Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
12 05 2022
12 05 2022
Historique:
received:
14
12
2021
accepted:
07
04
2022
entrez:
13
5
2022
pubmed:
14
5
2022
medline:
18
5
2022
Statut:
epublish
Résumé
Pancreatic necrosis is a consistent prognostic factor in acute pancreatitis (AP). However, the clinical scores currently in use are either too complicated or require data that are unavailable on admission or lack sufficient predictive value. We therefore aimed to develop a tool to aid in necrosis prediction. The XGBoost machine learning algorithm processed data from 2387 patients with AP. The confidence of the model was estimated by a bootstrapping method and interpreted via the 10th and the 90th percentiles of the prediction scores. Shapley Additive exPlanations (SHAP) values were calculated to quantify the contribution of each variable provided. Finally, the model was implemented as an online application using the Streamlit Python-based framework. The XGBoost classifier provided an AUC value of 0.757. Glucose, C-reactive protein, alkaline phosphatase, gender and total white blood cell count have the most impact on prediction based on the SHAP values. The relationship between the size of the training dataset and model performance shows that prediction performance can be improved. This study combines necrosis prediction and artificial intelligence. The predictive potential of this model is comparable to the current clinical scoring systems and has several advantages over them.
Identifiants
pubmed: 35552440
doi: 10.1038/s41598-022-11517-w
pii: 10.1038/s41598-022-11517-w
pmc: PMC9098474
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
7827Investigateurs
Szabolcs Kiss
(S)
Nelli Farkas
(N)
Zoltán Sipos
(Z)
Péter Fehérvári
(P)
László Pecze
(L)
Mária Földi
(M)
Áron Vincze
(Á)
Tamás Takács
(T)
László Czakó
(L)
Ferenc Izbéki
(F)
Adrienn Halász
(A)
Eszter Boros
(E)
József Hamvas
(J)
Márta Varga
(M)
Artautas Mickevicius
(A)
Nándor Faluhelyi
(N)
Orsolya Farkas
(O)
Szilárd Váncsa
(S)
Rita Nagy
(R)
Stefania Bunduc
(S)
Péter Jenő Hegyi
(PJ)
Katalin Márta
(K)
Katalin Borka
(K)
Attila Doros
(A)
Nóra Hosszúfalusi
(N)
László Zubek
(L)
Bálint Erőss
(B)
Zsolt Molnár
(Z)
Andrea Párniczky
(A)
Péter Hegyi
(P)
Andrea Szentesi
(A)
Judit Bajor
(J)
Szilárd Gódi
(S)
Patrícia Sarlós
(P)
József Czimmer
(J)
Imre Szabó
(I)
Gabriella Pár
(G)
Anita Illés
(A)
Roland Hágendorn
(R)
Balázs Csaba Németh
(BC)
Balázs Kui
(B)
Dóra Illés
(D)
László Gajdán
(L)
Veronika Dunás-Varga
(V)
Roland Fejes
(R)
Mária Papp
(M)
Zsuzsanna Vitális
(Z)
János Novák
(J)
Imola Török
(I)
Melania Macarie
(M)
Elena Ramírez-Maldonado
(E)
Ville Sallinen
(V)
Shamil Galeev
(S)
Barnabás Bod
(B)
Ali Tüzün Ince
(AT)
Dániel Pécsi
(D)
Péter Varjú
(P)
Márk Félix Juhász
(MF)
Klementina Ocskay
(K)
Alexandra Mikó
(A)
Zsolt Szakács
(Z)
Informations de copyright
© 2022. The Author(s).
Références
Bioinformatics. 2001 Jun;17(6):520-5
pubmed: 11395428
Gut. 2013 Jan;62(1):102-11
pubmed: 23100216
HPB Surg. 2013;2013:367581
pubmed: 24204087
J Gastroenterol Hepatol. 2021 Feb;36(2):286-294
pubmed: 33624891
Saudi J Gastroenterol. 2008 Jan;14(1):20-3
pubmed: 19568489
Physiol Rev. 2021 Oct 1;101(4):1691-1744
pubmed: 33949875
World J Gastrointest Surg. 2017 Oct 27;9(10):200-208
pubmed: 29109852
HPB (Oxford). 2004;6(3):161-8
pubmed: 18333070
Surgery. 2007 Jan;141(1):59-66
pubmed: 17188168
PLoS One. 2016 Oct 31;11(10):e0165309
pubmed: 27798670
Lancet. 2020 Sep 5;396(10252):726-734
pubmed: 32891214
J Gastroenterol Hepatol. 2021 Oct;36(10):2875-2883
pubmed: 33880797
World J Gastroenterol. 2014 Nov 21;20(43):16146-52
pubmed: 25473167
Lancet Gastroenterol Hepatol. 2016 Sep;1(1):45-55
pubmed: 28404111
Pancreatology. 2013 Jul-Aug;13(4 Suppl 2):e1-15
pubmed: 24054878
Pancreas. 2002 Apr;24(3):217-22
pubmed: 11893927
J Magn Reson Imaging. 2009 Nov;30(5):999-1004
pubmed: 19856413
J Gastroenterol Hepatol. 2021 Feb;36(2):295-298
pubmed: 33624889
World J Clin Cases. 2014 Dec 16;2(12):840-5
pubmed: 25516858
Pancreatology. 2006;6(1-2):123-31
pubmed: 16327290
Gut. 2019 Jun;68(6):1044-1051
pubmed: 29950344
Radiology. 1990 Feb;174(2):331-6
pubmed: 2296641
Ann Surg. 1989 Oct;210(4):495-503; discussion 503-4
pubmed: 2802834
Dig Endosc. 2021 Jan;33(2):231-241
pubmed: 33065754
Abdom Radiol (NY). 2020 May;45(5):1222-1231
pubmed: 31494708
Pancreatology. 2011;11(3):328-35
pubmed: 21757970
Int J Surg. 2016 Apr;28 Suppl 1:S163-71
pubmed: 26708848
Biomed Res Int. 2021 Jan 28;2021:6638919
pubmed: 33575333
Pancreatology. 2020 Jun;20(4):637-643
pubmed: 32386970
Acad Radiol. 2002 Apr;9(4):410-9
pubmed: 11942655
Ann Intern Med. 2015 Jan 6;162(1):55-63
pubmed: 25560714
Nat Med. 2021 Aug;27(8):1317-1319
pubmed: 34312557
Clin Endosc. 2017 Jul;50(4):357-365
pubmed: 28516758
Surgery. 2020 Dec;168(6):1032-1040
pubmed: 32843212
Am J Surg. 2021 May;221(5):927-934
pubmed: 32878690
Am J Gastroenterol. 2010 Feb;105(2):435-41; quiz 442
pubmed: 19861954
JGH Open. 2018 Dec 07;3(1):80-88
pubmed: 30834345
World J Gastroenterol. 2005 Oct 14;11(38):6049-52
pubmed: 16273623
Dig Dis Sci. 2019 Jul;64(7):1985-2005
pubmed: 31161524
Gastroenterology. 2020 Jan;158(1):67-75.e1
pubmed: 31479658