ObjectiveTo explore the accuracy of machine learning algorithms based on SHOX2 and RASSF1A methylation levels in predicting early-stage lung adenocarcinoma pathological types. MethodsA retrospective analysis was conducted on formalin-fixed paraffin-embedded (FFPE) specimens from patients who underwent lung tumor resection surgery at Affiliated Hospital of Nantong University from January 2021 to January 2023. Based on the pathological classification of the tumors, patients were divided into three groups: a benign tumor/adenocarcinoma in situ (BT/AIS) group, a minimally invasive adenocarcinoma (MIA) group, and an invasive adenocarcinoma (IA) group. The methylation levels of SHOX2 and RASSF1A in FFPE specimens were measured using the LungMe kit through methylation-specific PCR (MS-PCR). Using the methylation levels of SHOX2 and RASSF1A as predictive variables, various machine learning algorithms (including logistic regression, XGBoost, random forest, and naive Bayes) were employed to predict different lung adenocarcinoma pathological types. ResultsA total of 272 patients were included. The average ages of patients in the BT/AIS, MIA, and IA groups were 57.97, 61.31, and 63.84 years, respectively. The proportions of female patients were 55.38%, 61.11%, and 61.36%, respectively. In the early-stage lung adenocarcinoma prediction model established based on SHOX2 and RASSF1A methylation levels, the random forest and XGBoost models performed well in predicting each pathological type. The C-statistics of the random forest model for the BT/AIS, MIA, and IA groups were 0.71, 0.72, and 0.78, respectively. The C-statistics of the XGBoost model for the BT/AIS, MIA, and IA groups were 0.70, 0.75, and 0.77, respectively. The naive Bayes model only showed robust performance in the IA group, with a C-statistic of 0.73, indicating some predictive ability. The logistic regression model performed the worst among all groups, showing no predictive ability for any group. Through decision curve analysis, the random forest model demonstrated higher net benefit in predicting BT/AIS and MIA pathological types, indicating its potential value in clinical application. ConclusionMachine learning algorithms based on SHOX2 and RASSF1A methylation levels have high accuracy in predicting early-stage lung adenocarcinoma pathological types.
Objective To investigate the effects of tobacco smoke exposure on histone deacetylase 2 (HDAC2),interleukin-8(IL-8)and tumor necrosis factor-α(TNF-α)expression in peripheral blood of patients with lung adenocarcinoma and analyze the relationships among them. Methods Seventy-three cases diagnosed as lung adenocarcinoma were collected in the First Affiliated Hospital and Affiliated Tumor Hospital of Guangxi Medical University from April 2014 to March 2015.All patients underwent lung function test preoperatively.Fourteen healthy volunteers without tobacco smoke exposure and chronic obstructive pulmonary disease (COPD)were recruited as healthy control.According to the lung function and tobacco smoke exposure,all cases were divided into four groups,ie. a healthy control group (group A,14 cases),a group without tobacco smoke exposure and COPD(group B,19 cases),a group with tobacco smoke exposure and without COPD(group C,33 cases),and a group with tobacco smoke exposure and COPD(group D,21 cases).The expressions of HDAC2 mRNA,IL-8 mRNA and TNF-α mRNA in peripheral blood mononuclear cells (PBMCs)were detected by real-time polymerase chain reaction (PCR).The contents of IL-8 and TNF-α in serum were detected by ELISA. Results Compared with group A,the HDAC2 mRNA expression in PBMCs had no difference in group B(P>0.05),and was down-regulated significantly in group C and D (P<0.05),which in group D was the most obvious.Compared with group A,the expressions of IL-8 mRNA and TNF-α mRNA in PBMCs and the contents of IL-8 and TNF-α in serum were significantly higher in all lung adenocarcinoma patients(all P<0.05),and the up-regulation was more obvious in group D.The relative expression of HDAC2 mRNA in PBMCs showed no significant difference with respect to age,gender or TNM stage (P>0.05).IL-8 and TNF-α in PBMCs and serum showed no significant difference with respect to age and gender (P>0.05),and were higher in the patients with TNM stage Ⅲ lung adenocarcinoma than those with stage Ⅰ and Ⅱ(P<0.05),with no obvious difference between stage Ⅰ and stage Ⅱ (P>0.05). Conclusion Tobacco smoke exposure causes lower expression of HDAC2 and over-expression of IL-8 and TNF-α in peripheral blood of patients with lung adenocarcinoma,can aggravate inflammatory response especially when complicated with COPD,which may be related to the prognosis of lung adenocarcinoma.
