Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma
Abstract Background We aimed to develop and validate a predictive model for the overall survival (OS) of patients with nasopharyngeal carcinoma (NPC). Methods Overall, 519 patients were retrospectively reviewed in this study. In addition, a random forest model was used to identify significant progno...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-08-01
|
Series: | Cancer Cell International |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12935-021-02158-6 |
id |
doaj-f63cd6f4439245bdb7878756884fca77 |
---|---|
record_format |
Article |
spelling |
doaj-f63cd6f4439245bdb7878756884fca772021-08-29T11:40:57ZengBMCCancer Cell International1475-28672021-08-0121111210.1186/s12935-021-02158-6Development and validation of a risk prediction score for patients with nasopharyngeal carcinomaNing Xue0Guoping Ou1Weiguo Ma2Lina Jia3Jiahe Sheng4Qingxia Xu5Yubo Liu6Miaomiao Jia7Department of Clinical Laboratory, Affiliated Tumor Hospital of Zhengzhou University, Henan Tumor HospitalDepartment of Laboratory Medicine, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Sun Yat-Sen University Cancer CenterDepartment of Clinical Laboratory, Affiliated Tumor Hospital of Zhengzhou University, Henan Tumor HospitalDepartment of Clinical Laboratory, Affiliated Tumor Hospital of Zhengzhou University, Henan Tumor HospitalDepartment of Clinical Laboratory, Affiliated Tumor Hospital of Zhengzhou University, Henan Tumor HospitalDepartment of Clinical Laboratory, Affiliated Tumor Hospital of Zhengzhou University, Henan Tumor HospitalDepartment of Ultrasound, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer CenterDepartment of Clinical Laboratory, Affiliated Tumor Hospital of Zhengzhou University, Henan Tumor HospitalAbstract Background We aimed to develop and validate a predictive model for the overall survival (OS) of patients with nasopharyngeal carcinoma (NPC). Methods Overall, 519 patients were retrospectively reviewed in this study. In addition, a random forest model was used to identify significant prognostic factors for OS among NPC patients. Then, calibration plot and concordance index (C-index) were utilized to evaluate the predictive accuracy of the nomogram model. Results We used a random forest model to select the three most important features, dNLR, HGB and EBV DNA, which were significantly associated with the OS of NPC patients. Furthermore, the C-index of our model for OS were 0.733 (95% CI 0.673 ~ 0.793) and 0.772 (95% CI 0.691 ~ 0.853) in the two cohorts, which was significantly higher than that of the TNM stage, treatment, and EBV DNA. Based on the model risk score, patients were divided into two groups, associated with low-risk and high-risk. Kaplan–Meier curves demonstrated that the two subgroups were significantly associated with OS in the primary cohort, as well as in the validation cohort. The nomogram for OS was established using the risk score, TNM stage and EBV DNA in the two cohorts. The nomogram achieved a higher C-index of 0.783 (95% CI 0.730 ~ 0.836) than that of the risk score model 0.733 (95% CI 0.673 ~ 0.793) in the primary cohort (P = 0.005). Conclusions The established risk score model and nomogram resulted in more accurate prognostic prediction for individual patient with NPC.https://doi.org/10.1186/s12935-021-02158-6Nasopharyngeal carcinomaRisk scoreNomogramOverall survival |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ning Xue Guoping Ou Weiguo Ma Lina Jia Jiahe Sheng Qingxia Xu Yubo Liu Miaomiao Jia |
spellingShingle |
Ning Xue Guoping Ou Weiguo Ma Lina Jia Jiahe Sheng Qingxia Xu Yubo Liu Miaomiao Jia Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma Cancer Cell International Nasopharyngeal carcinoma Risk score Nomogram Overall survival |
author_facet |
Ning Xue Guoping Ou Weiguo Ma Lina Jia Jiahe Sheng Qingxia Xu Yubo Liu Miaomiao Jia |
author_sort |
Ning Xue |
title |
Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma |
title_short |
Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma |
title_full |
Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma |
title_fullStr |
Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma |
title_full_unstemmed |
Development and validation of a risk prediction score for patients with nasopharyngeal carcinoma |
title_sort |
development and validation of a risk prediction score for patients with nasopharyngeal carcinoma |
publisher |
BMC |
series |
Cancer Cell International |
issn |
1475-2867 |
publishDate |
2021-08-01 |
description |
Abstract Background We aimed to develop and validate a predictive model for the overall survival (OS) of patients with nasopharyngeal carcinoma (NPC). Methods Overall, 519 patients were retrospectively reviewed in this study. In addition, a random forest model was used to identify significant prognostic factors for OS among NPC patients. Then, calibration plot and concordance index (C-index) were utilized to evaluate the predictive accuracy of the nomogram model. Results We used a random forest model to select the three most important features, dNLR, HGB and EBV DNA, which were significantly associated with the OS of NPC patients. Furthermore, the C-index of our model for OS were 0.733 (95% CI 0.673 ~ 0.793) and 0.772 (95% CI 0.691 ~ 0.853) in the two cohorts, which was significantly higher than that of the TNM stage, treatment, and EBV DNA. Based on the model risk score, patients were divided into two groups, associated with low-risk and high-risk. Kaplan–Meier curves demonstrated that the two subgroups were significantly associated with OS in the primary cohort, as well as in the validation cohort. The nomogram for OS was established using the risk score, TNM stage and EBV DNA in the two cohorts. The nomogram achieved a higher C-index of 0.783 (95% CI 0.730 ~ 0.836) than that of the risk score model 0.733 (95% CI 0.673 ~ 0.793) in the primary cohort (P = 0.005). Conclusions The established risk score model and nomogram resulted in more accurate prognostic prediction for individual patient with NPC. |
topic |
Nasopharyngeal carcinoma Risk score Nomogram Overall survival |
url |
https://doi.org/10.1186/s12935-021-02158-6 |
work_keys_str_mv |
AT ningxue developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT guopingou developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT weiguoma developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT linajia developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT jiahesheng developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT qingxiaxu developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT yuboliu developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma AT miaomiaojia developmentandvalidationofariskpredictionscoreforpatientswithnasopharyngealcarcinoma |
_version_ |
1721186528829374464 |