Background: Lymph node metastasis (LNM) is difficult to precisely predict before surgery in patients with early-T-stage non-small cell lung cancer (NSCLC). This study aimed to develop machine learning (ML)-based predictive models for LNM. Methods: Clinical characteristics and imaging features were retrospectively collected from 1,102 NSCLC ≤ 2 cm patients. A total of 23 variables were included to develop predictive models for LNM by multiple ML algorithms. The models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance and decision curve analysis (DCA) for clinical values. A feature selection approach was used to identify optimal predictive factors. Results: The areas under the ROC curve (AUCs) of the 8 models ranged from 0.784 to 0.899. Some ML-based models performed better than models using conventional statistical methods in both ROC curves and decision curves. The random forest classifier (RFC) model with 9 variables introduced was identified as the best predictive model. The feature selection indicated the top five predictors were tumor size, imaging density, carcinoembryonic antigen (CEA), maximal standardized uptake value (SUV_max), and age. Conclusions: By incorporating clinical characteristics and radiographical features, it is feasible to develop ML-based models for the preoperative prediction of LNM in early-T-stage NSCLC, and the RFC model performed best.

Background: Previous researches had not proposed any prediction models for occult lymph node metastasis (OLNM). Considering the occurrence of OLNM and the importance of OLNM management, we aimed to... Lay abstract Lung cancer was once the leading cause of death among tumors. Today, as routine examination has become more common, the incidence of lung cancers ≤2 cm diameter has been increasing. Mu...

Clinicopathological models for predicting lymph node metastasis in patients with early-stage lung adenocarcinoma: the application of machine learning algorithms Yuming Chong, Yijun Wu, Jianghao Liu, Chang Han, Liang Gong, Xinyu Liu, Naixin Liang, Shanqing Li

Background: Lymph node metastasis (LNM) status is of key importance for the decision-making on treatment and survival prediction. There is no reliable method to precisely evaluate the risk of LNM in NSCLC patients. This study aims to develop and validate a dynamic nomogram to evaluate the risk of LNM in small-size NSCLC. Methods: The NSCLC ≤ 2 cm patients who underwent initial pulmonary surgery were retrospectively reviewed and randomly divided into a training cohort and a validation cohort as a ratio of 7:3. The training cohort was used for the least absolute shrinkage and selection operator (LASSO) regression to select optimal variables. Based on variables selected, the logistic regression models were developed, and were compared by areas under the receiver operating characteristic curve (AUCs) and decision curve analysis (DCA). The optimal model was used to plot a dynamic nomogram for calculating the risk of LNM and was internally and externally well-validated by calibration curves. Results: LNM was observed in 12.0% (83/774) of the training cohort and 10.1% (33/328) of the validation cohort (P = 0.743). The optimal model was used to plot a nomogram with six variables incorporated, including tumor size, carcinoembryonic antigen, imaging density, pathological type (adenocarcinoma or non-adenocarcinoma), lymphovascular invasion, and pleural invasion. The nomogram model showed excellent discrimination (AUC = 0.895 vs. 0.931) and great calibration in both the training and validation cohorts. At the threshold probability of 0–0.8, our nomogram adds more net benefits than the treat-none and treat-all lines in the decision curve. Conclusions: This study firstly developed a cost-efficient dynamic nomogram to precisely and expediently evaluate the risk of LNM in small-size NSCLC and would be helpful for clinicians in decision-making.

Background: Lymph node metastasis (LNM) status is critical to the treatment. Fewer studies has focused on LNM in patients with small-size non-small cell lung cancer (NSCLC). This study aims to investigate clinicopathological characteristics associated with skip N2 (SN2) and non-skip N2 (NSN2) metastasis, and their metastatic patterns in NSCLC with tumor size of 1–2 cm. Methods: We reviewed the records of NSCLC patients with tumor size of 1–2 cm who underwent lobectomy with systematic lymph node dissection (LND) between January 2013 and June 2019. Clinical, radiographical, and pathological characteristics were compared among N1, SN2, and NSN2 groups. Metastatic patterns of mediastinal lymph node were analyzed based on final pathology. Results: A total of 63 NSCLC patients with tumor size of 1–2 cm were staged as pN2, including 25 (39.7%) SN2 and 38 (60.3%) NSN2. The incidence rates of SN2 and NSN2 were 2.8% (25/884) and 4.3% (38/884), respectively. For all clinicopathological characteristics, no significant difference was observed among the groups of N1, SN2, and NSN2. For the tumor located in each lobe, specific nodal drainage stations were identified: 2R/4R for right upper lobe; 2R/4R and subcarinal node (#7) for right middle lobe and right lower lobe; 4L and subaortic node (#5) for left upper lobe; #7 for left lower lobe. However, there were still a few patients (10.9%, 5/46) had the involvement of lower zone for tumors of upper lobe and the involvement of upper zone for lower lobe. Conclusions: SN2 occurs frequently in patients with small-size NSCLC. Whether lobe-specific selective LND is suitable for all small-size patients deserves more studies to confirm. Surgeons should be more careful when performing selective LND for tumors located in the lower and upper lobes.

Background: The therapeutic effect of chemotherapy is still unclear for clinical usage among second primary non‐small cell lung cancer (NSCLC) patients. The aim of this study was to verify the therapeutic effect of chemotherapy and identify the prognostic factors among patients who had received chemotherapy for second primary NSCLC.Methods: A retrospective cohort was constructed based on the Surveillance, Epidemiology and End Results (SEER) database. Through least absolute shrinkage and selection operator regression, univariate Cox and multivariate Cox regression, we identified the prognostic factors among clinicopathological features. Propensity score matching analysis was used to verify the therapeutic effect of chemotherapy. Survival curves were plotted among the subgroups of the selected factors. We further selected clinicopathological features that would affect the prognosis among patients who had received chemotherapy through a similar process.Results: A total of 769 patients were enrolled to verify the therapeutic value of chemotherapy for second primary lung cancer. Significant differences were observed between the chemotherapy and nonchemotherapy group for cancer‐specific survival. 215 patients who had received chemotherapy were analyzed to identify the factors that might influence outcome on the therapeutic effect of chemotherapy. Age, tumor size, histology and treatment were selected as significant factors.Conclusions: The therapeutic effect of chemotherapy for second primary NSCLC was found to be significant. Age, tumor size and histology were significant prognostic factors among patients who had received chemotherapy for second primary NSCLC.Key points: Significant findings of the study A significant therapeutic effect of chemotherapy for second primary non‐small cell lung cancer was proven through univariate Cox regression and propensity score matching analysis. Prognostic factors for second primary non‐small cell lung cancer patients who had received chemotherapy. What this study adds Chemotherapy could be applied in clinical practice as an additional therapeutic method for second primary non‐small cell lung cancer patients. We selected prognostic factors for patients who had received chemotherapy to identify patients who were appropriate for chemotherapy.