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 help analyze large numbers of variables with complex interactions for the development of prediction models. Objectives: To validate the French TMA Reference Score in the United States Thrombotic Microangiopathy (USTMA) iTTP database and subsequently develop a novel mortality prediction tool, the USTMA TTP Mortality Index. Methods: We analyzed variables available at the time of initial presentation, including demographics, symptoms, and laboratory findings. We developed our model using gradient boosting machine, a machine learning ensemble method based on classification trees, implemented in the R package gbm. Results: In our cohort (n = 419), the French score predicted mortality with an area under the receiver operating characteristic curve of 0.63 (95% CI: 0.50-0.77), sensitivity of 0.35, and specificity of 0.84. Our gradient boosting machine model selected 8 variables to predict acute mortality with a cross-validated area under the receiver operating characteristic curve of 0.77 (95% CI: 0.71-0.82). The 2 cutoffs 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.

Race, rituximab, and relapse in TTP.

Immune-mediated thrombotic thrombocytopenic purpura (iTTP) is characterized by recurring episodes of thrombotic microangiopathy, causing ischemic organ impairment. Black patients are overrepresented in iTTP cohorts in the United States, but racial disparities in iTTP outcome and response to therapy have not been studied. Using the United States Thrombotic Microangiopathies Consortium iTTP Registry, we evaluated the impact of race on mortality and relapse-free survival (RFS) in confirmed iTTP in the United States from 1995 to 2020. We separately examined the impact of rituximab therapy and presentation with newly diagnosed (de novo) or relapsed iTTP on RFS by race. A total of 645 participants with 1308 iTTP episodes were available for analysis. Acute iTTP mortality did not differ by race. When all episodes of iTTP were included, Black race was associated with shorter RFS (hazard ratio [HR], 1.60; 95% CI, 1.16-2.21); the addition of rituximab to corticosteroids improved RFS in White (HR, 0.37; 95% CI, 0.18-0.73) but not Black patients (HR, 0.96; 95% CI, 0.71-1.31). In de novo iTTP, rituximab delayed relapse, but Black patients had shorter RFS than White patients, regardless of treatment. In relapsed iTTP, rituximab significantly improved RFS in White but not Black patients. Race affects overall relapse risk and response to rituximab in iTTP. Black patients may require closer monitoring, earlier retreatment, and alternative immunosuppression after rituximab treatment. How race, racism, and social determinants of health contribute to the disparity in relapse risk in iTTP deserves further study.

Transformation of a non-secretory neuroendocrine tumor to insulinoma after treatment with Sunitinib: A case report and review of the literature.

We report a case of a non-secretory neuroendocrine tumor which transformed into an insulin secreting tumor after treatment with Sunitinib. To our knowledge, this has only been described in three other cases worldwide. Previously reported case series find transformation of non-secretory neuroendocrine cancers into secretory lesions occurs in 3.4-6.8% of cases. Sunitinib is known to have the potential to lower blood glucose and induce epigenetic changes in cells of various types. We hypothesize that the mechanism for Sunitinib-induced transformation in cancer phenotype is through epigenetic changes in DNA expression within the tumor cells.