anlin WANG ; Minglan YU ; Tingting WANG ; Xuemei LIANG ; Rongfang HE ; Chaohua HUANG ; Wei LEI ; Jing CHEN ; Youguo TAN ; Kezhi LIU ; Bo XIANG
Psychiatry Investigation 2025;22(3):279-286
Objective:
Previous studies have discovered a correlation between cigarette smoking and cortical thickness and surface area, but the causal relationship remains unclear. The objective of this investigation is to scrutinize the causal association between them.
Methods:
To derive summary statistics from a genome-wide association study (GWAS) on cortical thickness, surface area, and four smoking behaviors: 1) age of initiation of regular smoking (AgeSmk); 2) smoking initiation (SmkInit); 3) smoking cessation (SmkCes); 4) cigarettes per day (CigDay). Linkage disequilibrium score regression (LDSC) was employed to examine genetic association analysis. Furthermore, for traits with significant genetic associations, Mendelian randomization (MR) analyses were conducted.
Results:
The LDSC analysis revealed nominal genetic correlations between AgeSmk and right precentral surface area, left caudal anterior cingulate surface area, left cuneus surface area, left inferior parietal surface area, and right caudal anterior cingulate thickness, as well as between CigDay and left caudal middle frontal surface area, between SmkCes and left entorhinal thickness, and between SmkInit and left rostral anterior cingulate surface area, right rostral anterior cingulate thickness, and right superior frontal thickness (rg=-0.36–0.29, p<0.05). MR analysis showed a unidirectional causal association between left caudal middle frontal surface area and CigDay (βIVW=0.056, pBonferroni=2×10-4).
Conclusion
Left caudal middle frontal surface area has the potential to serve as a significant predictor of smoking behavior.
7.Treatment of Asthma by Regulation of Intestinal Flora in Traditional Chinese Medicine Based on "Lung-Intestinal Coordination Therapy"
Wei ZHANG ; Jie SHI ; Xishu TAN ; Yule KOU ; Fei WANG
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(16):307-314
Bronchial asthma (asthma) is a heterogeneous disease characterized by airflow limitation, airway remodeling, and recurrent symptoms such as wheezing, shortness of breath, chest tightness, and cough. Its prevalence is gradually increasing, and a portion of patients are still poorly controlled, leading to a serious social and medical burden. Modern studies have proposed the concept of the "lung-gut axis", which is based on the crosstalk between microorganisms and their metabolites in the lungs and large intestine, and have indicated that microbial dysbiosis in these organs may affect the onset and progression of asthma. Traditional Chinese medicine (TCM) has found the phenomenon of lung-intestinal comorbidity and put forward the importance of "lung-intestinal coordination therapy" in the treatment of lung-related diseases. It has been found that intestinal flora and their metabolites can modulate immune responses through the lung-gut axis, demonstrating great potential for predicting asthma susceptibility, anticipating phenotypes, assessing asthma severity, and guiding treatment. TCM comopunds that embody lung-intestinal coordination therapy, including herbal formulas, single herbs, acupuncture, moxibustion, acupoint application, and spinal pinching therapy, has been shown to regulate intestinal flora, improve metabolism, regulate immunity, alleviate lung inflammation, reduce mucus secretion, inhibit airway remodeling, effectively alleviate symptoms, and delay lung function decline. Based on "lung-intestinal coordination therapy", this paper used intestinal flora as the entry point to summarize the underlying mechanisms of TCM in asthma treatment and highlighted the pivotal role of intestinal flora in asthma, providing a new idea for its clinical treatment through the intestinal flora .
