A large cohort study identifying a novel prognosis prediction model for lung adenocarcinoma through machine learning strategies

Yin Li,Fengkai Xu,Jie Gu,Di Ge,Qiaoliang Zhu,Chunlai Lu

doi:10.1186/s12885-019-6101-7

Abstract

BackgroundPredicting lung adenocarcinoma (LUAD) risk is crucial in determining further treatment strategies. Molecular biomarkers may improve risk stratification for LUAD.MethodsWe analyzed the gene expression profiles of LUAD patients from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO). We initially used three distinct algorithms (sigFeature, random forest, and univariate Cox regression) to evaluate each gene’s prognostic relevance. Survival related genes were then fitted into the least absolute shrinkage and selection operator (LASSO) model to build a risk prediction model for LUAD. After 100,000 times of calculation and model construction, a 16-gene-based prediction model capable of classifying LUAD patients into high-risk and low-risk groups was successfully built.ResultsUsing a combined strategy, we initially identified 2472 significant survival-related genes. Functional enrichment analysis demonstrated these genes’ relevance to tumor initiation and progression. Using the LASSO method, we successfully built a reliable risk prediction model. The risk model was validated in two external sets and an independent set. The expression of these 16 genes was highly correlated with patients’ risk. High-risk group patients witnessed poorer recurrence-free survival (RFS) and overall survival (OS) compared to low-risk group patients. Moreover, stratification analysis and decision curve analysis (DCA) confirmed the independence and potential translational value of this predictive tool. We also built a nomogram comprising risk model and stage to predict OS for LUAD patients.ConclusionsOur risk model may serve as a practical and reliable prognosis predictive tool for LUAD and could provide novel insights into the understanding of the molecular mechanism of this disease.

Highlights

Predicting lung adenocarcinoma (LUAD) risk is crucial in determining further treatment strategies
Lung cancer consists of two major histological types: Non-small-cell lung cancer (NSCLC), which accounts for approximately 85%, and small-cell lung cancer (SCLC)
A total of 1463 LUAD patients were enrolled in our study, among which 492 patients were assigned to the discovery set, 232 patients were assigned to the external testing set, 347 patients were included as the external validation set, and 386 patients were assigned to the independent set

Summary

Introduction

Predicting lung adenocarcinoma (LUAD) risk is crucial in determining further treatment strategies. The 5-year overall survival rate for lung cancer patients remains low at about 17% [2]. Lung cancer consists of two major histological types: Non-small-cell lung cancer (NSCLC), which accounts for approximately 85%, and small-cell lung cancer (SCLC). Lung adenocarcinoma (LUAD) is the major histological subtype of NSCLC, accounting for more than 40% of lung cancer incidence [3]. Li et al BMC Cancer (2019) 19:886 factors, the discovery of a novel prediction signature which is capable of predicting prognosis for LUAD patients and identifying the high-risk subgroup of LUAD patients is urgently demanded. In pursuit of predictive biomarkers for patients with LUAD, previous studies had highlighted various biomarkers that may have the potentiality to be used for prognosis prediction in LUAD. The limitations of some of these studies included small study populations, lack of validation, single-center cohorts, and model overfitting [6, 7]

Objectives

Methods

Results

Conclusion