Objective To select relatively specific biomarkers in serum from lung adenocarcinoma patients using surface-enhanced laser desorption ionization time of flight mass spectrometry （SELDI-TOF-MS） Protein Chip technology, and study the follow-up results of postoperative serum proteomic patterns. Methods Serum samples from 71 lung adenocarcinoma patients. 71 healthy volunteers with matched gender, age and history of smoking were analyzed by using weak cation exchange 2（WCX2） Protein Chip to select potentially biomarkers. Seventy-one patients were followed-up till 9 months after surgery. Compare the serum proteomic patterns 3,6 and 9 months after surgery. Results Five highly expressed potential biomarkers were identified with the relative molecular weights of 4 047.79, 4 203. 99, 4 959. 81, 5 329. 30 and 7 760. 12 Da. The postoperative serum proteomic patterns changed among individuals, and correlated with patients＇ clinical stage. Conclusions SELDI-TOF-MS Protein Chip technology is a quick, easy, convenient, and high-throughout analyzing method capable of selecting relatively specific, potential biomarkers from the serum of lung adenocarcinoma patients and may have attractive clinical value.
[Abstract]High-grade histologic subtypes of lung adenocarcinoma, such as micropapillary and solid patterns, are characterized by high invasiveness, increased risk of recurrence, and poor prognosis. Early preoperative identification of these subtypes is crucial for achieving individualized treatment and improving clinical outcomes. This review summarizes the clinical features, imaging manifestations, molecular mechanisms, and diagnostic advances related to these aggressive patterns. Studies have shown that micropapillary and solid subtypes are more common in male smokers, often present as solid nodules, and demonstrate strong predictive value in FDG-PET metabolic parameters and CT-based radiomics models. At the molecular level, EGFR mutations are more frequently observed in micropapillary types, whereas solid subtypes are often associated with high PD-L1 expression and TP53 mutations, indicating distinct therapeutic strategies for targeted and immunotherapies. In addition, serum markers such as CEA and CYFRA21-1, along with inflammatory indices like NLR and SII, may serve as auxiliary tools for subtype identification. Histologic subtypes of lung adenocarcinoma are evolving from descriptive classifications into critical determinants of treatment decisions and precision management. Clinicians should incorporate comprehensive histologic evaluation into individualized therapeutic planning. Multimodal integration technologies, combined with artificial intelligence algorithms, are advancing the accurate preoperative prediction and management of high-risk subtypes, thereby facilitating early diagnosis and stratified treatment of lung adenocarcinoma.
Objective To explore the correlation between lymph node metastasis and clinicopathological features of lung adenocarcinoma with diameter≤3 cm. Methods The clinicopathologic data of the patients with lung adenocarcinoma≤3 cm in diameter were retrospectively analyzed. The relationship between lymph node metastasis and age, gender, smoking history, pathological subtype, tumor location, tumor diameter, pleural invasion, vascular invasion and other factors was analyzed. The risk factors of lymph node metastasis were analyzed by univariate and multivariate logistic regression. Results Finally 1 718 patients were collected, including 697 males and 1 021 females with an average age of 58.89±9.85 years. The total lymph node metastasis rate was 12.9%, among whom 452 patients of adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) did not have lymph node metastasis, and the lymph node metastasis rate of invasive lung adenocarcinoma was 17.5%. Multivariate analysis showed that tumor diameter, micropapillary subtype, solid subtype, micropapillary component, solid component, vascular invasion and pleural invasion were independent risk factors for lymph node metastasis of invasive lung adenocarcinoma with diameter≤3 cm (P<0.05). While age, lepidic subtype and lepidic component were independent protective factors for lymph node metastasis (P<0.05). Conclusion Clinicopathological features can help predict lymph node metastasis of lung adenocarcinoma with diameter≤3 cm.
