Predicting prostate cancer specific-mortality with artificial intelligence-based Gleason grading.
Prognostic markers
Prostate cancer
Journal
Communications medicine
ISSN: 2730-664X
Titre abrégé: Commun Med (Lond)
Pays: England
ID NLM: 9918250414506676
Informations de publication
Date de publication:
2021
2021
Historique:
received:
15
03
2021
accepted:
05
05
2021
entrez:
23
5
2022
pubmed:
24
5
2022
medline:
24
5
2022
Statut:
epublish
Résumé
Gleason grading of prostate cancer is an important prognostic factor, but suffers from poor reproducibility, particularly among non-subspecialist pathologists. Although artificial intelligence (A.I.) tools have demonstrated Gleason grading on-par with expert pathologists, it remains an open question whether and to what extent A.I. grading translates to better prognostication. In this study, we developed a system to predict prostate cancer-specific mortality via A.I.-based Gleason grading and subsequently evaluated its ability to risk-stratify patients on an independent retrospective cohort of 2807 prostatectomy cases from a single European center with 5-25 years of follow-up (median: 13, interquartile range 9-17). Here, we show that the A.I.'s risk scores produced a Our results suggest that A.I.-based Gleason grading can lead to effective risk stratification, and warrants further evaluation for improving disease management.
Sections du résumé
Background
UNASSIGNED
Gleason grading of prostate cancer is an important prognostic factor, but suffers from poor reproducibility, particularly among non-subspecialist pathologists. Although artificial intelligence (A.I.) tools have demonstrated Gleason grading on-par with expert pathologists, it remains an open question whether and to what extent A.I. grading translates to better prognostication.
Methods
UNASSIGNED
In this study, we developed a system to predict prostate cancer-specific mortality via A.I.-based Gleason grading and subsequently evaluated its ability to risk-stratify patients on an independent retrospective cohort of 2807 prostatectomy cases from a single European center with 5-25 years of follow-up (median: 13, interquartile range 9-17).
Results
UNASSIGNED
Here, we show that the A.I.'s risk scores produced a
Conclusions
UNASSIGNED
Our results suggest that A.I.-based Gleason grading can lead to effective risk stratification, and warrants further evaluation for improving disease management.
Identifiants
pubmed: 35602201
doi: 10.1038/s43856-021-00005-3
pii: 5
pmc: PMC9053226
doi:
Types de publication
Journal Article
Langues
eng
Pagination
10Informations de copyright
© The Author(s) 2021.
Déclaration de conflit d'intérêts
Competing interestsE.W., K.N., M.S., M.M., F.T., Y.C., M.C.S., G.S.C., L.H.P., P-H.C.C., D.F.S., Y.L., and C.H.M are current or past employees of Google LLC, own Alphabet stock, and are coinventors on patents (in various stages) for machine learning using medical images. T.B., I.F-A., and M.B.A. are current or past consultants of Google LLC. M.P., R.R., F.N., H.M., P.R., A.H., and K.Z. are employees of the Medical University of Graz.
Références
Histopathology. 2006 May;48(6):644-54
pubmed: 16681679
Eur Urol. 2013 Aug;64(2):193-8
pubmed: 23522911
Future Oncol. 2009 Dec;5(10):1555-84
pubmed: 20001796
Nat Commun. 2019 Dec 18;10(1):5642
pubmed: 31852890
Int Urol Nephrol. 1996;28(1):73-7
pubmed: 8738623
JAMA Oncol. 2020 Sep 1;6(9):1372-1380
pubmed: 32701148
Eur Urol. 2016 Mar;69(3):428-35
pubmed: 26166626
Eur Urol. 2018 Feb;73(2):168-175
pubmed: 28400167
PLoS One. 2016 Jan 05;11(1):e0146189
pubmed: 26731672
JAMA Netw Open. 2020 Nov 2;3(11):e2023267
pubmed: 33180129
Lancet Oncol. 2020 Feb;21(2):222-232
pubmed: 31926806
JAMA Oncol. 2020 Dec 1;6(12):1912-1920
pubmed: 33090219
J Urol. 2009 Mar;181(3):956-62
pubmed: 19167731
Hum Pathol. 2001 Jan;32(1):74-80
pubmed: 11172298
Eur Urol. 2018 May;73(5):674-683
pubmed: 28117112
Eur Urol. 2015 Nov;68(5):768-74
pubmed: 25896124
Cancers (Basel). 2019 Nov 25;11(12):
pubmed: 31769420
Lancet. 2012 Dec 8;380(9858):2018-27
pubmed: 23084481
JAMA. 1982 May 14;247(18):2543-6
pubmed: 7069920
JAMA. 2006 Nov 15;296(19):2329-35
pubmed: 17105795
NPJ Digit Med. 2019 Oct 18;2:100
pubmed: 31646182
Eur Urol. 2016 Apr;69(4):592-598
pubmed: 26542947
Eur Urol. 2016 Aug;70(2):248-53
pubmed: 26525839
Urol J. 2012 Spring;9(2):486-90
pubmed: 22641492
J Clin Oncol. 2009 Jun 20;27(18):2924-30
pubmed: 19433689
Histopathology. 2012 Jan;60(1):59-74
pubmed: 22212078
J Urol. 2019 Sep;202(3):533-538
pubmed: 31042111
Virchows Arch. 2006 Oct;449(4):428-34
pubmed: 16941153
Int Braz J Urol. 2007 Sep-Oct;33(5):639-46; discussion 647-51
pubmed: 17980061
Mod Pathol. 2021 Mar;34(3):660-671
pubmed: 32759979
Lancet. 2018 May 12;391(10133):1927-1938
pubmed: 29550029
Lancet Oncol. 2020 Feb;21(2):233-241
pubmed: 31926805
BJU Int. 2009 Jun;103(12):1647-54
pubmed: 19154461
J Natl Compr Canc Netw. 2019 May 1;17(5):479-505
pubmed: 31085757
Eur Urol. 2013 Aug;64(2):199-201; discussion 202-3
pubmed: 23608669
NPJ Digit Med. 2019 Jun 7;2:48
pubmed: 31304394
Histopathology. 2013 Jan;62(2):247-56
pubmed: 23240715