Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

Keynote webinar | Spotlight on medication adherence

LIVE: Thursday 27th June 2024, 18:00-19:30 (CEST)
Join our expert panel to discover why you need to understand the drivers of non-adherence in your patients, and how you can optimize medication adherence in your clinics to drastically improve patient outcomes.
ADVANCED SEARCH
Log in
Top
BMC Medical Informatics and Decision Making
Published in: BMC Medical Informatics and Decision Making 5/2018

Open Access 01-12-2018 | Research

Application of data mining methods to improve screening for the risk of early gastric cancer

Authors: Mi-Mi Liu, Li Wen, Yong-Jia Liu, Qiao Cai, Li-Ting Li, Yong-Ming Cai

Published in: BMC Medical Informatics and Decision Making | Special Issue 5/2018

Login to get access

Abstract

Background

Although gastric cancer is a malignancy with high morbidity and mortality in China, the survival rate of patients with early gastric cancer (EGC) is high after surgical resection. To strengthen diagnosing and screening is the key to improve the survival and life quality of patients with EGC. This study applied data mining methods to improve screening for the risk of EGC on the basis of noninvasive factors, and displayed important influence factors for the risk of EGC.

Methods

The dataset was derived from a project of the First Hospital Affiliated Guangdong Pharmaceutical University. A series of questionnaire surveys, serological examinations and endoscopy plus pathology biopsy were conducted in 618 patients with gastric diseases. Their risk of EGC was categorized into low and high risk of EGC by the results of endoscopy plus pathology biopsy. The synthetic minority oversampling technique (SMOTE) was used to solve imbalance categories of the risk of EGC. Four classification models of the risk of EGC was established, including logistic regression (LR) and three data mining algorithms.

Results

The three data mining models had higher accuracy than the LR model. Gain curves of the three data mining models were convexes more closer to ideal curves by contrast with that of the LR model. AUC of the three data mining models were larger than that of the LR model as well. The three data mining models predicted the risk of EGC more effectively in comparison with the LR model. Moreover, this study found 16 important influence factors for the risk of EGC, such as occupations, helicobacter pylori infection, drinking hot water and so on.

