A nomogram to predict prognosis of patients with lung adenosquamous carcinoma: a population-based study

Integrative prognostic modeling for stage III lung adenosquamous carcinoma post-tumor resection: machine learning insights and web-based implementation

Introduction

The prognostic landscape of stage III Lung Adenosquamous Carcinoma (ASC) following primary tumor resection remains underexplored. A thoughtfully developed prognostic model has the potential to guide clinicians in patient counseling and the formulation of effective therapeutic strategies.

Methods

Utilizing data from the Surveillance, Epidemiology, and End Results database spanning 2000 to 2018, this study identified independent prognostic factors influencing Overall Survival (OS) in ASC using Boruta analysis. Employing Gradient Boosting, Random Forest, and Neural Network algorithms, predictive models were constructed. Model performance was assessed through key metrics, including Area Under the Receiver Operating Characteristic Curve (AUC), calibration plot, Brier score, and Decision Curve Analysis (DCA).

Results

Among 241 eligible patients, seven clinical parameters-age, sex, primary tumor size, N stage, primary tumor site, chemotherapy, and systemic therapy-were identified as significant predictors of OS. Advanced age, male gender, larger tumor size, absence of chemotherapy, and lack of systemic therapy were associated with poorer survival. The Random Forest model outperformed others, achieving 3- and 5-year AUCs of 0.80/0.79 (training) and 0.74/0.65 (validation). It also demonstrated better calibration, lower Brier scores (training: 0.189/0.171; validation: 0.207/0.199), and more favorable DCA. SHAP values enhanced model interpretability by highlighting the impact of each parameter on survival predictions. To facilitate clinical application, the Random Forest model was deployed on a web-based server for accessible prognostic assessments.

Conclusions

This study presents a robust machine learning model and a web-based tool that assist healthcare practitioners in personalized clinical decision-making and treatment optimization for ASC patients following primary tumor resection.

Characterization of Infiltrating Immune Cells and Secretory or Membrane-Associated Proteins in KRAS Lung Adenocarcinoma

Background

This study identified the expression and prognosis significance of secretory or membrane-associated proteins in KRAS lung adenocarcinoma (LUAD) and depicted the characteristics between the immune cell infiltration and the expression of these genes.

Methods

Gene expression data of LUAD samples (n = 563) were accessed from The Cancer Genome Atlas (TCGA). The expression of secretory or membrane-associated proteins was compared among the KRAS-mutant, wild-type, and normal groups, as well as the subgroup of the KRAS-mutant group. We identified the survival-related differentially expressed secretory or membrane-associated proteins and conducted the functional enrichment analysis. Then, the characterization and association between their expression and the 24 immune cell subsets were investigated. We also constructed a scoring model to predict KRAS mutation by LASSO and logistic regression analysis.

Results

Secretory or membrane-associated genes with differential expression (n = 74) across three groups (137 KRAS LUAD, 368 wild-type LUAD, and 58 normal groups) were identified, and the results of GO and KEGG indicated that they were strongly associated with immune cell infiltrations. Among them, ten genes were significantly related to the survival of patients with KRAS LUAD. The expression of IL37, KIF2, INSR, and AQP3 had the most significant correlations with immune cell infiltration. In addition, eight DEGs from the KRAS subgroups were highly correlated with immune infiltrations, especially TNFSF13B. Using LASSO-logistic regression, a KRAS mutation prediction model based on the 74 differentially expressed secretory or membrane-associated genes was built, and the accuracy was 0.79.

Conclusion

The research investigated the relationship between the expression of KRAS-related secretory or membrane-associated proteins in LUAD patients with prognostic prediction and immune infiltration characterization. Our study demonstrated that secretory or membrane-associated genes were closely associated with the survival of KRAS LUAD patients and were strongly correlated to immune cell infiltration.

Clinicopathological characteristics and prognosis of resectable lung adenosquamous carcinoma: a population-based study of the SEER database

OBJECTIVE

Adenosquamous carcinoma is a rare subtype of non-small cell lung cancer characterized by aggressive behavior, with combination of adenocarcinoma and squamous cell carcinoma components. The clinicopathological characteristics and prognosis of resectable adenosquamous carcinoma are incompletely understood and this study aimed to depict those in a large population.

METHODS

A total of 805 adenosquamous carcinoma, 7875 squamous cell carcinoma and 23 957 adenocarcinoma patients who underwent lobectomy or sublobectomy were queried from the Surveillance, Epidemiology, and End Results database (2010-17). Clinicopathological characteristics of adenosquamous carcinoma patients were compared with those of squamous cell carcinoma and adenocarcinoma patients. Prognostic factors were identified by univariable and multivariable Cox regression analyses. Propensity score matching was applied to reduce confounding effects.

RESULTS

Adenosquamous carcinoma was associated with higher pleural invasion incidence and poorer differentiation compared with squamous cell carcinoma or adenocarcinoma (P values < 0.001). The independent risk factors of cancer-specific survival of adenosquamous carcinoma patients were increasing age, male sex, invading through visceral pleura, poor differentiation and higher stage. Stage IB adenosquamous carcinoma patients whose tumor invaded through visceral pleura had significantly worse survival than those not (P = 0.003). Adenosquamous carcinoma patients had worse survival compared with squamous cell carcinoma (5-year-survival: 64.55 vs. 69.09%, P = 0.003) and adenocarcinoma (5-year-survival: 64.55 vs. 76.79%, P < 0.001) patients before match. And this difference persisted after match.

CONCLUSIONS

Resectable adenosquamous carcinoma patients had higher pleural invasion incidence, poorer differentiation and worse survival compared with squamous cell carcinoma and adenocarcinoma patients. Visceral pleural invasion status and differentiation grade were vital prognostic factors of adenosquamous carcinoma patients on the basis of stage.

Identification of Significant Secreted or Membrane-Located Proteins in Laryngeal Squamous Cell Carcinoma

Background. This study is aimed at investigating the expressions and prognostic values of secreted or membrane-located proteins (SMPs) in laryngeal squamous cell carcinoma (LSCC). The correlations between the expressions of SMPs and immune cells’ infiltrations were also investigated. Methods. The expression data of normal laryngeal and LSCC samples were obtained from the TCGA and GEO datasets. The differentially expressed SMPs were identified, and their prognostic values were analyzed. The biological functions of differentially expressed and worse-survival-related SMPs were explored. LASSO regression, Cox multivariate analysis, and nomogram were used to construct a model to predict the survival. Then, the infiltrations of the 24 immune cell populations were calculated using the GSVA method, and the correlations between the expression of SMPs and the immune infiltration were investigated. Results. 122 samples (12 normal and 120 LSCC) of the TCGA database and 114 samples (57 normal and 57 LSCC) of GSE127165 were included. We identified that 138 SMPs were significantly upregulated in LSCC samples of both the TCGA and GEO datasets, among which 52 SMPs were significantly correlated with worse survival. GO and KEGG analyses revealed those 52 SMPs significantly participate in tumor microenvironment and immune cells’ communication. Nine of 52 SMPs (ABCC5, ATP1B3, CLEC11A, FLNA, FSTL3, MMP1, NME1, OAS3, and PHLDB2) were included in the nomogram to effectively and accurately predict the LSCC patients’ survival. The expressions of most SMPs, such as MMP1 and FSTL3, were significantly positively correlated with the immune infiltration of LSCC. Conclusions. In this study, the expression, prognostic values, and correlations with immune infiltration of SMPs were analyzed in LSCC samples. Our analyses identified several significant SMPs differentially expressed between normal laryngeal and LSCC samples, correlated with worse survival, and related to the immune infiltration.