Objective To evaluate the predictive ability and clinical application value of artificial intelligence (AI) systems in the benign and malignant differentiation and pathological type of pulmonary nodules, and to summarize clinical application experience. Methods A retrospective analysis was conducted on the clinical data of patients with pulmonary nodules admitted to the Department of Thoracic Surgery, Second Hospital of Lanzhou University, from February 2016 to February 2025. Firstly, pulmonary nodules were divided into benign and non-benign groups, and the discriminative abilities of AI systems and clinicians were compared. Subsequently, lung nodules reported as precursor glandular lesions (PGL), microinvasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) in postoperative pathological results were analyzed, comparing the efficacy of AI systems and clinicians in predicting the pathological type of pulmonary nodules. Results In the analysis of benign/non-benign pulmonary nodules, clinical data from a total of 638 patients with pulmonary nodules were included, of which there were 257 males (10 patients and 1 patient of double and triple primary lesions, respectively) and 381 females (18 patients and 1 patient of double and triple primary lesions, respectively), with a median age of 55.0 (47.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis of the two groups of variables showed that, except for nodule location, the differences in the remaining variables were statistically significant (P<0.05). Multivariate logistic regression analysis showed that age, nodule type (subsolid pulmonary nodule), average density, spicule sign, and vascular convergence sign were independent influencing factors for non-benign pulmonary nodules, among which age, nodule type (subsolid pulmonary nodule), spicule sign, and vascular convergence sign were positively correlated with non-benign pulmonary nodules, while average density was negatively correlated with the occurrence of non-benign pulmonary nodules. The area under the receiver operating characteristic curve (AUC) of the malignancy risk value given by the AI system in predicting non-benign pulmonary nodules was 0.811, slightly lower than the 0.898 predicted by clinicians. In the PGL/MIA/IAC analysis, clinical data from a total of 411 patients with pulmonary nodules were included, of which there were 149 males (8 patients of double primary lesions) and 262 females (17 patients of double primary lesions), with a median age of 56.0 (50.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis results showed that, except for gender, nodule location, and vascular convergence sign, the differences in the remaining variables among the three groups of PGL, MIA, and IAC patients were statistically significant (P<0.05). Multinomial multivariate logistic regression analysis showed that the differences between the parameters in the PGL group and the MIA group were not statistically significant (P>0.05), and the maximum diameter and average density of the nodules were statistically different between the PGL and IAC groups (P<0.05), and were positively correlated with the occurrence of IAC as independent risk factors. The average AUC value, accuracy, recall rate, and F1 score of the AI system in predicting lung nodule pathological type were 0.807, 74.3%, 73.2%, and 68.5%, respectively, all better than the clinical physicians’ prediction of lung nodule pathological type indicators (0.782, 70.9%, 66.2%, and 63.7% respectively). The AUC value of the AI system in predicting IAC was 0.853, and the sensitivity, specificity, and optimal cutoff value were 0.643, 0.943, and 50.0%, respectively. Conclusion This AI system has demonstrated high clinical value in predicting the benign and malignant nature and pathological type of lung nodules, especially in predicting lung nodule pathological type, its ability has surpassed that of clinical physicians. With the optimization of algorithms and the adequate integration of multimodal data, it can better assist clinical physicians in formulating individualized diagnostic and treatment plans for patients with lung nodules.

