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.

Racial and Ethnic Differences in Distress, Depression, and Quality of Life in people with hemophilia.

Hemophilia-related distress (HRD) has been shown to be higher among those with lower educational attainment, but potential racial/ethnic differences have not been previously described. Thus, we examined HRD according to race/ethnicity. This cross-sectional study was a planned secondary analysis of the hemophilia-related distress questionnaire (HRDq) validation study data. Adults aged ≥ 18 years with Hemophilia A or B were recruited from one of two hemophilia treatment centers between July 2017-December 2019. HRDq scores can range from 0-120, and higher scores indicate higher distress. Self-reported race/ethnicity was grouped as Hispanic, non-Hispanic White (NHW) and non-Hispanic Black (NHB). Unadjusted and multivariable linear regression models were used to examine mediators of race/ethnicity and HRDq scores. Among 149 participants enrolled, 143 completed the HRDq and were included in analyses. Approximately 17.5% of participants were NHB, 9.1% were Hispanic and 72.0% were NHW. HRDq scores ranged from 2 to 83, with a mean of 35.1 [standard deviation (SD) = 16.5]. Average HRDq scores were significantly higher among NHB participants (mean = 42.6,SD = 20.6; p-value = .038) and similar in Hispanic participants (mean = 33.8,SD = 16.7, p-value = .89) compared to NHW (mean = 33.2,SD = 14.9) participants. In multivariable models, differences between NHB vs NHW participants persisted when adjusting for inhibitor status, severity, and target joint. However, after household income was adjusted for, differences in HRDq scores were no longer statistically significant (ß = 6.0 SD = 3.7; p-value = .10). NHB participants reported higher HRD than NHW participants. Household income mediated higher distress scores in NHB compared to NHW participants, highlighting the urgent need to understand social determinants of health and financial hardship in persons with hemophilia.

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.

Peritransplantation Red Blood Cell Transfusion Is Associated with Increased Risk of Graft-versus-Host Disease after Allogeneic Hematopoietic Stem Cell Transplantation.

More than 90% of allogeneic hematopoietic stem cell transplantation (allo-HSCT) recipients receive red blood cell (RBC) or platelet transfusions in the peritransplantation period. We tested the hypothesis that transfusions are associated with the development of severe (grade III-IV) acute graft-versus-host disease (aGVHD) or mortality after allo-HSCT in a retrospective study of 322 consecutive patients receiving an allogeneic bone marrow or granulocyte colony-stimulating factor-mobilized blood stem cell graft for a hematologic malignancy. Counting transfused RBC and platelet units between day -7 pretransplantation and day +27 post-transplantation, but excluding transfusions administered after a diagnosis of aGVHD, yielded medians of 5 RBC units and 2 platelet units transfused. Sixty-three patients (20%) developed a maximal grade III-IV aGVHD with onset up to day +150 post-transplantation (median aGVHD onset of 28 days). HLA mismatch (hazard ratio [HR], 2.4; 95% confidence interval [CI], 1.2 to 4.7; P = .01), and transfusion of more than the median number of RBC units (HR, 2.1; 95% CI, 1.1 to 3.7; P = .02) were independently associated with greater risk of grade III-IV aGVHD in a multivariable analysis model. Disease risk strata (HR, 1.7; 95% CI, 1.2 to 2.4 for high risk versus low risk; P = .005) and transfusion of more than the median number of RBC units (HR, 1.4; 95% CI, 1.0 to 2.0; P = .054) were independently associated with inferior overall survival. These data support our hypothesis that peritransplantation RBC transfusions are associated with the risk of developing severe aGVHD and worse overall survival following allo-HSCT, and suggest that strategies to reduce routine RBC transfusion may favorably reduce the incidence and severity of GVHD.

Epsilon aminocaproic acid prevents bleeding in severely thrombocytopenic patients with hematological malignancies.

BACKGROUND: Despite prophylactic platelet transfusions, bleeding remains a significant problem in thrombocytopenic patients. METHODS: The antifibrinolytic agent epsilon aminocaproic acid (EACA) was administered to 44 chronically (median duration, 273 days) and severely (platelet count, 8 × 10(9)/L; range, 1 × 10(9)/L-19 × 10(9)/L) thrombocytopenic patients with hematological malignancies. Prophylactic EACA at a dose of 1 g twice daily was orally administered for a median duration of 47 days (range, 7 days-209 days) until the platelet count recovered to > 30; × 10(9) /L. Platelets were only transfused if bleeding occurred. RESULTS: While receiving EACA, 59% of the patients did not bleed, 25% had 19 episodes of spontaneously resolving minor bleeding that did not require platelet transfusion, and 16% received a median of 4 platelet transfusions (range, 1 transfusion-8 transfusions) for 1 major traumatic and 9 spontaneous grade 2 to grade 3 bleeding (based on the World Health Organization classification of idiopathic thrombocytopenic purpura). No EACA toxicities were noted, and venous thromboses were not observed. CONCLUSIONS: EACA is well tolerated and is associated with a low risk of major bleeding in patients with hematological malignancies who are experiencing chronic severe thrombocytopenia.