A narrative review of prognosis prediction models for non-small cell lung cancer: what kind of predictors should be selected and how to improve models?

A predictive model for prognostic risk stratification of early-stage NSCLC based on clinicopathological and miRNA panel

OBJECTIVE

The 5-year survival rate of early-stage non-small cell lung cancer (NSCLC) is still not optimistic. We aimed to construct prognostic tools using clinicopathological (CP) and serum 8-miRNA panel to predict the risk of overall survival (OS) in early-stage NSCLC.

MATERIALS AND METHODS

A total of 799 patients with early-stage NSCLC, treated between April 2008 and September 2019, were included in this study. A sub-group of patients with serum samples, 280, were analyzed for miRNA profiling. The primary endpoint of the study was OS. The CP panel for prognosis was developed using multivariate and forward stepwise selection analyses. The serum 8-miRNA panel was developed using the miRNAs that were significant for prognosis, screened using real-time quantitative PCR (qPCR) followed by differential, univariate and Cox regression analyses. The combined model was developed using CP panel and serum 8-miRNA panel. The predictive performance of the panels and the combined model was evaluated using the area under curve (AUC) values of receiver operating characteristics (ROC) curves and Kaplan-Meier survival analysis.

RESULT

The prognostic panels and the combined model (comprising CP panel and serum 8-miRNA panel) was used to classify the patients into high-risk and low-risk groups. The OS rates of these two groups were significantly different (P<0.05). The two panels had higher AUC than the two guidelines, and the combined model had the highest AUC. The AUC of the combined model (AUC=0.788; 95 %CI 0.706-0.871) was better than that of the National Comprehensive Cancer Network (NCCN) guideline (AUC=0.601; 95 %CI 0.505-0.697) and Chinese Society of Clinical Oncology (CSCO) guideline (AUC=0.614; 95 %CI 0.520-0.708).

CONCLUSION

The combined model based on CP panel and serum 8-miRNA panel allows better prognostic risk stratification of patients with early-stage NSCLC to predict risk of OS.

Predictive risk score for isolated brain metastasis in non-small cell lung cancer

Background

Brain metastasis is common with non-small cell lung cancer (NSCLC). Patients with some early-stage cancers don't benefit from routine brain imaging. Currently clinical stage alone is used to justify additional brain imaging. Other clinical and demographic characteristics may be associated with isolated brain metastasis (IBM). We aimed to define the most salient clinical features associated with synchronous IBM, hypothesizing that clinical and demographic factors could be used to determine the risk of brain metastasis.

Methods

The National Cancer Database was used to identify patients with NSCLC from 2016-2020. Primary outcome was the presence of IBM relative to patients without evidence of any metastasis. Cohorts were divided into test and validation. The test cohort was used to identify risk factors for IBM using multivariable logistic regression. Using the regression, a scoring system was created to estimate the rate of synchronous IBM. The accuracy of the scoring system was evaluated with receiver operating characteristic (ROC) analysis using the validation cohort.

Results

Study population consisted of 396,113 patients: 25,907 IBM and 370,206 without metastatic disease. IBM was associated with age, clinical T stage, clinical N stage, Charlson/Deyo comorbidity score, histology, and grade. A scoring system using these factors showed excellent accuracy in the test and validation cohort in ROC analysis (0.806 and 0.805, respectively).

Conclusions

Clinical and demographic characteristics can be used to stratify the risk of IBM among patients with NSCLC and provide an evidence-based method to identify patients who require dedicated brain imaging in the absence of other metastatic disease.

Multiomics-Based Feature Extraction and Selection for the Prediction of Lung Cancer Survival

Lung cancer is a global health challenge, hindered by delayed diagnosis and the disease's complex molecular landscape. Accurate patient survival prediction is critical, motivating the exploration of various -omics datasets using machine learning methods. Leveraging multi-omics data, this study seeks to enhance the accuracy of survival prediction by proposing new feature extraction techniques combined with unbiased feature selection. Two lung adenocarcinoma multi-omics datasets, originating from the TCGA and CPTAC-3 projects, were employed for this purpose, emphasizing gene expression, methylation, and mutations as the most relevant data sources that provide features for the survival prediction models. Additionally, gene set aggregation was shown to be the most effective feature extraction method for mutation and copy number variation data. Using the TCGA dataset, we identified 32 molecular features that allowed the construction of a 2-year survival prediction model with an AUC of 0.839. The selected features were additionally tested on an independent CPTAC-3 dataset, achieving an AUC of 0.815 in nested cross-validation, which confirmed the robustness of the identified features.

Construction of a predictive model for immunotherapy efficacy in lung squamous cell carcinoma based on the degree of tumor-infiltrating immune cells and molecular typing

Background

To construct a predictive model of immunotherapy efficacy for patients with lung squamous cell carcinoma (LUSC) based on the degree of tumor-infiltrating immune cells (TIIC) in the tumor microenvironment (TME).

Methods

The data of 501 patients with LUSC in the TCGA database were used as a training set, and grouped using non-negative matrix factorization (NMF) based on the degree of TIIC assessed by single-sample gene set enrichment analysis (GSEA). Two data sets (GSE126044 and GSE135222) were used as validation sets. Genes screened for modeling by least absolute shrinkage and selection operator (LASSO) regression and used to construct a model based on immunophenotyping score (IPTS). RNA extraction and qPCR were performed to validate the prognostic value of IPTS in our independent LUSC cohort. The receiver operating characteristic (ROC) curve was constructed to determine the predictive value of the immune efficacy. Kaplan–Meier survival curve analysis was performed to evaluate the prognostic predictive ability. Correlation analysis and enrichment analysis were used to explore the potential mechanism of IPTS molecular typing involved in predicting the immunotherapy efficacy for patients with LUSC.

Results

The training set was divided into a low immune cell infiltration type (C1) and a high immune cell infiltration type (C2) by NMF typing, and the IPTS molecular typing based on the 17-gene model could replace the results of the NMF typing. The area under the ROC curve (AUC) was 0.82. In both validation sets, the IPTS of patients who responded to immunotherapy were significantly higher than those who did not respond to immunotherapy (P = 0.0032 and P = 0.0451), whereas the AUC was 0.95 (95% CI = 1.00–0.84) and 0.77 (95% CI = 0.58–0.96), respectively. In our independent cohort, we validated its ability to predict the response to cancer immunotherapy, for the AUC was 0.88 (95% CI = 1.00–0.66). GSEA suggested that the high IPTS group was mainly involved in immune-related signaling pathways.

Conclusions

IPTS molecular typing based on the degree of TIIC in the TME could well predict the efficacy of immunotherapy in patients with LUSC with a certain prognostic value.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03565-7.