Identification of a novel bile marker clusterin and a public online prediction platform based on deep learning for cholangiocarcinoma.
Cholangiocarcinoma
Clusterin
Deep learning
Diagnostic biomarker
Proteomics
Journal
BMC medicine
ISSN: 1741-7015
Titre abrégé: BMC Med
Pays: England
ID NLM: 101190723
Informations de publication
Date de publication:
08 08 2023
08 08 2023
Historique:
received:
01
03
2023
accepted:
20
07
2023
medline:
10
8
2023
pubmed:
9
8
2023
entrez:
8
8
2023
Statut:
epublish
Résumé
Cholangiocarcinoma (CCA) is a highly aggressive malignant tumor, and its diagnosis is still a challenge. This study aimed to identify a novel bile marker for CCA diagnosis based on proteomics and establish a diagnostic model with deep learning. A total of 644 subjects (236 CCA and 408 non-CCA) from two independent centers were divided into discovery, cross-validation, and external validation sets for the study. Candidate bile markers were identified by three proteomics data and validated on 635 clinical humoral specimens and 121 tissue specimens. A diagnostic multi-analyte model containing bile and serum biomarkers was established in cross-validation set by deep learning and validated in an independent external cohort. The results of proteomics analysis and clinical specimen verification showed that bile clusterin (CLU) was significantly higher in CCA body fluids. Based on 376 subjects in the cross-validation set, ROC analysis indicated that bile CLU had a satisfactory diagnostic power (AUC: 0.852, sensitivity: 73.6%, specificity: 90.1%). Building on bile CLU and 63 serum markers, deep learning established a diagnostic model incorporating seven factors (CLU, CA19-9, IBIL, GGT, LDL-C, TG, and TBA), which showed a high diagnostic utility (AUC: 0.947, sensitivity: 90.3%, specificity: 84.9%). External validation in an independent cohort (n = 259) resulted in a similar accuracy for the detection of CCA. Finally, for the convenience of operation, a user-friendly prediction platform was built online for CCA. This is the largest and most comprehensive study combining bile and serum biomarkers to differentiate CCA. This diagnostic model may potentially be used to detect CCA.
Sections du résumé
BACKGROUND
Cholangiocarcinoma (CCA) is a highly aggressive malignant tumor, and its diagnosis is still a challenge. This study aimed to identify a novel bile marker for CCA diagnosis based on proteomics and establish a diagnostic model with deep learning.
METHODS
A total of 644 subjects (236 CCA and 408 non-CCA) from two independent centers were divided into discovery, cross-validation, and external validation sets for the study. Candidate bile markers were identified by three proteomics data and validated on 635 clinical humoral specimens and 121 tissue specimens. A diagnostic multi-analyte model containing bile and serum biomarkers was established in cross-validation set by deep learning and validated in an independent external cohort.
RESULTS
The results of proteomics analysis and clinical specimen verification showed that bile clusterin (CLU) was significantly higher in CCA body fluids. Based on 376 subjects in the cross-validation set, ROC analysis indicated that bile CLU had a satisfactory diagnostic power (AUC: 0.852, sensitivity: 73.6%, specificity: 90.1%). Building on bile CLU and 63 serum markers, deep learning established a diagnostic model incorporating seven factors (CLU, CA19-9, IBIL, GGT, LDL-C, TG, and TBA), which showed a high diagnostic utility (AUC: 0.947, sensitivity: 90.3%, specificity: 84.9%). External validation in an independent cohort (n = 259) resulted in a similar accuracy for the detection of CCA. Finally, for the convenience of operation, a user-friendly prediction platform was built online for CCA.
CONCLUSIONS
This is the largest and most comprehensive study combining bile and serum biomarkers to differentiate CCA. This diagnostic model may potentially be used to detect CCA.
Identifiants
pubmed: 37553571
doi: 10.1186/s12916-023-02990-9
pii: 10.1186/s12916-023-02990-9
pmc: PMC10408060
doi:
Substances chimiques
Clusterin
0
Biomarkers, Tumor
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
294Commentaires et corrections
Type : ErratumIn
Informations de copyright
© 2023. BioMed Central Ltd., part of Springer Nature.
