Treffer: Establishment and validation of a diagnostic model for cholangiocarcinoma based on LightGBM machine-learning algorithm.

Title:
Establishment and validation of a diagnostic model for cholangiocarcinoma based on LightGBM machine-learning algorithm.
Authors:
Zhang Z; Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, P.R. China., Geng X; Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, P.R. China., Yin M; Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, P.R. China., Liang Y; Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, P.R. China., Zheng G; Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, P.R. China. zhengg@sdu.edu.cn.; Shandong Engineering Research Center of Biomarker and Artificial Intelligence Application, Jinan, China. zhengg@sdu.edu.cn.
Source:
Scientific reports [Sci Rep] 2025 Dec 02; Vol. 16 (1), pp. 933. Date of Electronic Publication: 2025 Dec 02.
Publication Type:
Journal Article; Validation Study
Language:
English
Journal Info:
Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s):
Original Publication: London : Nature Publishing Group, copyright 2011-
MeSH Terms:
Cholangiocarcinoma*/diagnosis , Cholangiocarcinoma*/genetics , Cholangiocarcinoma*/metabolism , Machine Learning* , Bile Duct Neoplasms*/diagnosis , Bile Duct Neoplasms*/genetics, Humans ; Gene Expression Regulation, Neoplastic ; Gene Expression Profiling ; Algorithms ; Female ; Male ; Biomarkers, Tumor/genetics ; ROC Curve ; Transcriptome ; Protein Interaction Maps ; Middle Aged ; Gene Regulatory Networks ; Boosting Machine Learning Algorithms
References:
J Exp Med. 2021 Oct 4;218(10):. (PMID: 34495298)
Brief Bioinform. 2024 Mar 27;25(3):. (PMID: 38752857)
Front Immunol. 2023 Mar 17;14:1178075. (PMID: 37006232)
Hepatology. 2023 Apr 1;77(4):1287-1302. (PMID: 35735979)
Blood. 2010 Nov 25;116(22):4395-403. (PMID: 20625009)
Sci Rep. 2019 Apr 18;9(1):6272. (PMID: 31000751)
PLoS One. 2017 Dec 22;12(12):e0190179. (PMID: 29272308)
BMC Genomics. 2016 Jun 29;17 Suppl 3:437. (PMID: 27357396)
Nat Immunol. 2010 Sep;11(9):785-97. (PMID: 20720586)
Front Immunol. 2023 Jun 27;14:1213629. (PMID: 37441069)
J Hepatol. 2022 Sep;77(3):849-864. (PMID: 35594992)
Research (Wash D C). 2024 Sep 25;7:0487. (PMID: 39324017)
J Med Internet Res. 2022 Aug 9;24(8):e38082. (PMID: 35943767)
Trends Immunol. 2007 Apr;28(4):184-92. (PMID: 17336159)
Arch Immunol Ther Exp (Warsz). 2010 Feb;58(1):77-80. (PMID: 20049650)
Neural Netw. 2025 Jan;181:106885. (PMID: 39546876)
Hum Pathol. 2004 Jul;35(7):881-6. (PMID: 15257553)
Nat Rev Gastroenterol Hepatol. 2020 Sep;17(9):557-588. (PMID: 32606456)
Hum Gene Ther. 2023 Sep;34(17-18):917-926. (PMID: 37350098)
Front Immunol. 2015 Jul 27;6:368. (PMID: 26284063)
Cell. 2018 Sep 6;174(6):1559-1570.e22. (PMID: 30100185)
Wiley Interdiscip Rev Nanomed Nanobiotechnol. 2019 Mar;11(2):e1528. (PMID: 29700990)
Comput Biol Med. 2023 May;157:106724. (PMID: 36898287)
Thyroid. 2005 Mar;15(3):210-21. (PMID: 15785240)
ACS Sens. 2025 Apr 25;10(4):3123-3133. (PMID: 40241481)
Eur J Med Res. 2023 Jun 14;28(1):190. (PMID: 37312170)
Int J Cardiol. 2022 Jul 1;358:59-64. (PMID: 35483478)
J Intern Med. 2022 Aug;292(2):278-295. (PMID: 35426190)
Theranostics. 2019 Feb 28;9(6):1714-1727. (PMID: 31037133)
Arterioscler Thromb Vasc Biol. 2009 Jan;29(1):40-6. (PMID: 19008531)
Ecotoxicol Environ Saf. 2025 Jan 15;290:117570. (PMID: 39721423)
EClinicalMedicine. 2025 Jul 17;86:103365. (PMID: 40727008)
Dialogues Clin Neurosci. 2025 Dec;27(1):24-33. (PMID: 40114582)
Nucleic Acids Res. 2016 Jan 4;44(D1):D457-62. (PMID: 26476454)
Cancer Cell Int. 2021 May 21;21(1):270. (PMID: 34020642)
J Leukoc Biol. 2004 Jan;75(1):135-42. (PMID: 14525962)
Semin Cancer Biol. 2013 Jun;23(3):190-9. (PMID: 23287459)
Blood. 2020 Sep 3;136(10):1155-1160. (PMID: 32573723)
Clin Exp Immunol. 2010 Sep;161(3):471-9. (PMID: 20636398)
PLoS One. 2017 Jun 15;12(6):e0179213. (PMID: 28617824)
Gastroenterol Rep (Oxf). 2019 Apr 21;7(5):354-360. (PMID: 31687155)
Cancer Cell. 2011 Sep 13;20(3):300-14. (PMID: 21907922)
BMC Cancer. 2015 Jun 09;15:459. (PMID: 26054405)
Hepatology. 2022 Dec;76(6):1617-1633. (PMID: 35030285)
Nucleic Acids Res. 2000 Jan 1;28(1):27-30. (PMID: 10592173)
Curr Opin Gastroenterol. 2020 Mar;36(2):70-76. (PMID: 31895228)
Crit Rev Food Sci Nutr. 2025;65(10):1878-1893. (PMID: 38351493)
Essays Biochem. 2020 Oct 8;64(4):607-647. (PMID: 32830223)
EBioMedicine. 2021 May;67:103375. (PMID: 33993051)
Comput Methods Programs Biomed. 2019 Sep;178:47-58. (PMID: 31416562)
J Med Internet Res. 2023 Nov 15;25:e47664. (PMID: 37966870)
Nat Rev Gastroenterol Hepatol. 2023 Jun;20(6):349-365. (PMID: 36697706)
Cancer. 2023 Jan 15;129(2):184-214. (PMID: 36382577)
Int J Surg. 2025 Oct 1;111(10):6867-6884. (PMID: 40576176)
Grant Information:
82172347 National Natural Science Foundation of China; tstp20221156 Taishan scholar program of Shandong Province
Contributed Indexing:
Keywords: Cholangiocarcinoma; Diagnostic model; Immune cell infiltration; Machine-learning algorithm; WGCNA
Substance Nomenclature:
0 (Biomarkers, Tumor)
Entry Date(s):
Date Created: 20251202 Date Completed: 20260108 Latest Revision: 20260111
Update Code:
20260111
PubMed Central ID:
PMC12783296
DOI:
10.1038/s41598-025-30431-5
PMID:
41331315
Database:
MEDLINE

