Background: Lung cancer is the most common cancer worldwide, both in terms of the incidence and mortality. NDC80 complex comprising of NDC80, NUF2, SPC24, and SPC25 is a heterotetrameric protein complex located in the outer layer of the kinetochore and plays a critical role in mitosis. This study focuses on the effects of NDC80 complex genes on clinical features and prognosis in lung adenocarcinoma (LUAD).

The Knl1-Mis12-Ndc80 (KMN) network genes (including KNL, MIS12 and NDC80 complexes) encode a highly conserved network of protein complexes that act in cell mitosis. In recent years, multiple studies revealed that KMN network genes also play a vital role in tumor appearance and growth. However, the role of the KMN gene network in non-small cell lung cancer (NSCLC) remains unknown. In this study, we analyzed the effects of KMN genes expression and clinical phenotype in patients with lung adenocarcinoma (LUAD). The expression of KMN network genes and related clinical information was extracted from The Cancer Genome Atlas. The samples were classified into cluster I and II by consistent clustering. We analyzed the gene distribution by principal component analysis, and the potential risk characteristics were analyzed using the least absolute shrinkage and selection operator Cox regression algorithm. Univariate and multivariate Cox regression analyses were used to analyze the clinical information. The Database for Annotation, Visualization, and Integrated Discovery, Gene MANIA and gene set enrichment analysis were used to analyze function and correlation among genes of the KMN network. The expression levels of nine out of ten KMN genes were significantly up-regulated in LUAD and were associated with poor overall survival (OS). Higher expression of NDC80 and KNL1 was related to low OS in both univariate and multivariate analyses. According to two independent prognostic KMN network genes (KNL1 and NDC80), a risk signature was established to predict the prognosis of patients with LUAD. Additionally, the genes NDC80 and KNL1 were considerably enriched in pathways associated with signaling pathways, biological processes, and the cell cycle. The results indicate that KMN network genes are intimately related to lung adenocarcinoma. KMN network genes are involved in the malignant process of LUAD. Assessment of NDC80 and KNL1 might be helpful for prognostic stratification and treatment strategy development.

Non-small cell lung carcinoma (NSCLC) is a complex disease, with many different potential gene mutations that drive its formation, occurrence, and development. It is estimated that about 3% of NSCLC patients are accompanied by MET exon 14 skipping (METex14) mutations, and the prognosis of such patients is generally poor, which forms a formidable challenge for us. Savolitinib (Orpathys) is the first highly selective MET inhibitor in China. Here, we presented an NSCLC patient with MET∆ex14 mutation, who was initially uncertain whether existed intrapulmonary metastasis and recently underwent percutaneous coronary intervention for acute myocardial infarction and received savolitinib 600 mg once a day. The tumor was significantly shrunk 6 months later, and no metastatic lesions were found. Eventually, it was determined that the patient was in the early stage of lung cancer. After experts’ consultation and evaluation, the patient accepted radical tumor resection and recovered well. Therefore, savolitinib is an important treatment strategy for NSCLC patients with MET∆ex14 mutation, who was not suitable for surgery. Our experience may provide supporting evidence and guidance for implementing an effective therapeutic strategy for similar cases.

Uncommon atypical mutations account for 10–15% of all epidermal growth factor receptor (EGFR) activating mutations in nonsmall-cell lung cancer (NSCLC). Tumors harboring rare EGFR mutations show highly heterogeneous responses to EGFR tyrosine kinase inhibitors (TKIs). There is insufficient clinical evidence for uncommon types of EGFR mutations, especially those with compound EGFR mutations. In addition, for those with uncommon compound EGFR mutations, few studies have focused on acquired resistance mechanisms and subsequent treatment strategies after disease progression on EGFR-TKIs. Here, a 66-year-old smoking male was diagnosed with lung adenocarcinoma accompanied by pleural metastasis. A rare L833V/H835L compound mutation in exon 21 of EGFR was detected in tumor biopsy by next-generation sequencing. Afatinib was used as first-line therapy and showed favorable efficacy. The patient continued afatinib treatment for a duration of 24 months. A new T790M mutation was detected with a rebiopsy after progression on afatinib. Then the patient received cryoablation therapy and a third-generation EGFR-TKI, furmonertinib. Our case suggests that a comprehensive screening for EGFR mutations should be conducted before and during treatment in clinical practice, and afatinib and furmonertinib could be first- and second-line treatment options in NSCLC patients harboring EGFR L833V/H835L mutations.

Objective: To develop and validate an interpretable machine learning–based model for the early identification of the risk of clinical deterioration during hospitalization in newly diagnosed lung cancer patients. Methods: Clinical data of patients with newly diagnosed lung cancer admitted between July 2023 and December 2025 were retrospectively collected in this single-center study. A hybrid feature selection strategy integrating least absolute shrinkage and selection operator (LASSO) regression and the Boruta algorithm was employed to identify key predictors. Logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) models were constructed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC), calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) values were further applied to interpret the model's decision-making process. Results: A total of 1,001 newly diagnosed lung cancer patients were included, comprising 121 patients (12.1%) in the deterioration group and 880 patients (87.9%) in the non-deterioration group. Through the hybrid feature selection approach, five core predictive variables were identified, including Activities of Daily Living (ADL) score, lymphocyte count, C-reactive protein (CRP), respiratory rate, and neutrophil count. Among the models, the SVM model achieved the highest observed AUC of 0.822 (95% CI: 0.737–0.899) in the internal validation set, with a sensitivity of 0.750 (95% CI: 0.594–0.893) and a specificity of 0.792 (95% CI: 0.740–0.838). After Platt scaling calibration, the model achieved a Brier score of 0.083 (Hosmer-Lemeshow p = 0.649), with a calibration intercept of 0.141 and a slope of 1.126, indicating satisfactory agreement between predicted and observed risks. DCA suggested a potential net clinical benefit. SHAP analysis, in conjunction with multivariable regression results, consistently demonstrated that ADL score and lymphocyte count were associated with reduced risk of clinical deterioration, whereas CRP and neutrophil count were associated with increased risk. Conclusion: The SVM model developed in this study may help identify patients at risk of clinical deterioration among hospitalized lung cancer patients and may assist healthcare professionals in achieving early risk identification and potential clinical decision support.