Validation of a Post-Transplant Lymphoproliferative Disorder Risk Prediction Score and Derivation of a New Prediction Score Using a National Bone Marrow Transplant Registry Database.

Abstract

BACKGROUND\nWe externally validated Fujimoto s Post-Transplant Lymphoproliferative Disorder (PTLD) scoring system for risk prediction by using the Taiwan Blood and Marrow Transplant Registry Database (TBMTRD), and aimed to create a superior scoring system using machine learning methods.\n\n\nMATERIALS AND METHODS\nConsecutive allogeneic hematopoietic cell transplant (HCT) recipients registered in the TBMTRD from 2009 to 2018 were included in this study. The Fujimoto PTLD score was calculated for each patient. The machine learning algorithm, LASSO, was used to construct a new score system, which was validated using the 5-fold cross validation method.\n\n\nRESULTS\nWe identified 2,148 allogeneic HCT recipients, of which 57 (2.65%) developed PTLD in the TBMTRD. In this population, the probability for PTLD development by Fujimoto score at five years for patients in the low, intermediate, high and very high-risk groups were 1.15%, 3.06%, 4.09%, 8.97%, respectively. The score model had acceptable discrimination with a C-statistic of 0.65 and a near-perfect moderate calibration curve (HL test P of 0.81). Using LASSO regression analysis, a four-risk-group model was constructed and the new model showed better discrimination in the validation cohort when compared with The Fujimoto PTLD score (C-statistic: 0.75 vs. 0.65).\n\n\nCONCLUSION\nOur study demonstrated a more comprehensive model when compared with Fujimoto s PTLD scoring system, which included additional predictors identified through machine learning that may have enhanced discrimination. The widespread use of this promising tool for risk stratification of patients receiving HCT allows identification of high-risk patients that may benefit from preemptive treatment for PTLD.\n\n\nIMPLICATIONS FOR PRACTICE\nWe validated the Fujimoto score for the prediction of PTLD development following HSCT in an external, independent, and nationally representative population. We also developed a more comprehensive model with enhanced discrimination for better risk stratification of patients receiving HSCT, potentially changing clinical managements in certain risk groups. Previously unreported risk factors associated with the development of PTLD after HSCT were identified using the machine learning algorithm, LASSO, including pre-HSCT medical history of mechanical ventilation, and the chemotherapy agents used in conditioning regimen.