Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Oct;34(10):1025-1034.
doi: 10.5152/tjg.2023.22346.

Predicting Duodenal Cancer Risk in Patients with Familial Adenomatous Polyposis Using Machine Learning Model

Sami Akbulut  1 , Zeynep Küçükakçalı  2 , Cemil Çolak  2
Affiliations

Predicting Duodenal Cancer Risk in Patients with Familial Adenomatous Polyposis Using Machine Learning Model

Sami Akbulut et al. Turk J Gastroenterol. 2023 Oct.

Abstract

Background/aims: The aim of this study was to both classify data of familial adenomatous polyposis patients with and without duode- nal cancer and to identify important genes that may be related to duodenal cancer by XGboost model.

Materials and methods: The current study was performed using expression profile data from a series of duodenal samples from familial adenomatous polyposis patients to explore variations in the familial adenomatous polyposis duodenal adenoma-carcinoma sequence. The expression profiles obtained from cancerous, adenomatous, and normal tissues of 12 familial adenomatous polyposis patients with duodenal cancer and the tissues of 12 familial adenomatous polyposis patients without duodenal cancer were compared. The ElasticNet approach was utilized for the feature selection. Using 5-fold cross-validation, one of the machine learning approaches, XGboost, was utilized to classify duodenal cancer. Accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score performance metrics were assessed for model performance.

Results: According to the variable importance obtained from the modeling, ADH1C, DEFA5, CPS1, SPP1, DMBT1, VCAN-AS1, APOB genes (cancer vs. adenoma); LOC399753, APOA4, MIR548X, and ADH1C genes (adenoma vs. adenoma); SNORD123, CEACAM6, SNORD78, ANXA10, SPINK1, and CPS1 (normal vs. adenoma) genes can be used as predictive biomarkers.

Conclusions: The proposed model used in this study shows that the aforementioned genes can forecast the risk of duodenal cancer in patients with familial adenomatous polyposis. More comprehensive analyses should be performed in the future to assess the reliability of the genes determined.

PubMed Disclaimer

Conflict of interest statement

Declaration of Interests: The authors declare that they have no conflicts of interest.

Figures

Figure 1.
Figure 1.
Graph for performance metrics obtained from XGboost models.
Figure 2.
Figure 2.
The graph of variable importance values.
Figure 3.
Figure 3.
Graph for performance metrics obtained from XGboost models.
Figure 4.
Figure 4.
The graph of variable importance values.
Figure 5.
Figure 5.
Graph for performance metrics obtained from XGboost models.
Figure 6.
Figure 6.
The graph of variable importance values.
See this image and copyright information in PMC

References

    1. Leone PJ, Mankaney G, Sarvapelli S, et al. Endoscopic and histologic features associated with gastric cancer in familial adenomatous polyposis. Gastrointest Endosc. 2019;89(5):961 968. ( 10.1016/j.gie.2018.12.018) - DOI - PubMed
    1. Dinarvand P, Davaro EP, Doan JV, et al. Familial adenomatous polyposis syndrome: an update and review of extraintestinal ­manifestations. Arch Pathol Lab Med. 2019;143(11):1382 1398. ( 10.5858/arpa.2018-0570-RA) - DOI - PubMed
    1. Campos FG. Surgical treatment of familial adenomatous polyposis: dilemmas and current recommendations. World J Gastroenterol. 2014;20(44):16620 16629. ( 10.3748/wjg.v20.i44.16620) - DOI - PMC - PubMed
    1. Agüera-González S, Burton OT, Vázquez-Chávez E, et al. Adenomatous polyposis coli defines Treg differentiation and anti-inflammatory function through microtubule-mediated NFAT localization. Cell Rep. 2017;21(1):181 194. ( 10.1016/j.celrep.2017.09.020) - DOI - PubMed
    1. Kemp Bohan PM, Mankaney G, Vreeland TJ, et al. Chemoprevention in familial adenomatous polyposis: past, present and future. Fam Cancer. 2021;20(1):23 33. ( 10.1007/s10689-020-00189-y) - DOI - PMC - PubMed

MeSH terms