Modeling serum M‐protein response for early detection of biochemical relapse in myeloma patients treated with bortezomib, lenalidomide and dexamethasone

Abstract

Abstract Multiple myeloma (MM) treatment guidelines recommend waiting for formal progression criteria (FPC) to be met before proceeding to the next line of therapy. As predicting progression may allow early switching to next‐line therapy while the disease burden is relatively low, we evaluated the predictive accuracy of a mathematical model to anticipate relapse 180 days before the FPC is met. A subset of 470/1143 patients from the IA16 dataset who were initially treated with VRd (Velcade (bortezomib), Revlimid (lenalidomide), and dexamethasone) in the CoMMpass study (NCT01454297) were randomly split 2:1 into training and testing sets. A model of M‐protein dynamics was developed using the training set and used to predict relapse probability in patients in the testing set given their response histories up to 12 or more months of treatment. The predictive accuracy of this model and M‐protein “velocity” were assessed via receiver operating characteristics (ROC) analysis. The final model was a two‐population tumor growth inhibition model with additive drug effect and transit delay compartments for cell killing. The ROC area under the curve value of relapse prediction 180 days ahead of observed relapse by FPC was 0.828 using at least 360 days of response data, which was superior to the M‐protein velocity ROC score of 0.706 under the same conditions. The model can predict future relapse from early M‐protein responses and can be used in a future clinical trial to test whether early switching to second‐line therapy results in better outcomes in MM.