ObjectiveTo investigate the effect of different lymph node dissection methods on the prognosis of patients with stage ⅠA spread through air space (STAS)-positive lung adenocarcinoma≤ 2 cm. MethodsClinical data of 3148 patients with lung adenocarcinoma who underwent surgery at the Department of Thoracic Surgery, the First Affiliated Hospital of University of Science and Technology of China from 2016 to 2018 were retrospectively analyzed. Patients with stage ⅠA STAS-positive lung adenocarcinoma≤ 2 cm were included and divided into two groups based on lymph node dissection methods: systematic lymph node dissection group and limited lymph node dissection group. Compare the clinical and pathological data of two groups of patients and use Cox proportional hazards regression model for multivariate survival analysis. ResultsA total of 209 STAS-positive patients were enrolled in the study, including 98 males and 111 females, aged 28-83 (60.42±10.15) years. Univariate analysis showed that the mode of lymph node dissection, past history, micropapillary histological subtype, and papillary histological subtype were risk factors for patient prognosis. Multifactorial analysis showed that lymph node dissection method, age, and micropapillary histological subtype were risk factors for patient prognosis. Meanwhile, among STAS-positive patients, systematic lymph node dissection had a better prognosis than limited lymph node dissection patients. ConclusionSTAS plays an important role in patient prognosis as an independent risk factor for prognosis of stage ⅠA ≤2 cm lung adenocarcinoma. When STAS is positive, the choice of systematic lymph node dissection may be more favourable to patients' long-term prognosis.
Objective To explore the role of cyclin B1 (CCNB1), cyclin B2 (CCNB2) and cyclin dependent kinase 1 (CDK1) in lung adenocarcinoma (LUAD) using bioinformatic data. Methods First, RNA expression data were downloaded from two datasets in Gene Expression Omnibus (GEO), and DESeq2 software was used to identify deferentially expressed genes (DEGs). Subsequent analyses were conducted based on the results of these DEGs: protein-protein interaction (PPI) network was constructed with STRING database; the modules in PPI network were analyzed by Molecular Complex Detection software, and the most significant modules were selected, the genes included in these modules were the hub genes; high-throughput RNA sequencing data from other databases were used to verify the expression of these hub genes to confirm whether they were DEGs; survival curve analyses of the confirmed DEGs were conducted to select genes that had significant influence on the survival of LUAD; the expression of these hub genes in different stages of LUAD were also analyzed. Then, Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis was performed for these selected hub genes using KOBAS database. MuTarget tool was used to analyze the correlations between the expression of these selected hub genes and gene mutation status in LUAD. The potential value of these hub genes in the treatment of LUAD was explored based on the drug information in GDSC database. Finally, immunohistochemical data from Human Protein Atlas (HPA) database were used to verify the expression of these hub genes in LUAD again. Results According to the expression data in GEO, 594 up-regulated genes and 651 down-regulated genes were identified (P<0.05), among which 30 hub genes were selected for subsequent analyses. The RNA high-throughput sequencing data of other databases verified that 18 genes were DEGs, among which 8 hub genes had significant impact on disease-free survival in LUAD (P<0.05). Moreover, the 8 genes were differentially expressed in different stages of LUAD, which were higher in the middle and late stage of LUAD. Among the 8 genes. CCNB1, CCNB2 and CDK1 were significantly enriched in the cell cycle pathway. The expression of CCNB1, CCNB2 and CDK1 in LUAD was closely related to the TP53 mutation status. In addition, CDK1 was associated with four drugs, revealing the potential value of CDK1 in the treatment of LUAD. Finally, immunohistochemical data from HPA database verified that CCNB1, CCNB2 and CDK1 were highly expressed in LUAD in the protein level. Conclusion Overexpression of CCNB1, CCNB2 and CDK1 are associated with poor prognosis of LUAD, indicating that the three genes may be prognostic biomarkers of LUAD and CDK1 is a potential therapeutic target for LUAD.
