A machine-learning approach to human ex vivo lung perfusion predicts transplantation outcomes and promotes organ utilization.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
09 08 2023
09 08 2023
Historique:
received:
28
09
2022
accepted:
26
07
2023
medline:
11
8
2023
pubmed:
10
8
2023
entrez:
9
8
2023
Statut:
epublish
Résumé
Ex vivo lung perfusion (EVLP) is a data-intensive platform used for the assessment of isolated lungs outside the body for transplantation; however, the integration of artificial intelligence to rapidly interpret the large constellation of clinical data generated during ex vivo assessment remains an unmet need. We developed a machine-learning model, termed InsighTx, to predict post-transplant outcomes using n = 725 EVLP cases. InsighTx model AUROC (area under the receiver operating characteristic curve) was 79 ± 3%, 75 ± 4%, and 85 ± 3% in training and independent test datasets, respectively. Excellent performance was observed in predicting unsuitable lungs for transplantation (AUROC: 90 ± 4%) and transplants with good outcomes (AUROC: 80 ± 4%). In a retrospective and blinded implementation study by EVLP specialists at our institution, InsighTx increased the likelihood of transplanting suitable donor lungs [odds ratio=13; 95% CI:4-45] and decreased the likelihood of transplanting unsuitable donor lungs [odds ratio=0.4; 95%CI:0.16-0.98]. Herein, we provide strong rationale for the adoption of machine-learning algorithms to optimize EVLP assessments and show that InsighTx could potentially lead to a safe increase in transplantation rates.
Identifiants
pubmed: 37558674
doi: 10.1038/s41467-023-40468-7
pii: 10.1038/s41467-023-40468-7
pmc: PMC10412608
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4810Informations de copyright
© 2023. Springer Nature Limited.
Références
Clin Transplant. 2020 Jul;34(7):e13870
pubmed: 32271967
N Engl J Med. 2011 Apr 14;364(15):1431-40
pubmed: 21488765
Transplantation. 2022 Apr 1;106(4):702-704
pubmed: 34144553
J Heart Lung Transplant. 2017 Jun 21;:
pubmed: 28689646
Ann Thorac Surg. 2021 Apr;111(4):1156-1163
pubmed: 32890490
Am J Surg. 2022 Jul;224(1 Pt B):437-442
pubmed: 34980465
Am J Transplant. 2017 May;17(5):1396-1404
pubmed: 27977885
J Heart Lung Transplant. 2015 Jun;34(6):849-57
pubmed: 25907141
J Heart Lung Transplant. 2021 Jul;40(7):687-695
pubmed: 33781664
Am J Respir Crit Care Med. 2022 Apr 15;205(8):873-882
pubmed: 35044901
J Heart Lung Transplant. 2017 Sep;36(9):985-995
pubmed: 28551353
Am J Transplant. 2009 Oct;9(10):2262-9
pubmed: 19663886
Eur J Cardiothorac Surg. 2017 Mar 1;51(3):577-586
pubmed: 28082471
J Med Syst. 2017 Dec 23;42(2):25
pubmed: 29273867
JAMA Surg. 2019 Dec 1;154(12):1143-1150
pubmed: 31596484
World J Transplant. 2014 Jun 24;4(2):40-2
pubmed: 25032094
JTCVS Open. 2020 May 13;3:164-168
pubmed: 36003866
Am J Transplant. 2021 Nov;21(11):3704-3713
pubmed: 33872459
Am J Transplant. 2013 Jun;13(6):1441-9
pubmed: 23668775
J Heart Lung Transplant. 2008 Dec;27(12):1319-25
pubmed: 19059112
Eur Respir J. 2019 Apr 4;53(4):
pubmed: 30655281
Nat Rev Gastroenterol Hepatol. 2022 Mar;19(3):199-209
pubmed: 34997204
Clin Transplant. 2022 Apr;36(4):e14570
pubmed: 34954872
J Thorac Dis. 2021 Dec;13(12):6963-6975
pubmed: 35070380
J Thorac Dis. 2019 Apr;11(4):1635-1650
pubmed: 31179109
Transplantation. 2016 Sep;100(9):1862-70
pubmed: 27479157
J Heart Lung Transplant. 2017 Oct;36(10):1097-1103
pubmed: 28942784
Lancet. 2015 Jun 27;385(9987):2577-84
pubmed: 25888086
J Heart Lung Transplant. 2012 Oct;31(10):1120-6
pubmed: 22975103
Ann Surg. 2015 Mar;261(3):591-7
pubmed: 25371129
J Vis Exp. 2015 Jul 15;(101):e52909
pubmed: 26275014
J Thorac Cardiovasc Surg. 2021 Aug;162(2):490-499.e2
pubmed: 32928548
Int J Mol Sci. 2021 May 13;22(10):
pubmed: 34068301
Transplantation. 2020 May;104(5):947-955
pubmed: 31815900
J Thorac Cardiovasc Surg. 2012 Nov;144(5):1200-6
pubmed: 22944089
J Thorac Dis. 2021 Nov;13(11):6602-6617
pubmed: 34992839