Références
Hepatology. 2011 Mar;53(3):875-84
pubmed: 21374660
ACS Nano. 2021 Dec 28;15(12):19522-19534
pubmed: 34813275
Nat Rev Gastroenterol Hepatol. 2020 Sep;17(9):557-588
pubmed: 32606456
Biochim Biophys Acta Rev Cancer. 2020 Aug;1874(1):188394
pubmed: 32698040
Mod Pathol. 2017 Sep;30(9):1273-1286
pubmed: 28664934
Gastroenterol Rep (Oxf). 2015 May;3(2):136-43
pubmed: 25304323
Nat Commun. 2022 May 19;13(1):2757
pubmed: 35589723
Hepatobiliary Pancreat Dis Int. 2020 Dec;19(6):515-523
pubmed: 32753331
Biochim Biophys Acta Rev Cancer. 2021 Apr;1875(2):188409
pubmed: 32827580
J Cancer. 2020 Apr 7;11(14):4073-4080
pubmed: 32368289
Gastroenterology. 2013 Dec;145(6):1215-29
pubmed: 24140396
Biochim Biophys Acta Mol Cell Biol Lipids. 2020 Sep;1865(9):158737
pubmed: 32404277
Br J Cancer. 2017 Jan;116(3):349-355
pubmed: 28081547
Hepatology. 2008 Jul;48(1):308-21
pubmed: 18536057
Cancer Res. 2021 Jul 1;81(13):3679-3692
pubmed: 33975883
Proteomics Clin Appl. 2017 Sep;11(9-10):
pubmed: 28561948
Hepatology. 2017 Oct;66(4):1125-1143
pubmed: 28555885
Lancet. 2014 Jun 21;383(9935):2168-79
pubmed: 24581682
Nat Rev Gastroenterol Hepatol. 2016 May;13(5):261-80
pubmed: 27095655
Tumour Biol. 2017 Jun;39(6):1010428317705764
pubmed: 28618946
Clin Cancer Res. 2020 Jul 1;26(13):3248-3258
pubmed: 32299821
Endoscopy. 2012 Nov;44(11):1055-8
pubmed: 23108773
Parasitol Int. 2017 Aug;66(4):479-485
pubmed: 26456596
Arch Surg. 2012 Jan;147(1):26-34
pubmed: 22250108
Scand J Gastroenterol. 2013 Apr;48(4):496-503
pubmed: 23410061
Proteomics. 2011 May;11(10):2134-8
pubmed: 21500345
J Biomed Sci. 2020 Jan 3;27(1):13
pubmed: 31900160
Liver Int. 2019 May;39 Suppl 1:19-31
pubmed: 30851228
BMC Gastroenterol. 2009 Apr 30;9:30
pubmed: 19405942
Sci Rep. 2021 Jul 21;11(1):14838
pubmed: 34290294
J Pharm Pharm Sci. 2020;23(1):65-74
pubmed: 32310756
Adv Cancer Res. 2009;105:93-113
pubmed: 19879425
Diagn Pathol. 2020 Oct 14;15(1):127
pubmed: 33054843
Nat Biomed Eng. 2020 Jul;4(7):743-753
pubmed: 32632227
Acta Radiol. 2008 Oct;49(8):855-62
pubmed: 18608012
Adv Cancer Res. 2009;105:45-61
pubmed: 19879422
Dis Markers. 2014;2014:168960
pubmed: 25574066
Cancer. 2004 Oct 1;101(7):1609-15
pubmed: 15378479
Hepatology. 2014 Sep;60(3):896-907
pubmed: 24497320
United European Gastroenterol J. 2017 Aug;5(5):668-676
pubmed: 28815030
Neoplasma. 2006;53(4):343-6
pubmed: 16830064
Cancer Lett. 2020 Feb 28;471:61-71
pubmed: 31830558
Nat Rev Gastroenterol Hepatol. 2011 Aug 02;8(9):512-22
pubmed: 21808282
BMJ. 2020 Dec 8;371:m4266
pubmed: 33293274
Int J Biochem Cell Biol. 2002 May;34(5):427-31
pubmed: 11906815
Medicina (Kaunas). 2020 Nov 16;56(11):
pubmed: 33207685
Biomark Med. 2017 Jan;11(1):11-18
pubmed: 27874286
PLoS One. 2012;7(10):e47476
pubmed: 23118872
Front Oncol. 2021 Sep 30;11:699401
pubmed: 34660269
J Ethnopharmacol. 2015 Jun 20;168:208-16
pubmed: 25849734
Biochim Biophys Acta Rev Cancer. 2021 Apr;1875(2):188500
pubmed: 33385484