8.Efficacy of Nirmatrelvir tablet/Ritonavir tablet in patients infected with COVID-19 aged 90 years and older
Xueman WEI ; Jingxiang ZHANG ; Tan LIU
Shanghai Journal of Preventive Medicine 2025;37(5):441-445
ObjectiveTo study the effect and efficacy of Nirmatrelvir tablet/Ritonavir tablet in the treatment of patients with COVID‑19 infection aged ≥90 years, to inform pharmacological treatment of patients aged ≥90 years with COVID‑19 infection. MethodsMild to moderate COVID-19 patients who were hospitalized in the Department of Geriatrics of the First Affiliated Hospital of the Naval Medical University from March 2022 to June 2024, aged ≥90 years, and who had not been vaccinated against novel coronavirus were selected as the research subjects. A total of 112 patients who received Nirmatrelvir tablet/Ritonavir tablet antiviral treatment within 5 days after the diagnosis of COVID‑19 infection were referred to the drug group, and 80 patients who were not treated with antiviral drugs were referred to as the control group. A retrospective research method was employed to gather and compare patitents’ clinical laboratory data before and after antiviral treatment, such as blood routine tests, inflammatory markers, coagulation function tests, liver and renal function tests, electrolyte levels, and blood gas analysis, between the drug group and the control group. Additionally, the time duration to negative conversion and 28-day all-cause mortality rates were compared between the two groups. Logistic regression analysis was conducted on factors associated with mortality, such as the oxyhemoglobin saturation after treatment, time duration to negative conversion, and the use of Nirmatrelvir tablet/Ritonavir tablet or not, while correlation analysis was performed to evaluate the efficacy of Nirmatrelvir tablet/Ritonavir tablet based on the level of oxyhemoglobin saturation, time duration to negative conversion, and all-cause mortality rates within 28 days. ResultsAfter treatment, oxyhemoglobin saturation increased in the drug group (t=-2.726, P=0.011), and the differences between the indicators in the control group compared to the pre-treatment period were not statistically significant (all P>0.05). The time to negative conversion and 28-day all-cause mortality of control group were higher than those in the drug group (all P<0.05). Logistic regression analysis revealed that the lower the post-treatment oxyhemoglobin saturation, the lower the use of Nirmatrelvir tablet/Ritonavir tablet, the longer the time to conversion, and the higher the mortality rate of the patients (all P<0.05). Correlation analysis showed that treatment with Nirmatrelvir tablet/Ritonavir tablet resulted in higher oxyhemoglobin saturation (r=0.425, P=0.008), shorter time to negative conversion (r=-0.398, P=0.013), and lower all-cause mortality rates within 28 days (r=-0.370, P=0.022). ConclusionNirmatrelvir tablet/Ritonavir tablet is effective in mild and moderate infection patients aged ≥90 years who have not been vaccinated against COVID‑19 infection, and can increase patients’ oxyhemoglobin saturation, shorten the time to negative conversion, and reduce 28-day all-cause mortality rate.
9.Study on the correlation between the distribution of traditional Chinese medicine syndrome elements and salivary microbiota in patients with pulmonary nodules
Hongxia XIANG ; iawei HE ; Shiyan TAN ; Liting YOU ; Xi FU ; Fengming YOU ; Wei SHI ; Qiong MA ; Yifeng REN
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2025;32(05):608-618
Objective To analyze the differences in distribution of traditional Chinese medicine (TCM) syndrome elements and salivary microbiota between the individuals with pulmonary nodules and those without, and to explore the potential correlation between the distribution of TCM syndrome elements and salivary microbiota in patients with pulmonary nodules. Methods We retrospectively recruited 173 patients with pulmonary nodules (PN) and 40 healthy controls (HC). The four diagnostic information was collected from all participants, and syndrome differentiation method was used to analyze the distribution of TCM syndrome elements in both groups. Saliva samples were obtained from the subjects for 16S rRNA high-throughput sequencing to obtain differential microbiota and to explore the correlation between TCM syndrome elements and salivary microbiota in the evolution of the pulmonary nodule disease. Results The study found that in the PN group, the primary TCM syndrome elements related to disease location were the lung and liver, and the primary TCM syndrome elements related to disease nature were yin deficiency and phlegm. In the HC group, the primary TCM syndrome elements related to disease location were the lung and spleen, and the primary TCM syndrome elements related to disease nature were dampness and qi deficiency. There were differences between the two groups in the distribution of TCM syndrome elements related to disease location (lung, liver, kidney, exterior, heart) and disease nature (yin deficiency, phlegm, qi stagnation, qi deficiency, dampness, blood deficiency, heat, blood stasis) (P<0.05). The species abundance of the salivary microbiota was higher in the PN group than that in the HC group (P<0.05), and there was significant difference in community composition between the two groups (P<0.05). Correlation analysis using multiple methods, including Mantel test network heatmap analysis and Spearman correlation analysis and so on, the results showed that in the PN group, Prevotella and Porphyromonas were positively correlated with disease location in the lung, and Porphyromonas and Granulicatella were positively correlated with disease nature in yin deficiency (P<0.05). Conclusion The study concludes that there are notable differences in the distribution of TCM syndrome elements and the species abundance and composition of salivary microbiota between the patients with pulmonary nodules and the healthy individuals. The distinct external syndrome manifestations in patients with pulmonary nodules, compared to healthy individuals, may be a cascade event triggered by changes in the salivary microbiota. The dual correlation of Porphyromonas with both disease location and nature suggests that changes in its abundance may serve as an objective indicator for the improvement of symptoms in patients with yin deficiency-type pulmonary nodules.