BACKGROUND: Lung cancer is one of the most common malignant tumors worldwide and a major cause of cancer-related deaths. Early-stage lung cancer is often manifested as pulmonary nodules, and accurate assessment of the malignancy risk is crucial for prolonging survival and avoiding overtreatment. This study aims to construct a model based on image feature parameters automatically extracted by artificial intelligence (AI) to evaluate its effectiveness in predicting the malignancy of part-solid nodule (PSN). METHODS: This retrospective study analyzed 229 PSN from 222 patients who underwent pulmonary nodule resection at Lanzhou University Second Hospital between October 2020 and February 2025. According to pathological results, 45 cases of benign lesions and precursor glandular lesion were categorized into the non-malignant group, and 184 cases of pulmonary malignancies were categorized into the malignant group. All patients underwent preoperative chest computed tomography (CT), and AI software was used to extract imaging feature parameters. Univariate analysis was used to screen significant variables; variance inflation factor (VIF) was calculated to exclude highly collinear variables, and LASSO regression was further applied to identify key features. Multivariate Logistic regression was used to determine independent risk factors. Based on the selected variables, five models were constructed: Logistic regression, random forest, XGBoost, LightGBM, and support vector machine (SVM). Receiver operating characteristic (ROC) curves were used to assess the performance of the models. RESULTS: The independent risk factors for the malignancy of PSN include roughness (ngtdm), dependence variance (gldm), and short run low gray-level emphasis (glrlm). Logistic regression achieved area under the curves ( AUCs) of 0.86 and 0.89 in the training and testing sets, respectively, showing good performance. XGBoost had AUCs of 0.78 and 0.77, respectively, demonstrating relatively balanced performance, but with lower accuracy. SVM showed an AUC of 0.93 in the training set, which decreased to 0.80 in the testing set, indicating overfitting. LightGBM performed excellently in the training set with an AUC of 0.94, but its performance declined in the testing set, with an AUC of 0.88. In contrast, random forest demonstrated stable performance in both the training and testing sets, with AUCs of 0.89 and 0.91, respectively, exhibiting high stability and excellent generalizability. CONCLUSIONS The random forest model constructed based on independent risk factors demonstrated the best performance in predicting the malignancy of PSN and could provide effective auxiliary predictions for clinicians, supporting individualized treatment decisions.
.
Humans ; Male ; Female ; Lung Neoplasms/pathology* ; Middle Aged ; Retrospective Studies ; Artificial Intelligence ; Aged ; Tomography, X-Ray Computed ; Adult ; Solitary Pulmonary Nodule/diagnostic imaging* ; ROC Curve

We reported a 32 years female patient in whom lung metastasis from breast cancer was presented as solitary pulmonary pure ground-glass opacity (GGO) lesion. The patient received rational preoperative examinations and surgery though the preoperative diagnosis was not accurate. Because of different therapy strategies and purposes, it is crucial to make distinction of atypical metastases from primary cancers. Thus, for patients with a history of malignancy, possible metastasis should be taken into consideration if new GGO was found on the CT. Besides this, the follow-up interval of CT should be shortened appropriately, preoperative examinations and surgical procedures should be made according to the suggestions of multidisciplinary team.

Objective    To compare the surgical efficacy of Da Vinci robot-assisted minimally invasive esophagectomy (RAMIE) and video-assisted minimally invasive esophagectomy (VAMIE) on esophageal cancer. Methods    Online databases including PubMed, the Cochrane Library, Medline, EMbase and CNKI from inception to 31, December 2019 were searched by two researchers independently to collect the literature comparing the clinical efficacy of RAMIE and VAMIE on esophageal cancer. Newcastle-Ottawa Scale was used to assess quality of the literature. The meta-analysis was performed by RevMan 5.3. Results    A total of 14 studies with 1 160 patients were enrolled in the final study, and 12 studies were of high quality. RAMIE did not significantly prolong total operative time (P=0.20). No statistical difference was observed in the thoracic surgical time through the McKeown surgical approach (MD=3.35, 95%CI –3.93 to 10.62, P=0.37) or in surgical blood loss between RAMIE and VAMIE (MD=–9.48, 95%CI –27.91 to 8.95, P=0.31). While the RAMIE could dissect more lymph nodes in total and more lymph nodes along the left recurrent laryngeal recurrent nerve (MD=2.24, 95%CI 1.09 to 3.39, P=0.000 1; MD=0.89, 95%CI 0.13 to 1.65, P=0.02) and had a lower incidence of vocal cord paralysis (RR=0.70, 95%CI 0.53 to 0.92, P=0.009). Conclusion    There is no statistical difference observed between RAMIE and VAMIE in surgical time and blood loss. RAMIE can harvest more lymph nodes than VAMIE, especially left laryngeal nerve lymph nodes. RAMIE shows a better performance in reducing the left laryngeal nerve injury and a lower rate of vocal cord paralysis compared with VAMIE.