Lung cancer is one of the malignant tumors with the greatest threat to human health, and studies have shown that some genes play an important regulatory role in the occurrence and development of lung cancer. In this paper, a LightGBM ensemble learning method is proposed to construct a prognostic model based on immune relate gene (IRG) profile data and clinical data to predict the prognostic survival rate of lung adenocarcinoma patients. First, this method used the Limma package for differential gene expression, used CoxPH regression analysis to screen the IRG to prognosis, and then used XGBoost algorithm to score the importance of the IRG features. Finally, the LASSO regression analysis was used to select IRG that could be used to construct a prognostic model, and a total of 17 IRG features were obtained that could be used to construct model. LightGBM was trained according to the IRG screened. The K-means algorithm was used to divide the patients into three groups, and the area under curve (AUC) of receiver operating characteristic (ROC) of the model output showed that the accuracy of the model in predicting the survival rates of the three groups of patients was 96%, 98% and 96%, respectively. The experimental results show that the model proposed in this paper can divide patients with lung adenocarcinoma into three groups [5-year survival rate higher than 65% (group 1), lower than 65% but higher than 30% (group 2) and lower than 30% (group 3)] and can accurately predict the 5-year survival rate of lung adenocarcinoma patients.
Lung adenocarcinoma is a prevalent histological subtype of non-small cell lung cancer with different morphologic and molecular features that are critical for prognosis and treatment planning. In recent years, with the development of artificial intelligence technology, its application in the study of pathological subtypes and gene expression of lung adenocarcinoma has gained widespread attention. This paper reviews the research progress of machine learning and deep learning in pathological subtypes classification and gene expression analysis of lung adenocarcinoma, and some problems and challenges at the present stage are summarized and the future directions of artificial intelligence in lung adenocarcinoma research are foreseen.
ObjectiveTo investigate the risk factors for lymph node metastasis in resectable lung adenocarcinoma by combining spatial location, clinical, and imaging features, and to construct a lymph node metastasis prediction model. MethodsA retrospective study on patients who underwent chest computed tomography (CT) at the First Affiliated Hospital of Nanjing Medical University from June 2016 to June 2020 and were surgically confirmed to have invasive lung adenocarcinoma with or without lymph node metastasis was conducted. Patients were divided into a positive group and a negative group based on the presence or absence of lymph node metastasis. Clinical and imaging data of the patients were collected, and the independent risk factors for lymph node metastasis in resectable lung adenocarcinoma were analyzed using univariate and multivariate logistic regression. A combined spatial location-clinical-imaging feature prediction model for lymph node metastasis was established and compared with the traditional lymph node metastasis prediction model that does not include spatial location features. ResultsA total of 611 patients were included, with 333 in the positive group, including 172 males and 161 females, with an average age of (58.9±9.7) years; and 278 in the negative group, including 127 males and 151 females, with an average age of (60.1±11.4) years. Univariate and multivariate logistic regression analyses showed that the spatial relationship of the lesion to the lung hilum, nodule type, pleural changes, and serum carcinoembryonic antigen (CEA) levels were independent risk factors for lymph node metastasis. Based on this, the combined spatial location-clinical-imaging feature prediction model had a sensitivity of 91.67%, specificity of 74.05%, accuracy of 87.88%, and area under the curve (AUC) of 0.885. The traditional lymph node metastasis prediction model, which did not include spatial location features, had a sensitivity of 76.40%, specificity of 72.10%, accuracy of 53.86%, and AUC of 0.827. The difference in AUC between the two prediction methods was statistically significant (P=0.026). Compared with the traditional prediction model, the predictive performance of the combined spatial location-clinical-imaging feature prediction model was significantly improved. ConclusionIn patients with resectable lung adenocarcinoma, those with basal spatial location, solid density, pleural changes with wide base depression, and elevated serum CEA levels have a higher risk of lymph node metastasis.