10.Construction and evaluation of a "disease-syndrome combination" prediction model for pulmonary nodules based on oral microbiomics
Yifeng REN ; Shiyan TAN ; Qiong MA ; Qian WANG ; Liting YOU ; Wei SHI ; Chuan ZHENG ; Jiawei HE ; Fengming YOU
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2025;32(08):1105-1114
Objective To construct a "disease-syndrome combination" mathematical representation model for pulmonary nodules based on oral microbiome data, utilizing a multimodal data algorithm framework centered on dynamic systems theory. Furthermore, to compare predictive models under various algorithmic frameworks and validate the efficacy of the optimal model in predicting the presence of pulmonary nodules. Methods A total of 213 subjects were prospectively enrolled from July 2022 to March 2023 at the Hospital of Chengdu University of Traditional Chinese Medicine, Sichuan Cancer Hospital, and the Chengdu Integrated Traditional Chinese and Western Medicine Hospital. This cohort included 173 patients with pulmonary nodules and 40 healthy subjects. A novel multimodal data algorithm framework centered on dynamic systems theory, termed VAEGANTF (Variational Auto Encoder-Generative Adversarial Network-Transformer), was proposed. Subsequently, based on a multi-dimensional integrated dataset of “clinical features-syndrome elements-microorganisms”, all subjects were divided into training (70%) and testing (30%) sets for model construction and efficacy testing, respectively. Using pulmonary nodules as dependent variables, and combining candidate markers such as clinical features, lesion location, disease nature, and microbial genera, the independent variables were screened based on variable importance ranking after identifying and addressing multicollinearity. Missing values were then imputed, and data were standardized. Eight machine learning algorithms were then employed to construct pulmonary nodule risk prediction models: random forest, least absolute shrinkage and selection operator (LASSO) regression, support vector machine, multilayer perceptron, eXtreme Gradient Boosting (XGBoost), VAE-ViT (Vision Transformer), GAN-ViT, and VAEGANTF. K-fold cross-validation was used for model parameter tuning and optimization. The efficacy of the eight predictive models was evaluated using confusion matrices and receiver operating characteristic (ROC) curves, and the optimal model was selected. Finally, goodness-of-fit testing and decision curve analysis (DCA) were performed to evaluate the optimal model. Results There were no statistically significant differences between the two groups in demographic characteristics such as age and sex. The 213 subjects were randomly divided into training and testing sets (7 : 3), and prediction models were constructed using the eight machine learning algorithms. After excluding potential problems such as multicollinearity, a total of 301 clinical feature information, syndrome elements, and microbial genera markers were included for model construction. The area under the curve (AUC) values of the random forest, LASSO regression, support vector machine, multilayer perceptron, and VAE-ViT models did not reach 0.85, indicating poor efficacy. The AUC values of the XGBoost, GAN-ViT, and VAEGANTF models all reached above 0.85, with the VAEGANTF model exhibiting the highest AUC value (AUC=0.923). Goodness-of-fit testing indicated good calibration ability of the VAEGANTF model, and decision curve analysis showed a high degree of clinical benefit. The nomogram results showed that age, sex, heart, lung, Qixu, blood stasis, dampness, Porphyromonas genus, Granulicatella genus, Neisseria genus, Haemophilus genus, and Actinobacillus genus could be used as predictors. Conclusion The “disease-syndrome combination” risk prediction model for pulmonary nodules based on the VAEGANTF algorithm framework, which incorporates multi-dimensional data features of “clinical features-syndrome elements-microorganisms”, demonstrates better performance compared to other machine learning algorithms and has certain reference value for early non-invasive diagnosis of pulmonary nodules.

Result Analysis
Print
Save
E-mail