Search

Background: Images from magnetic resonance imaging (MRI) are crucial unstructured data for prognostic evaluation in nasopharyngeal carcinoma (NPC). We developed and validated a prognostic system based on the MRI features and clinical data of locoregionally advanced NPC (LA-NPC) patients to distinguish low-risk patients with LA-NPC for whom concurrent chemoradiotherapy (CCRT) is sufficient.Methods: This multicenter, retrospective study included 3444 patients with LA-NPC from January 1, 2010, to January 31, 2017. A 3-dimensional convolutional neural network was used to learn the image features from pretreatment MRI images. An eXtreme Gradient Boosting model was trained with the MRI features and clinical data to assign an overall score to each patient. Comprehensive evaluations were implemented to assess the performance of the predictive system. We applied the overall score to distinguish high-risk patients from low-risk patients. The clinical benefit of induction chemotherapy (IC) was analyzed in each risk group by survival curves.Results: We constructed a prognostic system displaying a concordance index of 0.776 (95% confidence interval [CI] = 0.746 to 0.806) for the internal validation cohort and 0.757 (95% CI = 0.695 to 0.819), 0.719 (95% CI = 0.650 to 0.789), and 0.746 (95% CI = 0.699 to 0.793) for the 3 external validation cohorts, which presented a statistically significant improvement compared with the conventional TNM staging system. In the high-risk group, patients who received induction chemotherapy plus CCRT had better outcomes than patients who received CCRT alone, whereas there was no statistically significant difference in the low-risk group.Conclusions: The proposed framework can capture more complex and heterogeneous information to predict the prognosis of patients with LA-NPC and potentially contribute to clinical decision making. [ABSTRACT FROM AUTHOR]

Objective: Two cycles of induction chemotherapy (IC) followed by 2 cycles of platinum-based concurrent chemoradiotherapy (CCRT) (2IC+2CCRT) for locoregionally advanced nasopharyngeal carcinoma (LA-NPC) is widely adopted but not evidence-confirmed. This study aimed to determine the clinical value of 2IC+2CCRT regarding efficacy, toxicity and cost-effectiveness., Methods: This real-world study from two epidemic centers used propensity score matching (PSM) and inverse probability of treatment weighting (IPTW) analyses. The enrolled patients were divided into three groups based on treatment modality: Group A (2IC+2CCRT), Group B (3IC+2CCRT or 2IC+3CCRT) and Group C (3IC+3CCRT). Long-term survival, acute toxicities and cost-effectiveness were compared among the groups. We developed a prognostic model dividing the population into high- and low-risk cohorts, and survivals including overall survival (OS), progression-free survival (PFS), distant metastasis-free survival (DMFS) and locoregional relapse-free survival (LRRFS) were compared among the three groups according to certain risk stratifications., Results: Of 4,042 patients, 1,175 were enrolled, with 660, 419, and 96 included in Groups A, B and C, respectively. Five-year survivals were similar among the three groups after PSM and confirmed by IPTW. Grade 3-4 neutropenia and leukocytopenia were significantly higher in Groups C and B than in Group A (52.1% vs. 41.5% vs. 25.2%; 41.7% vs. 32.7% vs. 25.0%) as were grade 3-4 nausea/vomiting and oral mucositis (29.2% vs. 15.0% vs. 6.1%; 32.3% vs. 25.3% vs. 18.0%). Cost-effective analysis suggested that 2IC+2CCRT was the least expensive, while the health benefits were similar to those of the other groups. Further exploration showed that 2IC+2CCRT tended to be associated with a shorter PFS in high-risk patients, while 3IC+3CCRT potentially contributed to poor PFS in low-risk individuals, mainly reflected by LRRFS., Conclusions: In LA-NPC patients, 2IC+2CCRT was the optimal choice regarding efficacy, toxicity and cost-effectiveness; however, 2IC+2CCRT and 3IC+3CCRT probably shortened LRRFS in high- and low-risk populations, respectively., Competing Interests: Conflicts of Interest: The authors have no conflicts of interest to declare., (Copyright ©2023 Chinese Journal of Cancer Research. All rights reserved.)

Background: Images from magnetic resonance imaging (MRI) are crucial unstructured data for prognostic evaluation in nasopharyngeal carcinoma (NPC). We developed and validated a prognostic system based on the MRI features and clinical data of locoregionally advanced NPC (LA-NPC) patients to distinguish low-risk patients with LA-NPC for whom concurrent chemoradiotherapy (CCRT) is sufficient., Methods: This multicenter, retrospective study included 3444 patients with LA-NPC from January 1, 2010, to January 31, 2017. A 3-dimensional convolutional neural network was used to learn the image features from pretreatment MRI images. An eXtreme Gradient Boosting model was trained with the MRI features and clinical data to assign an overall score to each patient. Comprehensive evaluations were implemented to assess the performance of the predictive system. We applied the overall score to distinguish high-risk patients from low-risk patients. The clinical benefit of induction chemotherapy (IC) was analyzed in each risk group by survival curves., Results: We constructed a prognostic system displaying a concordance index of 0.776 (95% confidence interval [CI] = 0.746 to 0.806) for the internal validation cohort and 0.757 (95% CI = 0.695 to 0.819), 0.719 (95% CI = 0.650 to 0.789), and 0.746 (95% CI = 0.699 to 0.793) for the 3 external validation cohorts, which presented a statistically significant improvement compared with the conventional TNM staging system. In the high-risk group, patients who received induction chemotherapy plus CCRT had better outcomes than patients who received CCRT alone, whereas there was no statistically significant difference in the low-risk group., Conclusions: The proposed framework can capture more complex and heterogeneous information to predict the prognosis of patients with LA-NPC and potentially contribute to clinical decision making., (© The Author(s) 2020. Published by Oxford University Press. All rights reserved. For permissions, please email: journals.permissions@oup.com.)