Dataset Information

Using a machine learning algorithm to predict acute graft-versus-host disease following allogeneic transplantation.

ABSTRACT: Acute graft-versus-host disease (aGVHD) is 1 of the critical complications that often occurs following allogeneic hematopoietic stem cell transplantation (HSCT). Thus far, various types of prediction scores have been created using statistical calculations. The primary objective of this study was to establish and validate the machine learning-dependent index for predicting aGVHD. This was a retrospective cohort study that involved analyzing databases of adult HSCT patients in Japan. The alternating decision tree (ADTree) machine learning algorithm was applied to develop models using the training cohort (70%). The ADTree algorithm was confirmed using the hazard model on data from the validation cohort (30%). Data from 26?695 HSCT patients transplanted from allogeneic donors between 1992 and 2016 were included in this study. The cumulative incidence of aGVHD was 42.8%. Of >40 variables considered, 15 were adapted into a model for aGVHD prediction. The model was tested in the validation cohort, and the incidence of aGVHD was clearly stratified according to the categorized ADTree scores; the cumulative incidence of aGVHD was 29.0% for low risk and 58.7% for high risk (hazard ratio, 2.57). Predicting scores for aGVHD also demonstrated the link between the risk of development aGVHD and overall survival after HSCT. The machine learning algorithms produced clinically reasonable and robust risk stratification scores. The relatively high reproducibility and low impacts from the interactions among the variables indicate that the ADTree algorithm, along with the other data-mining approaches, may provide tools for establishing risk score.

SUBMITTER: Arai Y

PROVIDER: S-EPMC6880900 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using a machine learning algorithm to predict acute graft-versus-host disease following allogeneic transplantation.

Arai Yasuyuki Y Kondo Tadakazu T Fuse Kyoko K Shibasaki Yasuhiko Y Masuko Masayoshi M Sugita Junichi J Teshima Takanori T Uchida Naoyuki N Fukuda Takahiro T Kakihana Kazuhiko K Ozawa Yukiyasu Y Eto Tetsuya T Tanaka Masatsugu M Ikegame Kazuhiro K Mori Takehiko T Iwato Koji K Ichinohe Tatsuo T Kanda Yoshinobu Y Atsuta Yoshiko Y

Blood advances 20191101 22

Acute graft-versus-host disease (aGVHD) is 1 of the critical complications that often occurs following allogeneic hematopoietic stem cell transplantation (HSCT). Thus far, various types of prediction scores have been created using statistical calculations. The primary objective of this study was to establish and validate the machine learning-dependent index for predicting aGVHD. This was a retrospective cohort study that involved analyzing databases of adult HSCT patients in Japan. The alternati ...[more]

PMID: 31751471

Similar Datasets

Project description:Chronic graft-versus-host disease (cGVHD) is major cause of morbidity and mortality following allogeneic hematopoietic cell transplantation (HCT). Ixazomib is an oral, second-generation, proteasome inhibitor that has been shown in preclinical models to prevent GVHD. We conducted a phase I/II trial in 57 patients to evaluate the safety and efficacy of ixazomib administration for cGVHD prophylaxis in patients undergoing allogeneic HCT. Oral ixazomib was administered on a weekly basis for a total of 4 doses, beginning days +60 through +90, to recipients of matched related donor (MRD, n = 25) or matched unrelated donor (MUD, n = 26) allogeneic HCT in phase II portion of the study, once the recommended phase II dose of 4 mg was identified in phase I (n = 6). All patients received peripheral blood graft and standard GVHD prophylaxis of tacrolimus and methotrexate. Ixazomib administration was safe and well tolerated, with thrombocytopenia, leukopenia, gastrointestinal complaints, and fatigue the most common adverse events (>10%). In phase II (n = 51), the cumulative incidence of cGVHD at 1 year was 36% (95% confidence interval [CI], 19% to 54%) in the MRD cohort and 39% (95% CI, 21% to 56%) in the MUD cohort. One-year cumulative incidence of nonrelapse mortality (NRM) and relapse was 0% and 20% (95% CI, 8% to 36%) in the MRD cohort, respectively. In the MUD cohort, the respective NRM and relapse rates were 4% (0% to 16%) and 34% (17% to 52%). The outcomes on the study were compared post hoc with contemporaneous matched Center for International Blood and Marrow Transplant Research (CIBMTR) controls. This post hoc analysis showed no significant improvement in cGVHD rates in both the MRD (hazard ratio [HR] = 0.85, P = .64) or MUD cohorts (HR = 0.68, P = .26) on the study compared with CIBMTR controls. B cell activating factor plasma levels were significantly higher after ixazomib dosing in those who remained cGVHD free compared with those developed cGVHD. This study shows that the novel strategy of short-course oral ixazomib following allogeneic HCT is safe but did not demonstrate significant improvement in cGVHD incidence in recipients of MRD and MUD transplantation compared with matched CIBMTR controls. This study is registered at www.clinicaltrials.gov as NCT02250300.

Dataset Information

Using a machine learning algorithm to predict acute graft-versus-host disease following allogeneic transplantation.

Publications

Using a machine learning algorithm to predict acute graft-versus-host disease following allogeneic transplantation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets