Predicting the risk of ibrutinib in combination with R-ICE in patients with relapsed or refractory DLBCL using explainable machine learning algorithms

Relapsed or refractory diffuse large B-cell lymphoma (DLBCL) poses significant therapeutic challenges due to heterogeneous patient outcomes. This study aimed to evaluate the efficacy of the ibrutinib plus R-ICE regimen and to leverage explainable machine learning models (ML) for predicting treatment risks and outcomes. Retrospective data from 28 patients treated between March 2019 and July 2022 were analyzed. Machine learning models, including CoxBoost + StepCox, were developed and validated using bootstrap methods. Synthetic minority over-sampling combined with propensity score matching (SMOTE-PSM) addressed class imbalances. Prognostic performance was compared against the Cox proportional hazards model using decision curve and calibration analysis, as well as time-dependent ROC curves. The CoxBoost + StepCox model achieved an average C-index of 0.955 for overall survival (OS) and progression-free survival (PFS). Key prognostic indicators included elevated lactate dehydrogenase (LDH), initial treatment response, time to relapse > 12 months, and CD5 + expression. Calibration curves showed a C-index of 0.932 for OS and 0.972 for PFS in the training set. CD5 + was most predictive for OS and LDH for PFS. Machine learning models demonstrated high accuracy and clinical utility, indicating potential for data-driven treatment decisions in DLBCL.