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. MethodsA 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. ResultsThere 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.
ObjectiveTo investigate the heterogeneity of gut microbiota between patients with solitary pulmonary nodules (SPN) and multiple pulmonary nodules (MPN), and to explore the intrinsic relationship between Traditional Chinese Medicine (TCM) constitution types and the intestinal microecology. MethodsA prospective study was conducted on 280 patients with pulmonary nodules enrolled between April 2022 and December 2024 from Hospital of Chengdu University of Traditional Chinese Medicine, Sichuan Cancer Hospital, Chengdu Integrated Traditional Chinese Medicine & Western Medicine Hospital. Among them, 118 (42.1%) were male and 162 (57.9%) were female, with a median age of 50 (42, 57) years. Based on imaging findings, patients were divided into a SPN group (n=65) and an MPN group (n=215). TCM constitution types were identified using a Constitution in Chinese Medicine Questionnaire. Fecal samples were collected for 16S rRNA sequencing. Bioinformatics analysis was employed to analyze inter-group differences in microbial community structure. The correlation between TCM constitutions and gut microbiota was examined using Procrustes analysis and Spearman correlation analysis. ResultsThe distribution of TCM constitution types between the two groups showed a statistically significant difference (P<0.05). The SPN group was predominantly characterized by the Qi-depression constitution, while the MPN group was more commonly associated with Yang-deficiency and Phlegm-dampness constitutions. Microbiota analysis revealed that the gut microbiota health index was significantly higher in the SPN group than in the MPN group (P<0.05), whereas the microbiota dysbiosis index showed the opposite pattern. Taxonomic analysis identified higher abundances of Ruminococcus_torques_group, Haemophilus, and Fusobacterium in the SPN group. The abundance of Leuconostoc was significantly increased in the MPN group. Procrustes analysis and Spearman correlation analysis indicated that in the SPN group, the Qi-depression constitution was positively correlated with Ruminococcus_torques_group and Bacteroides. In the MPN group, the Yang-deficiency constitution was negatively correlated with Faecalibacterium, while no statistically significant correlations were found between specific bacterial genera and the Phlegm-dampness or Qi-deficiency constitutions. ConclusionSPN and MPN exhibit significant heterogeneity in TCM constitutional tendencies and microecological characteristics. The abundance of specific bacterial genera may serve as potential biomarkers for distinguishing between SPN and MPN. The interaction between TCM constitutions and specific gut microbiota provides a theoretical basis for the precise TCM syndrome differentiation and microecological intervention in pulmonary nodules.
Pulmonary organoids currently represent the most accurate in vitro model for mimicking the structure and function of the human lung, serving as a transformative tool in respiratory research and medical practice. However, their broad application is hindered by several challenges, including limited maturity, lack of standardization, unclear regulatory pathways, high costs, and difficulties in scaling production. This review systematically outlines the current research status and development trends of pulmonary organoids, with emphasis on their value as in vitro models and research platforms for elucidating the biological features and pathophysiological mechanisms of lung diseases. Special attention is given to their emerging role in traditional Chinese medicine (TCM), such as evaluating pharmacological effects of herbal compounds, screening active ingredients, and exploring mechanisms underlying TCM syndrome differentiation and treatment. The aim of this review is to provide comprehensive evidence to support precision diagnosis, drug development, and therapeutic strategies for respiratory diseases.