Conclusions

The three data mining models have optimal predictive behaviors over the LR model, therefore can effectively evaluate the risk of EGC and assist clinicians in improving the diagnosis and screening of EGC. Sixteen important influence factors for the risk of EGC were illustrated, which may helpfully assess gastric carcinogenesis, and remind to early prevention and early detection of gastric cancer. This study may also be conducive to clinical researchers in selecting and conducting the optimal predictive models.
Literature
1.
Chen WQ, Zheng RS, Zhang SW, Zeng HM, Zou XL, Hao J. Report of Cancer incidence and mortality in China, 2013. China Cancer. 2017;26:1–7.
2.
3.
4.
Wang YC, Wei LJ, Liu JT, Li SX, Wang QS. Comparison and Analysis of the incidence and mortality rate of Cancer in developed and developing countries. Chin J Clin Oncol. 2012;39:679–82.
5.
Deng GH. A review on early diagnosis of gastric cancer. Clin J Chin Med. 2017;9:146–8.
6.
Park CH, Kim EH, Chung H, Lee H, Park JC, Shin SK, Lee YC, An JY, Kim HI, Cheong JH. The optimal endoscopic screening interval for detecting early gastric neoplasms. Gastrointest Endosc. 2014;80:253–9.CrossRefPubMed
7.
Zhu P, Wu YL. The present situation and countermeasure for missed diagnosis of gastric cancer with gastroscopy in China. J Int Med Con Pract. 2015;10:158–60.
8.
Crowther PS, Cox RJ. A method for optimal division of data sets for use in neural networks. Knowledge-based intelligent information and engineering systems, Pt 4, Proceedings. 2005;3684:1–7.
9.
López V, Fernandez A, Garcia S, Palade V, Herrera F. An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Inf Sci. 2013;250:113–41.CrossRef
10.
Luengo J, Fernandez A, Garcia S, Herrera F. Addressing data complexity for imbalanced data sets: analysis of SMOTE-based oversampling and evolutionary undersampling. Soft Comput. 2011;15:1909–36.CrossRef
11.
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321–57.CrossRef
12.
Nakamura M, Kajiwara Y, Otsuka A, Kimura H. LVQ-SMOTE-learning vector quantization based synthetic minority over-sam-pling technique for biomedical data. Biodata Mining. 2013;6:1–10.CrossRef
13.
Dai HL. Class imbalance learning via a fuzzy total margin based support vector machine. Appl Soft Comput. 2015;31:172–84.CrossRef
14.
Sun T, Wu HF, Liang ZG, He W, Zhang L, Lv PX, Guo XH. Application of SMOTE arithmetic for unbalanced data. Beijing Biomed Eng. 2012;31:528–30.
15.
Chen SJ, Yang L, Wu SZ, Li J. C4.5 classification-based quantitative analysis of risk factors for respiratory diseases. Chin J Med Library Inform Sci. 2016;25:35–41.
16.
Lawrence RL, Moran CJ. The America view classification methods accuracy comparison project: a rigorous approach for model selection. Remote Sens Environ. 2015;170:115–20.CrossRef
17.
Rafe V, Farhoud SH, Rasoolzadeh S. Breast Cancer prediction by using C5.0 algorithm and BOOSTING method. J Med Imag Health Inform. 2014;4:600–4.CrossRef
18.
Madden MG. On the classification performance of TAN and general Bayesian networks. Knowl-Based Syst. 2009;22:489–95.CrossRef
19.
Browne A. Representation and extrapolation in multilayer perceptrons. Neural Comput. 2002;14:1739–54.CrossRefPubMed
20.
Kim YS. Performance evaluation for classification methods: a comparative simulation study. Expert Syst Appl. 2010;37:2292–306.CrossRef
21.
Kim YS. Comparison of the decision tree, artificial neural network, and linear regression methods based on the number and types of independent variables and sample size. Expert Syst Appl. 2008;34:1227–34.CrossRef
22.
Ture M, Tokatli F, Omurlu IK. The comparisons of prognostic indexes using data mining techniques and cox regression analysis in the breast cancer data. Expert Syst Appl. 2009;36:8247–54.CrossRef
23.
Delen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med. 2005;34:113–27.CrossRefPubMed
24.
Yamaguchi Y, Nagata Y, Hiratsuka R, Kawase Y, Tominaga T, Takeuchi S, Sakaganni S, Ishida S. Gastric Cancer screening by combined assay for serum anti-helicobacter pylori IgG antibody and serum pepsinogen levels-the ABC method. Digestion. 2016;93:13–8.CrossRefPubMed
25.
Meng WB, Bai B, Sheng L, Li Y, Yue P, Li X, Qiao L. Role of helicobacter pylori in gastric Cancer: advances and controversies. Discov Med. 2015;20:285–93.PubMed
26.
Li YX, Li XM, Zhang N, Zhang W, Chen C, Tao L, Zhao J, Li SG, Li F, Zhang WJ. Associations of helicobacter pylori infection with the pathogenesis, progression and prognosis in patients with gastric cancer. Chin J Cancer Prev Treat. 2015;22:91–4.
27.
Zou SM, Du RY, Wen D, Chen Y, Wang FH, Zhao D, Zhu N. Heavy metals pollution in vegetables grown on some farmlands around Dabaoshan mine and its HealthyRisk evaluation. J Agric Res Environ. 2016;33:568–75.
28.
Dong M, Liu HB, Wang YX, Shi WF. Analysis of water quality from homemade wells in Fangshan district. Beijing Chin J Health Lab Tec. 2016;26:2240–1.
29.
Chen L, Chen J, Zhang XZ, Xie P. A review of reproductive toxicity of microcystins. J Hazard Mater. 2016;301:381–99.CrossRefPubMed
30.
Wu ZY, Chen RF, Liu WY, Ye QY, Chen F, Wang Z, Huang GP, Xiang XQ, Zhang GB. A case-control study on the relationship of drinking water from farmland edge and digestive tract cancers. Zhejiang Prev Med. 2014;26:888–92.
31.
Malongane F, McGaw LJ, Mudau FN. The synergistic potential of various teas, herbs and therapeutic drugs in health improvement: a review. J Sci Food Agric. 2017;97:4679–89.CrossRef
32.
Cheng SL, Zhang FB, Li B. Risk factors for gastric Cancer in Chinese population: a meta-analysis. Chin J Public Health. 2017;33:1775–80.
33.
Karagulle M, Fidan E, Kavgac H, Ozdemir F. The effects of environmental and dietary factors on the development of gastric cancer. J Buon. 2014;19:1076–82.PubMed
34.
35.
36.
Yaghoobi M, Bijarchi R, Narod SA. Family history and the risk of gastric cancer. Br J Cancer. 2010;102:237–42.CrossRefPubMed
37.
38.
Sekikawa A, Fukui H, Maruo T, Tsumura T, Okabe Y, Osaki Y. Diabetes mellitus increases the risk of early gastric cancer development. Eur J Cancer. 2014;50:2065–71.CrossRefPubMed
39.
Hong JB, Zuo W, Wang AJ, Xu S, Tu LX, Chen YX, Zhu X, Lu NH. Gastric ulcer patients are more susceptible to developing gastric cancer compared with concomitant gastric and duodenal ulcer patients. Oncol Lett. 2014;8:2790–4.CrossRefPubMedPubMedCentral
40.
Ali Z, Deng Y, Ma C. Progress of research in gastric Cancer. J Nanosci Nanotechnol. 2012;12:8241–8.CrossRefPubMed
41.
Jang JS, Choi SR, Han SY, et al. Predictive significance of serum IL-6, VEGF, and CRP in gastric adenoma and mucosal carcinoma before endoscopic submucosal dissection. Kor J Gastroenterol. 2009;54:99–107.CrossRef
42.
Metadata
Title
Application of data mining methods to improve screening for the risk of early gastric cancer
Authors
Mi-Mi Liu
Li Wen
Yong-Jia Liu
Qiao Cai
Li-Ting Li
Yong-Ming Cai
Publication date
01-12-2018
Publisher
BioMed Central
DOI
https://doi.org/10.1186/s12911-018-0689-4

Other articles of this Special Issue 5/2018

BMC Medical Informatics and Decision Making 5/2018 Go to the issue

Research

Automatic gene annotation using GO terms from cellular component domain

Research

An automated pipeline for analyzing medication event reports in clinical settings

Research

A prototype of knowledge-based patient safety event reporting and learning system

Research

Primary health information standard system based on semantic interoperability

Research

A longitudinal feature selection method identifies relevant genes to distinguish complicated injury and uncomplicated injury over time

Research

SBLC: a hybrid model for disease named entity recognition based on semantic bidirectional LSTMs and conditional random fields