A machine-learning approach to predict mortality due to immune-mediated thrombotic thrombocytopenic purpura

Background Mortality due to immune-mediated thrombotic thrombocytopenic purpura (iTTP) remains significant. Predicting mortality risk may potentially help individualize treatment. The French Thrombotic Microangiopathy (TMA) Reference Score has not been externally validated in the United States. Recent advances in machine-learning technology can analyze large numbers of variables with complex interactions for the development of prediction models. Methods We utilized the United States Thrombotic Microangiopathies (USTMA) iTTP database (n=419) to validate the French TMA Reference score and subsequently develop a novel prediction tool, the USTMA TTP Mortality Index. We analyzed variables available at the time of initial presentation, including demographics, symptoms, and laboratory findings. We developed our model using gradient boosting machine (GBM), a machine learning ensemble method based on classification trees, implemented in the R package gbm. Results In our cohort, the French score predicted mortality with an AUC=0.63 (95% CI: 0.50-0.77), sensitivity=0.35 and specificity=0.84. Our GBM model selected eight variables to predict acute mortality with a cross validated AUC=0.77 (95% CI: 0.71-0.82). The two cut-offs corresponded to sensitivities of 0.64 and 0.50, and specificities of 0.76 and 0.87 respectively. Conclusion The USTMA Mortality Index was acceptable for predicting mortality due to acute iTTP in the USTMA registry, but not sensitive enough to rule out death. Identifying patients at high-risk of iTTP-related mortality may help individualize care and ultimately improve iTTP survival outcomes. Further studies are needed to provide external validation. Our model is one of many recent examples where machine-learning models may show promise in clinical prediction tools in healthcare.