Predicting overall survival after initial chemotherapy for diffuse large B-cell lymphoma using CT nomogram analysis.
[OBJECTIVES] The study aims to evaluate the potential value of a CT nomogram in predicting overall survival in patients with diffuse large B-cell lymphoma (DLBCL) after initial chemotherapy.
APA
Yin M, Yu C, et al. (2026). Predicting overall survival after initial chemotherapy for diffuse large B-cell lymphoma using CT nomogram analysis.. BMC medical imaging, 26(1). https://doi.org/10.1186/s12880-026-02203-8
MLA
Yin M, et al.. "Predicting overall survival after initial chemotherapy for diffuse large B-cell lymphoma using CT nomogram analysis.." BMC medical imaging, vol. 26, no. 1, 2026.
PMID
41699541
Abstract
[OBJECTIVES] The study aims to evaluate the potential value of a CT nomogram in predicting overall survival in patients with diffuse large B-cell lymphoma (DLBCL) after initial chemotherapy.
[METHODS] A retrospective analysis was conducted on the CT images and clinical data of DLBCL patients who received chemotherapy from January 2013 to May 2018. A total of 130 patients were included and randomly divided into a training cohort ( = 91) and a validation cohort ( = 39) at a 7:3 ratio. CT radiomics features were extracted, and the Rad-score was calculated using the least absolute shrinkage and selection operator (LASSO) algorithm. Independent clinical risk factors were identified using univariate and multivariate Cox regression, and then a nomogram model was developed jointly with the Rad-score. The operating characteristic curve (ROC), calibration curve, and decision curve assessments were utilized to assess the model’s predicting performance.
[RESULTS] The 15 radiomics features highly correlated with OS in DLBCL patients were identified and used to calculate the Rad-score. A nomogram model was constructed by combining Rad-score with independent risk factors (Ann Arbor staging, International Prognostic Index (IPI) score, Karnofsky performance status (KPS), effectiveness) based on multivariate analysis. In the training and validation cohorts, the AUC values of the nomogram model for predicting 3 and 5 years OS were 0.860 and 0.810, respectively, 0.838 and 0.816, respectively, which were higher than the Rad-score model (0.744 and 0.763, respectively, 0.787 and 0.562, respectively). Furthermore, the calibration and decision curve evaluations revealed that the nomogram model provided accurate predictions and had high clinical utility in predicting OS in DLBCL patients.
[CONCLUSION] The nomogram model combined with clinical characteristics and Rad-score provides a good prediction of OS in DLBCL patients.
[METHODS] A retrospective analysis was conducted on the CT images and clinical data of DLBCL patients who received chemotherapy from January 2013 to May 2018. A total of 130 patients were included and randomly divided into a training cohort ( = 91) and a validation cohort ( = 39) at a 7:3 ratio. CT radiomics features were extracted, and the Rad-score was calculated using the least absolute shrinkage and selection operator (LASSO) algorithm. Independent clinical risk factors were identified using univariate and multivariate Cox regression, and then a nomogram model was developed jointly with the Rad-score. The operating characteristic curve (ROC), calibration curve, and decision curve assessments were utilized to assess the model’s predicting performance.
[RESULTS] The 15 radiomics features highly correlated with OS in DLBCL patients were identified and used to calculate the Rad-score. A nomogram model was constructed by combining Rad-score with independent risk factors (Ann Arbor staging, International Prognostic Index (IPI) score, Karnofsky performance status (KPS), effectiveness) based on multivariate analysis. In the training and validation cohorts, the AUC values of the nomogram model for predicting 3 and 5 years OS were 0.860 and 0.810, respectively, 0.838 and 0.816, respectively, which were higher than the Rad-score model (0.744 and 0.763, respectively, 0.787 and 0.562, respectively). Furthermore, the calibration and decision curve evaluations revealed that the nomogram model provided accurate predictions and had high clinical utility in predicting OS in DLBCL patients.
[CONCLUSION] The nomogram model combined with clinical characteristics and Rad-score provides a good prediction of OS in DLBCL patients.
같은 제1저자의 인용 많은 논문 (5)
- Identification and evaluation of glutamine-related gene characteristics based on multi-omics to predict the prognosis of patients with colorectal cancer.
- Chlorine-coordinated iron single-atom nanozymes for amplified ferroptosis in triple-negative breast cancer therapy.
- Global, regional, and national burden of disease associated with low-fiber dietary patterns for colorectal cancer from 1990 to 2021: A systematic analysis for the global burden of disease 2021.
- CDC6/THBS1 accelerates pancreatic cancer progression via AKT-mediated glycolytic reprogramming.
- Biodegradable 3D Injectable Amino Acid Hydrogels Delivering Immune Adjuvant for Enhancing Immunotherapy in Colon Cancer.