BACKGROUND: Lung cancer is the cancer with the highest mortality at home and abroad at present. The detection of lung nodules is a key step to reducing the mortality of lung cancer. Artificial intelligence-assisted diagnosis system presents as the state of the art in the area of nodule detection, differentiation between benign and malignant and diagnosis of invasive subtypes, however, a validation with clinical data is necessary for further application. Therefore, the aim of this study is to evaluate the effectiveness of artificial intelligence-assisted diagnosis system in predicting the invasive subtypes of early‑stage lung adenocarcinoma appearing as pulmonary nodules. METHODS: Clinical data of 223 patients with early-stage lung adenocarcinoma appearing as pulmonary nodules admitted to the Lanzhou University Second Hospital from January 1st, 2016 to December 31th, 2021 were retrospectively analyzed, which were divided into invasive adenocarcinoma group (n=170) and non-invasive adenocarcinoma group (n=53), and the non-invasive adenocarcinoma group was subdivided into minimally invasive adenocarcinoma group (n=31) and preinvasive lesions group (n=22). The malignant probability and imaging characteristics of each group were compared to analyze their predictive ability for the invasive subtypes of early-stage lung adenocarcinoma. The concordance between qualitative diagnostic results of artificial intelligence-assisted diagnosis of the invasive subtypes of early-stage lung adenocarcinoma and postoperative pathology was then analyzed. RESULTS: In different invasive subtypes of early-stage lung adenocarcinoma, the mean CT value of pulmonary nodules (P<0.001), diameter (P<0.001), volume (P<0.001), malignant probability (P<0.001), pleural retraction sign (P<0.001), lobulation (P<0.001), spiculation (P<0.001) were significantly different. At the same time, it was also found that with the increased invasiveness of different invasive subtypes of early-stage lung adenocarcinoma, the proportion of dominant signs of each group gradually increased. On the issue of binary classification, the sensitivity, specificity, and area under the curve (AUC) values of the artificial intelligence-assisted diagnosis system for the qualitative diagnosis of invasive subtypes of early-stage lung adenocarcinoma were 81.76%, 92.45% and 0.871 respectively. On the issue of three classification, the accuracy, recall rate, F1 score, and AUC values of the artificial intelligence-assisted diagnosis system for the qualitative diagnosis of invasive subtypes of early-stage lung adenocarcinoma were 83.86%, 85.03%, 76.46% and 0.879 respectively. CONCLUSIONS Artificial intelligence-assisted diagnosis system could predict the invasive subtypes of early‑stage lung adenocarcinoma appearing as pulmonary nodules, and has a certain predictive value. With the optimization of algorithms and the improvement of data, it may provide guidance for individualized treatment of patients.
Adenocarcinoma/pathology* ; Adenocarcinoma of Lung/pathology* ; Artificial Intelligence ; Humans ; Lung Neoplasms/pathology* ; Multiple Pulmonary Nodules ; Neoplasm Invasiveness ; Retrospective Studies

The incidence of rib fracture in patients with chest trauma is about 70%. Simple rib fractures do not need special treatment. Multiple rib fractures and flail chest are critical cases of blunt trauma, which often cause serious clinical consequences and need to be treated cautiously. Nowadays, there is a controversy about the diagnosis and treatment of multiple rib fractures and flail chest. In the past, most of the patients were treated by non-operative treatment, and only less than 1% of the patients with flail chest underwent surgery. In recent years, studies have confirmed that surgical reduction and internal fixation can shorten the hospital stay, and reduce pain and cost for patients with flail chest, but there is still a lack of relevant clinical consensus and guidelines for diagnosis and treatment, which leads to great differences in clinical diagnosis and treatment plans. This article reviewed the treatment, surgical indications and surgical timing of multiple rib fractures and flail chest.

Objective    To investigate the prognostic survival status and influence factors for surgical treatment of esophageal squamous cell carcinoma (ESCC) in pathological stage T1b (pT1b). Methods    The patients with ESCC in pT1b undergoing Ivor-Lewis or McKeown esophagectomy in Lanzhou University Second Hospital from 2012 to 2015 were collected, including 78 males (78.3%) and 17 females (21.7%) with an average age of 61.4±7.4 years. Results    The most common postoperative complications were pneumonia (15.8%), anastomotic leakage (12.6%) and arrhythmia (8.4%). Ninety-three (97.9%) patients underwent R0 resection, with an average number of lymph node dissections of 14.4±5.6. The rate of lymph node metastasis was 22.1%, and the incidence of lymph vessel invasion was 13.7%. The median follow-up time was 60.4 months, during which 25 patients died and 27 patients relapsed. The overall survival rate at 3 years was 86.3%, and at 5 years was 72.7%. Multivariate Cox regression analysis showed that lymph node metastasis (P=0.012, HR=2.60, 95%CI 1.23-5.50) and lympovascular invasion (P=0.014, HR=2.73, 95%CI 1.22-6.09) were independent risk factors for overall survival of pT1b ESCC. Conclusion    Esophagectomy via right chest approach combined with two-fields lymphadenectomy is safe and feasible for patients with pT1b ESCC. The progress of pT1b ESCC with lymph node metastasis or lymphovascular invasion is relatively poor.

