Interpretable prognostic modeling of endometrial cancer.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
13 12 2022
13 12 2022
Historique:
received:
07
09
2022
accepted:
09
12
2022
entrez:
13
12
2022
pubmed:
14
12
2022
medline:
16
12
2022
Statut:
epublish
Résumé
Endometrial carcinoma (EC) is one of the most common gynecological cancers in the world. In this work we apply Cox proportional hazards (CPH) and optimal survival tree (OST) algorithms to the retrospective prognostic modeling of disease-specific survival in 842 EC patients. We demonstrate that linear CPH models are preferred for the EC risk assessment based on clinical features alone, while interpretable, non-linear OST models are favored when patient profiles can be supplemented with additional biomarker data. We show how visually interpretable tree models can help generate and explore novel research hypotheses by studying the OST decision path structure, in which L1 cell adhesion molecule expression and estrogen receptor status are correctly indicated as important risk factors in the p53 abnormal EC subgroup. To aid further clinical adoption of advanced machine learning techniques, we stress the importance of quantifying model discrimination and calibration performance in the development of explainable clinical prediction models.
Identifiants
pubmed: 36513790
doi: 10.1038/s41598-022-26134-w
pii: 10.1038/s41598-022-26134-w
pmc: PMC9747711
doi:
Substances chimiques
Biomarkers, Tumor
0
Neural Cell Adhesion Molecule L1
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
21543Informations de copyright
© 2022. The Author(s).
Références
Biom J. 2006 Dec;48(6):1029-40
pubmed: 17240660
J Clin Epidemiol. 2010 Jul;63(7):721-7
pubmed: 20338724
Stat Med. 2011 Feb 20;30(4):377-99
pubmed: 21225900
Front Med (Lausanne). 2022 Mar 04;9:851890
pubmed: 35308550
Sci Rep. 2021 Jun 29;11(1):13505
pubmed: 34188098
Mod Pathol. 2015 Jun;28(6):836-44
pubmed: 25720322
Int J Methods Psychiatr Res. 2011 Mar;20(1):40-9
pubmed: 21499542
BMJ. 2022 May 24;377:e069249
pubmed: 35609902
Circ Cardiovasc Qual Outcomes. 2019 May;12(5):e004879
pubmed: 31043064
Public Health. 2018 Nov;164:1-6
pubmed: 30149185
Cancers (Basel). 2021 Mar 23;13(6):
pubmed: 33806979
Sci Rep. 2021 Mar 26;11(1):6968
pubmed: 33772109
J Surg Oncol. 2015 May;111(6):790-4
pubmed: 25900897
Br J Cancer. 2015 Jul 14;113(2):299-310
pubmed: 26172027
Korean J Radiol. 2021 Oct;22(10):1697-1707
pubmed: 34269532
Cancer. 2017 Mar 1;123(5):802-813
pubmed: 28061006
PLoS Med. 2013;10(7):e1001491
pubmed: 23935462
Acta Oncol. 2021 Jul;60(7):897-903
pubmed: 33905297
J Pathol Clin Res. 2017 Oct 14;3(4):279-293
pubmed: 29085668
J Clin Epidemiol. 2019 Jun;110:12-22
pubmed: 30763612
Stat Med. 2020 Sep 20;39(21):2714-2742
pubmed: 32548928
Front Artif Intell. 2020 Nov 24;3:539879
pubmed: 33733200
Biometrics. 1974 Mar;30(1):89-99
pubmed: 4813387
Cochrane Database Syst Rev. 2014 Dec 22;(12):ED000095
pubmed: 25549990
JAMA. 2017 Oct 10;318(14):1377-1384
pubmed: 29049590
J Clin Epidemiol. 2016 Jun;74:167-76
pubmed: 26772608
Stat Med. 2009 Jul 10;28(15):1982-98
pubmed: 19452569
Diagn Progn Res. 2022 Jul 7;6(1):13
pubmed: 35794668
Cancers (Basel). 2022 Feb 12;14(4):
pubmed: 35205661
Gynecol Oncol. 2021 Jun;161(3):787-794
pubmed: 33858677
Gynecol Oncol. 2021 May;161(2):573-580
pubmed: 33551200
J Clin Epidemiol. 2016 Jan;69:245-7
pubmed: 25981519
Ann Intern Med. 2015 Jan 6;162(1):55-63
pubmed: 25560714
JAMA Netw Open. 2020 Sep 1;3(9):e2018327
pubmed: 32986110
Mod Pathol. 2016 Feb;29(2):174-81
pubmed: 26743472
Ann Oncol. 2016 Jan;27(1):16-41
pubmed: 26634381
Int J Gynecol Cancer. 2021 Jan;31(1):12-39
pubmed: 33397713
Stat Med. 1999 Sep 15-30;18(17-18):2529-45
pubmed: 10474158
BMC Med Res Methodol. 2022 Jan 13;22(1):12
pubmed: 35026997
J Natl Cancer Inst. 2013 Aug 7;105(15):1142-50
pubmed: 23781004