Related Experiment Video
Updated: Sep 13, 2026
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Reusable Pipeline for Converting Real-World Lymphoma Registry Data to CDISC Standards: Implementation and Validation
Michael J Kane1, Dai Chihara1, Amy Ayers1
1Department of Lymphoma and Myeloma, The University of Texas MD Anderson Cancer Center, Houston, TX.
Purpose:
Heterogeneity in cancer registries limits reuse of real-world data (RWD) alongside clinical trials to support regulatory decisions. Rituximab, gemcitabine, and oxaliplatin (R-GemOx) is commonly a comparator in large B-cell lymphoma (LBCL) trials and used in practice, but RWD are not structured for trial comparison. We developed a reusable pipeline to convert the Lymphoma Epidemiology of Outcomes Consortium for Real World Evidence (LEO CReWE) registry into Clinical Data Interchange Standards Consortium (CDISC)-compliant data sets by constructing a generalized, registry-wide Study Data Tabulation Model (SDTM) and deriving analysis-ready Analysis Data Model (ADaM) data sets.
Methods:
Using R 4.5.2 with the sdtm.oak, admiral, and admiralonco packages, we generated ADaM for 183 patients with relapsed/refractory LBCL treated with R-GemOx across the multicenter LEO cohort.
Results:
ADaM-derived summary statistics showed exact concordance with published results for this cohort: median age 68 years, complete response rate 29%, median overall survival 13.5 months, and median event-free survival 2.3 months. CDISC conformance was assessed using the CDISC Open Rules Engine (CORE); no finding represented rejection-level structural nonconformance. The generalized SDTM enabled rapid regeneration of ADaM as cohort definitions changed, including a separate cohort treated with axicabtagene ciloleucel (a chimeric antigen receptor T-cell), and supports federated analyses in which sites retain control of patient-level data.
Conclusion:
This work demonstrates a practical, reusable pipeline for CDISC-standardized RWD in lymphoma.