Search

Graft-versus-host-disease-free, relapse-free survival (GRFS) is a useful composite endpoint that measures survival without relapse or significant morbidity after allogeneic hematopoietic stem cell transplantation (allo-HSCT). We aimed to develop a novel analytical method that appropriately handles right-censored data and competing risks to understand the risk for GRFS and each component of GRFS. This study was a retrospective data-mining study on a cohort of 2207 adult patients who underwent their first allo-HSCT at the Kyoto Stem Cell Transplantation Group (KSCTG), a multi-institutional joint research group of 17 transplantation centers in Japan. The primary endpoint was GRFS. A stacked ensemble of Cox proportional hazard regression and seven machine learning algorithms was applied to develop a prediction model. The median age of patients was 48 years. For GRFS, the stacked ensemble model achieved better predictive accuracy evaluated by C-index than other top-of-the-art competing risk models (ensemble model: 0.670, Cox-PH: 0.668, Random Survival Forest: 0.660, Dynamic DeepHit: 0.646). The probability of GRFS after 2 years was 30.54% for the high-risk and 40.69% for the low-risk group, respectively (hazard ratio [HR] compared to the low-risk group: 2.127; 95% CI: 1.19-3.80). We developed a novel predictive model for survival analysis that showed superior risk stratification to existing methods using a stacked ensemble of multiple machine learning algorithms., アンサンブル学習を用いた造血幹細胞移植予後予測モデルの開発 --機械学習を用いた新規生存時間解析手法の実装--. 京都大学プレスリリース. 2021-12-28.

Transplant-associated thrombotic microangiopathy (TA-TMA) is a fatal complication of allogeneic hematopoietic stem cell transplantation (allo-HSCT). However, so far, no large cohort study determined the risk factors and the most effective therapeutic strategies for TA-TMA. Thus, the present study aimed to clarify these clinical aspects based on a large multicenter cohort. This retrospective cohort study was performed by the Kyoto Stem Cell Transplantation Group (KSCTG). A total of 2425 patients were enrolled from 14 institutions. All patients were aged ≥16 years, presented with hematological diseases, and received allo-HSCT after the year 2000. TA-TMA was observed in 121 patients (5.0%) on day 35 (median) and was clearly correlated with inferior overall survival (OS) (hazard ratio [HR], 4.93). Pre- and post-HSCT statistically significant risk factors identified by multivariate analyses included poorer performance status (HR, 1.69), HLA mismatch (HR, 2.17), acute graft-versus-host disease (aGVHD; grades 3-4) (HR, 4.02), Aspergillus infection (HR, 2.29), and veno-occlusive disease/sinusoidal obstruction syndrome (VOD/SOS; HR, 4.47). The response rate and OS significantly better with the continuation or careful reduction of calcineurin inhibitors (CNI) than the conventional treatment strategy of switching from CNI to corticosteroids (response rate, 64.7% vs 20.0%). In summary, we identified the risk factors and the most appropriate therapeutic strategies for TA-TMA. The described treatment strategy could improve the outcomes of patients with TA-TMA in the future.