Prediction of allogeneic hematopoietic stem-cell transplantation mortality 100 days after transplantation using a machine learning algorithm: A European group for blood and marrow transplantation acute leukemia working party retrospective data mining study

Roni Shouval, Myriam Labopin, Ori Bondi, Hila Mishan-Shamay, Avichai Shimoni, Fabio Ciceri, Jordi Esteve, Sebastian Giebel, Norbert C. Gorin, Christoph Schmid, Emmanuelle Polge, Mahmoud Aljurf, Nicolaus Kroger, Charles Craddock, Andrea Bacigalupo, Jan J. Cornelissen, Frederic Baron, Ron Unger, Arnon Nagler, Mohamad Mohty

Research output: Contribution to journalArticle

Abstract

Purpose Allogeneic hematopoietic stem-cell transplantation (HSCT) is potentially curative for acute leukemia (AL), but carries considerable risk. Machine learning algorithms, which are part of the data mining (DM) approach, may serve for transplantation-related mortality risk prediction. Patients and Methods This work is a retrospective DM study on a cohort of 28,236 adult HSCT recipients from the AL registry of the European Group for Blood and Marrow Transplantation. The primary objective was prediction of overall mortality (OM) at 100 days after HSCT. Secondary objectives were estimation of nonrelapse mortality, leukemia-free survival, and overall survival at 2 years. Donor, recipient, and procedural characteristics were analyzed. The alternating decision tree machine learning algorithm was applied for model development on 70% of the data set and validated on the remaining data. Results OM prevalence at day 100 was 13.9% (n = 3,936). Of the 20 variables considered, 10 were selected by the model for OM prediction, and several interactions were discovered. By using a logistic transformation function, the crude score was transformed into individual probabilities for 100-day OM (range, 3% to 68%). The model's discrimination for the primary objective performed better than the European Group for Blood and Marrow Transplantation score (area under the receiver operating characteristics curve, 0.701 v 0.646; P <.001). Calibration was excellent. Scores assigned were also predictive of secondary objectives. Conclusion The alternating decision tree model provides a robust tool for risk evaluation of patients with AL before HSCT, and is available online (http://bioinfo.lnx.biu.ac.il/bondi/web1.html). It is presented as a continuous probabilistic score for the prediction of day 100 OM, extending prediction to 2 years. The DM method has proved useful for clinical prediction in HSCT.

Original languageEnglish
Pages (from-to)3144-3151
Number of pages8
JournalJournal of Clinical Oncology
Volume33
Issue number28
DOIs
Publication statusPublished - Oct 1 2015

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Fingerprint Dive into the research topics of 'Prediction of allogeneic hematopoietic stem-cell transplantation mortality 100 days after transplantation using a machine learning algorithm: A European group for blood and marrow transplantation acute leukemia working party retrospective data mining study'. Together they form a unique fingerprint.

  • Cite this

    Shouval, R., Labopin, M., Bondi, O., Mishan-Shamay, H., Shimoni, A., Ciceri, F., Esteve, J., Giebel, S., Gorin, N. C., Schmid, C., Polge, E., Aljurf, M., Kroger, N., Craddock, C., Bacigalupo, A., Cornelissen, J. J., Baron, F., Unger, R., Nagler, A., & Mohty, M. (2015). Prediction of allogeneic hematopoietic stem-cell transplantation mortality 100 days after transplantation using a machine learning algorithm: A European group for blood and marrow transplantation acute leukemia working party retrospective data mining study. Journal of Clinical Oncology, 33(28), 3144-3151. https://doi.org/10.1200/JCO.2014.59.1339