Affiliation:
1. Department of ENT, First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, China
2. Department of Radiology, Xiangyang First People’s Hospital, Hubei University of Medicine, Xiangyang, Hubei, China
Abstract
BACKGROUND: Nasopharyngeal carcinoma (NC) is one of the prevalent malignancies of the head and neck region with poor prognosis. OBJECTIVE: The aim of this study is to establish a predictive model for assessing NC prognosis based on clinical and MR radiomics data, subsequently to develop a nomogram for practical application. METHODS: Retrospective analysis was conducted on clinical and imaging data collected between May 2010 and August 2018, involving 211 patients diagnosed with histologically confirmed NC who received concurrent chemoradiotherapy or radical surgery in Xiangyang No. 1 People’s Hospital. According to 5–10 years of follow-up results, the patients were divided into two groups: the study group (n= 76), which experienced recurrence, metastasis, or death, and the control group (n= 135), characterized by normal survival. Training and testing subsets were established at a 7:3 ratio, with a predefined time cutoff. In the training set, three prediction models were established: a clinical data model, an imaging model, and a combined model using the integrated variation in clinical characteristics along with MR radiomics parameters (Delta-Radscore) observed before and after concurrent chemoradiotherapy. Model performance was compared using Delong’s test, and net clinical benefit was assessed via decision curve analysis (DCA). Then, external validation was conducted on the test set, and finally a nomogram predicting NC prognosis was created. RESULTS: Univariate analysis identified that the risk factors impacting the prognosis of NC included gender, pathological type, neutrophil to lymphocyte ratio (NLR), degree of tumor differentiation, MR enhancement pattern, and Delta-Radscore (P< 0.05). The combined model established based on the abovementioned factors exhibited significantly higher predictive performance [AUC: 0.874, 95% CI (0.810–0.923)] than that of the clinical data model [AUC: 0.650, 95% CI (0.568–0.727)] and imaging model [AUC: 0.824, 95% CI (0.753–0.882)]. DCA also demonstrated superior clinical net benefit in the combined model, a finding further verified by results from the test set. The developed nomogram, based on the combined model, exhibited promising performance in clinical applications. CONCLUSION: The Delta-Radscore derived from MR radiomics data before and after concurrent chemoradiotherapy helps enhance the performance of the NC prognostic model. The combined model and resultant nomogram provide valuable support for clinical decision-making in NC treatment, ultimately contributing to an improved survival rate.