Dataset Information

A Novel Early-Stage Lung Adenocarcinoma Prognostic Model Based on Feature Selection With Orthogonal Regression.

ABSTRACT: Carcinoma diagnosis and prognosis are still hindered by the lack of effective prediction model and integration methodology. We proposed a novel feature selection with orthogonal regression (FSOR) method to resolve predictor selection and performance optimization. Functional enrichment and clinical outcome analyses with multi-omics information validated the method's robustness in the early-stage prognosis of lung adenocarcinoma. Furthermore, compared with the classic least absolute shrinkage and selection operator (LASSO) regression method [the averaged 1- to 4-years predictive area under the receiver operating characteristic curve (AUC) measure, 0.6998], the proposed one outperforms more accurately by 0.7208 with fewer predictors, particularly its averaged 1- to 3-years AUC reaches 0.723, vs. classic 0.6917 on The Cancer Genome Atlas (TCGA). In sum, the proposed method can deliver better prediction performance for early-stage prognosis and improve therapy strategy but with less predictor consideration and computation burden. The self-composed running scripts, together with the processed results, are available at https://github.com/gladex/PM-FSOR.

SUBMITTER: Tang B

PROVIDER: S-EPMC7874010 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Novel Early-Stage Lung Adenocarcinoma Prognostic Model Based on Feature Selection With Orthogonal Regression.

Tang Binhua B Wang Yuqi Y Chen Yu Y Li Ming M Tao Yongfeng Y

Frontiers in cell and developmental biology 20210108

Carcinoma diagnosis and prognosis are still hindered by the lack of effective prediction model and integration methodology. We proposed a novel feature selection with orthogonal regression (FSOR) method to resolve predictor selection and performance optimization. Functional enrichment and clinical outcome analyses with multi-omics information validated the method's robustness in the early-stage prognosis of lung adenocarcinoma. Furthermore, compared with the classic least absolute shrinkage and ...[more]

PMID: 33585460

Similar Datasets

Project description:PurposeTP53 mutation, one of the most frequent mutations in early-stage lung adenocarcinoma (LUAD), triggers a series of alterations in the immune landscape, progression, and clinical outcome of early-stage LUAD. Our study was designed to unravel the effects of TP53 mutation on the immunophenotype of early-stage LUAD and formulate a TP53-associated immune prognostic model (IPM) that can estimate prognosis in early-stage LUAD patients.Materials and methodsImmune-associated differentially expressed genes (DEGs) between TP53 mutated (TP53MUT ) and TP53 wild-type (TP53WT ) early-stage LUAD were comprehensively analyzed. Univariate Cox analysis and least absolute shrinkage and selection operator (LASSO) analysis identified the prognostic immune-associated DEGs. We constructed and validated an IPM based on the TCGA and a meta-GEO composed of GSE72094, GSE42127, and GSE31210, respectively. The CIBERSORT algorithm was analyzed for assessing the percentage of immune cell types. A nomogram model was established for clinical application.ResultsTP53 mutation occurred in approximately 50.00% of LUAD patients, stimulating a weakened immune response in early-stage LUAD. Sixty-seven immune-associated DEGs were determined between TP53WT and TP53MUT cohort. An IPM consisting of two prognostic immune-associated DEGs (risk score = 0.098 * ENTPD2 expression + 0.168 * MIF expression) was developed through 397 cases in the TCGA and further validated based on 623 patients in a meta-GEO. The IPM stratified patients into low or high risk of undesirable survival and was identified as an independent prognostic indicator in multivariate analysis (HR = 2.09, 95% CI: 1.43-3.06, p < 0.001). Increased expressions of PD-L1, CTLA-4, and TIGIT were revealed in the high-risk group. Prognostic nomogram incorporating the IPM and other clinicopathological parameters (TNM stage and age) achieved optimal predictive accuracy and clinical utility.ConclusionThe IPM based on TP53 status is a reliable and robust immune signature to identify early-stage LUAD patients with high risk of unfavorable survival.

Project description:BackgroundBased on computed tomography (CT) findings of lung cancer, solid nodules have a much worse prognosis than subsolid nodules, even if the nodules are subcentimeter in size. There is, however, no systematic method for determining the prognosis of solid tumors on CT. This study aimed to discover the prognostic factor of early-stage solid lung adenocarcinoma using three-dimensional CT volumetry.MethodsPatients with pathological stage I solid lung adenocarcinoma who underwent complete resection between 2007 and 2012 were selected in this retrospective study. Clinicopathological data and preoperative multidetector CT findings, such as tumor size on the two-dimensional axial image, three-dimensional tumor volume between -600 and 199 HU, and three-dimensional solid volume between 0 and 199 HU, which corresponded to highly solid components, were compared between recurrence and non-recurrence. Furthermore, these radiological values were compared to pathological invasive volume (PIV).ResultsDuring this time, 709 patients had their lung cancer completely removed. From this cohort, 90 patients with pathological stage I solid lung adenocarcinoma were selected. In addition, recurrence was found in 26 patients (28.9%). Although two-dimensional axial image, serum carcinoembryonic antigen (CEA) level, and SUVmax on 18F fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) did not differ statistically between recurrent and non-recurrent patients, three-dimensional tumor and solid tumor volume did. Multivariate analysis indicated that three-dimensional solid tumor volume [hazard ratio: 2.440; 95% confidence interval (CI): 1.110-5.361, P=0.026] and epidermal growth factor receptor (EGFR) mutation (hazard ratio: 4.307; 95% CI: 1.328-13.977, P=0.015) were significantly associated with disease-free survival (DFS). When three-dimensional tumor and solid tumor volume were compared to PIV, three-dimensional solid tumor volume (3,091 mm3 on average) showed a highly similar value with PIV (2,930 mm3 on average), whereas three-dimensional tumor volume (6,175 mm3 on average) was significantly larger than PIV (P<0.001).ConclusionsIn patients with early-stage solid lung adenocarcinoma, the measurement of three-dimensional solid tumor volume, which is correlated with PIV, accurately predicted the postoperative outcome.

Dataset Information

A Novel Early-Stage Lung Adenocarcinoma Prognostic Model Based on Feature Selection With Orthogonal Regression.

Publications

A Novel Early-Stage Lung Adenocarcinoma Prognostic Model Based on Feature Selection With Orthogonal Regression.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets