Objectives: This study aimed to explore the predictive value of MRI-based radiomic model for progression-free survival (PFS) in nonmetastatic nasopharyngeal carcinoma (NPC). Methods: A total of 327 nonmetastatic NPC patients [training cohort (n = 230) and validation cohort (n = 97)] were enrolled. The clinical and MRI data were collected. The least absolute shrinkage selection operator (LASSO) and recursive feature elimination (RFE) were used to select radiomic features. Five models [Model 1: clinical data, Model 2: overall stage, Model 3: radiomics, Model 4: radiomics + overall stage, Model 5: radiomics + overall stage + Epstein-Barr virus (EBV) DNA] were constructed. The prognostic performances of these models were evaluated by Harrell's concordance index (C-index). The Kaplan-Meier method was applied for the survival analysis. Results : Model 5 incorporating radiomics, overall stage, and EBV DNA yielded the highest C-indices for predicting PFS in comparison with Model 1, Model 2, Model 3, and Model 4 (training cohorts: 0.805 vs. 0.766 vs. 0.749 vs. 0.641 vs. 0.563, validation cohorts: 0.874 vs. 0.839 vs. 836 vs. 0.689 vs. 0.456). The survival curve showed that the high-risk group yielded a lower PFS than the low-risk group.
Conclusions:The model incorporating radiomics, overall stage, and EBV DNA showed better performance for predicting PFS in nonmetastatic NPC patients.
BACKGROUND:
Balancing the cardiovascular risk and benefit of anthracycline-based chemotherapy in patients with diffuse large B-cell lymphoma is an important clinical issue. We aimed to evaluate whether the pretreatment coronary artery calcium score (CACS) can stratify the risk of cancer therapy-related cardiac dysfunction (CTRCD) and major adverse cardiovascular events (MACEs) in patients with diffuse large B-cell lymphoma receiving anthracycline-based chemotherapy.
METHODS:
The patients with diffuse large B-cell lymphoma from 4 hospitals were retrospectively enrolled. The CACS was automatically calculated on nongated chest computed tomography before treatment using artificial intelligence-CACS software and divided into 3 categories (0, 1–100, and >100). The associations between the CACS and CTRCD and between the CACS and MACEs were assessed by logistic regression and Fine-Gray competing-risk regression model. Nelson–Aalen cumulative risk curve was performed to assess the cumulative incidence of MACEs.
RESULTS:
A total of 1468 patients (785 men and 683 women; 100% Asian) were enrolled, and 362 and 185 patients developed CTRCD and MACEs, respectively. Compared with a CACS of 0 (n=826), there was stepwise higher odds of CTRCD with a CACS between 1 and 100 (n=356; odds ratio, 2.587) and a CACS >100 (n=286; odds ratio, 5.239). The CACS was associated with MACEs (1–100 versus 0: subdistribution hazard ratio 3.726; >100 versus 0: subdistribution hazard ratio 7.858; all
P
<0.001). Competing risk-adjusted MACEs rates for patients with a CACS of 0, 1 to 100, and >100 were 1.21%, 8.43%, and 11.19%, respectively, at 3 years, and 3.27%, 16.01%, 31.12%, respectively, at 5 years.
CONCLUSIONS:
The automatic CACS derived from chest computed tomography before treatment was helpful to identify high-risk patients of CTRCD and MACE and guide clinicians to implement cardiovascular protection strategies in patients with diffuse large B-cell lymphoma who received anthracycline-based chemotherapy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.