Weitere Informationen

The escalating annual death toll attributed to Cholangiocarcinoma (CCA) is, in part, a consequence of delayed diagnosis. This study developed an optimal CCA diagnostic model through the application of 11 machine-learning algorithms. Initially, 105 differentially expressed genes (DEGs) were identified by analyzing gene expression profiles from 307 CCA tumor tissues and 124 adjacent non-tumor tissues. WGCNA, F-test, characteristic importance, and Lasso regression analysis were employed to identify key DEGs, including APOF, DIO1, APOM, and OTC. Subsequently, diagnostic models were constructed based on APOF, DIO1, and OTC using 11 machine-learning algorithms. The LightGBM algorithm was determined as the optimal model through ROC curve analysis and machine learning performance evaluation, achieving an AUC of 0.84, with accuracy, precision, and recall values of 0.80, 0.83, and 0.90, respectively. Subsequent analyses included gene enrichment, protein-protein interaction (PPI), and CCA-related drug assessments. Additionally, the study revealed an imbalance in immune cell infiltration in CCA and identified CCL16 as a chemokine involved in immunoregulation. RT-qPCR confirmed that APOF, DIO1, and OTC were significantly downregulated in CCA tumor tissues. In conclusion, this research provides new directions for the diagnosis and immunotherapy of this disease.
(© 2025. The Author(s).)

Declarations. Competing interests: The authors declare no competing interests.