Using a machine learning algorithm to predict acute graft-versus-host disease following allogeneic transplantation.
Journal
Blood advances
ISSN: 2473-9537
Titre abrégé: Blood Adv
Pays: United States
ID NLM: 101698425
Informations de publication
Date de publication:
26 11 2019
26 11 2019
Historique:
received:
05
09
2019
accepted:
17
10
2019
entrez:
22
11
2019
pubmed:
22
11
2019
medline:
9
9
2020
Statut:
ppublish
Résumé
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.
Identifiants
pubmed: 31751471
pii: 428816
doi: 10.1182/bloodadvances.2019000934
pmc: PMC6880900
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
3626-3634Informations de copyright
© 2019 by The American Society of Hematology.
Références
Biol Blood Marrow Transplant. 2013 Dec;19(12):1683-9
pubmed: 24055655
Lancet Psychiatry. 2016 Jan;3(1):13-15
pubmed: 26772057
Bone Marrow Transplant. 2013 Mar;48 Suppl 1:S1-37
pubmed: 23462821
Cancer Med. 2019 Sep;8(11):5058-5067
pubmed: 31305031
Blood. 2007 Dec 15;110(13):4576-83
pubmed: 17785583
Bone Marrow Transplant. 2016 Jan;51(1):96-102
pubmed: 26367230
Int J Hematol. 2007 Oct;86(3):269-74
pubmed: 17988995
BMC Med. 2015 Jan 06;13:1
pubmed: 25563062
Bone Marrow Transplant. 2014 Mar;49(3):332-7
pubmed: 24096823
J Hematol Oncol. 2015 Sep 04;8:102
pubmed: 26337829
Biol Blood Marrow Transplant. 2011 Aug;17(8):1196-204
pubmed: 21193054
Haematologica. 2016 Oct;101(10):1260-1266
pubmed: 27354023
Ann Intern Med. 2015 Jan 6;162(1):W1-73
pubmed: 25560730
J Clin Oncol. 2015 Oct 1;33(28):3144-51
pubmed: 26240227
Nat Biotechnol. 2008 Feb;26(2):195-7
pubmed: 18259176
Int J Hematol. 2016 Jan;103(1):3-10
pubmed: 26547570
Transplantation. 1974 Oct;18(4):295-304
pubmed: 4153799
Ann Intern Med. 2011 Feb 15;154(4):290-1; author reply 291-2
pubmed: 21320945
PLoS One. 2016 Mar 04;11(3):e0150637
pubmed: 26942424
Clin Epidemiol. 2017 Mar 31;9:195-204
pubmed: 28408854
Bone Marrow Transplant. 2005 Mar;35(6):609-17
pubmed: 15696179
Lancet Haematol. 2015 Jan;2(1):e21-9
pubmed: 26687425
Biol Blood Marrow Transplant. 2015 Apr;21(4):761-7
pubmed: 25585275
Sci Rep. 2017 Aug 7;7(1):7402
pubmed: 28784991
Blood. 2015 Jul 16;126(3):415-22
pubmed: 26031916