Objective To explore the research state and topics of lung cancer with chronic obstructive pulmonary disease (COPD) in China using the visualization methods. Methods Literature about lung cancer with COPD was searched through WanFang, CNKI, CBM, PubMed, The Cochrane Library and EMbase databases from inception to March 2018 by computer. We used BICOMS software to analyze the main information and produce co-word matrix, gCLUTO software to cluster, and NetDraw and Cytoscape software to draw the pictures. Results There were 304 studies related to lung cancer with COPD which originated from 173 journals including 23 indexed by Chinese Science Citation Database (CSCD) with 42 articles published, accounting for 13.8% of the total number of studies. There were 37 articles from 24 journals indexed by Science Citation Index (SCI) accounting for 12.2% of the total number of studies. The studies grew rapidly since 2012. The study involved 32 provinces, municipalities, and autonomous regions, among which Beijing, Sichuan, Shanghai, Guangzhou and Jiangsu provinces and cities were the main research areas. Sixty-nine high-frequency keywords were obtained with frequency 2 as the threshold, which was clustered into 5 categories by dual cluster analysis. Among them, topic 0 showed pathogenesis and radiological diagnosis of lung cancer with COPD, topic 1 was about the clinical characteristics of different pathological types of lung cancer with COPD and Chinese medicine treatment, topic 2 aimed at the impact of risk factors on surgical complications and the relationship between chemotherapy or targeted therapies and patient survival prognosis, topic 3 involved the pigenetic correlation between lung cancer and COPD and topic 4 was about clinical studies of perioperative comprehensive management of lung cancer patients with COPD. Conclusion The bibliometrics results show that there are considerable-amount achievements on lung cancer combined with COPD in China, and the researches have gradually increased since 2012. Horizontal research topics are extensive, and the focus of the study is to explore the perioperative comprehensive management and basic research of lung cancer with COPD, but the longitudinal themes need to be further studied. The results of some studies have not yet reached a consensus. There are few high-quality multi-center studies and a lack of clinical-directed achievement.

Objective To observe the growth of xenografted tumor in nude mice after DDX46 expression decreased, and to further study the role of DDX46 in the development and progression of esophageal squamous cell carcinoma. Methods DDX46-shRNA mediated RNAi was applied to silencing DDX46 in Eca-109 cells. Twenty-five female BALB/c nude mice were divided into 3 groups: an experiment group (DDX46-shRNA-LV, n=10), a control group (Control-LV, n=10) and a blank control group (Het-1A, n=5). The prepared Eca-109 cells of DDX46-shRNA-LV and Control-LV were subcutaneously injected into the right armpit of mice (4×106 cells per mouse), while Het-1A cells were subcutaneously injected into the bilateral armpits of mice (4×106 cells per side). Tumor growth was monitored twice a week on the 14th day after injection. Tumor volume was measured with calipers, in vivo imager to observe the fluorescence of each group. Further, western blotting analysis was used to detect the changes of apoptosis signaling molecules in xenografted tumor after DDX46 silence. Results The growth of xenografted tumor in nude mice was significantly slower in the DDX46-shRNA-LV group than that in the Control-LV group throughout the study period (P<0.001). Western blotting analysis showed that silencing DDX46 effectively suppressed the expression of DDX46, and upregulated the expression of cleaved Caspase-3 and cleaved PARP-1 in xenografted tumor (P<0.01). Conclusion DDX46 is involved in the development and progression of esophageal squamous cell carcinoma, and the silence of DDX46 expression can inhibit the growth of esophageal squamous cell carcinoma, which probably by positive regulation of apoptosis signaling pathway.