RESUMO
OBJECTIVE: Patients with lung cancer are at risk of radiation pneumonia (RP) after receiving radiotherapy. We established a prediction model according to the critical indicators extracted from radiation pneumonia patients. MATERIALS AND METHODS: 74 radiation pneumonia patients were involved in the training set. Firstly, the clinical data, hematological and radiation dose parameters of the 74 patients were screened by Logistics regression univariate analysis according to the level of radiation pneumonia. Next, Stepwise regression analysis was utilized to construct the regression model. Then, the influence of continuous variables on RP was tested by smoothing function. Finally, the model was externally verified by 30 patients in validation set and visualized by R code. RESULTS: In the training set, there was 40 patients suffered≥ level 2 acute radiation pneumonia. Clinical data (diabetes), blood indexes (lymphocyte percentage, basophil percentage, platelet count) and radiation dose (V15 > 40%, V20 > 30%, V35 >18%, V40 > 15%) were related to radiation pneumonia (P < 0.05). Particularly, stepwise regression analysis indicated that the history of diabetes, the basophils percentage, platelet count and V20 could be the best combination used for predicting radiation pneumonia. The column chart was obtained by fitting the regression model with the combined indicator. The receiver operating characteristic (ROC) curve showed that the AUC in the development term was 0.853, the AUC was 0.656 in the validation term. And calibration curves of both groups showed the high stability in efficiently diagnostic. Furthermore, the DCA curve showed that the model had a satisfactory positive net benefit. CONCLUSION: The combination of the basophils percentage, platelet count and V20 is available to build a predictive model of radiation pneumonia for patients with advanced lung cancer.
Assuntos
Neoplasias Pulmonares/radioterapia , Pneumonite por Radiação/epidemiologia , Idoso , Comorbidade , Feminino , Testes Hematológicos , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Modelos Estatísticos , Estadiamento de Neoplasias , Prognóstico , Curva ROC , Dosagem Radioterapêutica , Estudos RetrospectivosRESUMO
BACKGROUND: The development of human tumors is associated with the abnormal expression of various functional genes, and a massive tumor-based database needs to be deeply mined. Based on a multigene prediction model, access to urgent prognosis of patients has become possible. MATERIALS AND METHODS: We selected three RNA expression profiles (GSE32863, GSE10072, and GSE43458) from the lung adenocarcinoma (LUAD) database of the Gene Expression Omnibus (GEO) and analyzed the differentially expressed genes (DEGs) between tumor and normal tissue using GEO2R program. After that, we analyzed the transcriptome data of 479 LUAD samples (54 normal tissue samples and 425 cancer tissue samples) and their clinical follow-up data from the (TCGA) database. Kaplan-Meier (KM) curve and receiver operating characteristic (ROC) were used to assess the prediction model. Multivariate Cox analysis was used to identify independent predictors. TCGA pancreatic adenocarcinoma datasets were used to establish a nomogram model. RESULTS: We found 98 significantly prognosis-related genes using KM and COX analysis, among which six genes were found to be the DEGs in GEO. Using multivariate analysis, it was found that a single gene could not be used as an independent predictor of prognosis. However, the risk score calculated by weighting these six genes could serve as an independent prognosis predictor. COX analysis performed with multiple covariates such as age, gender, tumor stage, and TNM typing showed that risk score could still be utilized as an independent risk factor for patient survival rate (p = 0.013) and had an applicable reliability (area under the curve, AUC = 0.665). By combining risk score and various clinical features, the nomogram model was constructed, which had been proven to have high consistency for the prediction of 3- and 5-year survival rate (concordance = 0.751) and high accuracy as tested by ROC (AUC = 0.71;AUC = 0.708). CONCLUSION: We proposed a method to predict the prognosis of LUAD by weighting multiple genes and constructed a nomogram model suitable for the prognostic evaluation of LUAD, which could provide a new tool for the identification of therapeutic targets and the efficacy evaluation of LUAD.