Application of Data Mining Technology in the Screening for Gallbladder Stones: A Cross-Sectional Retrospective Study of Chinese Adults
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: The purpose of this study was to use data mining methods to establish a simple and reliable predictive model based on the risk factors related to gallbladder stones (GS) to assist in their diagnosis and reduce medical costs. Materials and Methods: This was a retrospective cross-sectional study. A total of 4215 participants underwent annual health ex aminations between January 2019 and December 2019 at the Physical Examination Center of Shengjing Hospital Affiliated to Chi na Medical University. After rigorous data screening, the records of 2105 medical examiners were included for the construction of J48, multilayer perceptron (MLP), Bayes Net, and Naïve Bayes algorithms. A ten-fold cross-validation method was used to verify the recognition model and determine the best classification algorithm for GS. Results: The performance of these models was evaluated using metrics of accuracy, precision, recall, F-measure, and area under the receiver operating characteristic curve. Comparison of the F-measure for each algorithm revealed that the F-measure values for MLP and J48 (0.867 and 0.858, respectively) were not statistically significantly different (p>0.05), although they were significantly higher than the F-measure values for Bayes Net and Naïve Bayes (0.824 and 0.831, respectively; p<0.05). Conclusion: The results of this study showed that MLP and J48 algorithms are effective at screening individuals for the risk of GS. The key attributes of data mining can further promote the prevention of GS through targeted community intervention, improve the outcome of GS, and reduce the burden on the medical system.
Abstract
Purpose: The purpose of this study was to use data mining methods to establish a simple and reliable predictive model based on the risk factors related to gallbladder stones (GS) to assist in their diagnosis and reduce medical costs. Materials and Methods: This was a retrospective cross-sectional study. A total of 4215 participants underwent annual health ex aminations between January 2019 and December 2019 at the Physical Examination Center of Shengjing Hospital Affiliated to Chi na Medical University. After rigorous data screening, the records of 2105 medical examiners were included for the construction of J48, multilayer perceptron (MLP), Bayes Net, and Naïve Bayes algorithms. A ten-fold cross-validation method was used to verify the recognition model and determine the best classification algorithm for GS. Results: The performance of these models was evaluated using metrics of accuracy, precision, recall, F-measure, and area under the receiver operating characteristic curve. Comparison of the F-measure for each algorithm revealed that the F-measure values for MLP and J48 (0.867 and 0.858, respectively) were not statistically significantly different (p>0.05), although they were significantly higher than the F-measure values for Bayes Net and Naïve Bayes (0.824 and 0.831, respectively; p<0.05). Conclusion: The results of this study showed that MLP and J48 algorithms are effective at screening individuals for the risk of GS. The key attributes of data mining can further promote the prevention of GS through targeted community intervention, improve the outcome of GS, and reduce the burden on the medical system.
참고문헌 (26)
- Miao YG, "Research progress on causes and treatment of cholecystolithiasis", J Hepatopancreatobiliary Surg, 28, pp.155~157 (2016)
- European Association for the Study of the Liver(EASL), "EASL clinical practice guidelines on the prevention, diagnosis and treatment of gallstones", J Hepatol, 65, pp.146~181 (2016)
- Wang Y, "Role of the biliary microbiome in gallstone disease", Expert Rev Gastroenterol Hepatol, 12, pp.1193~1205 (2018)
- Everhart JE, "Burden of digestive diseases in the United States part I : overall and upper gastrointestinal diseases", Gastroenterology, 136, pp.376~386 (2009)
- Gellert-Kristensen H, "Identification and replication of six loci associated with gallstone disease", Hepatology, 70, pp.597~609 (2019)
- Littlefield A, "Cholelithiasis : presentation and management", J Midwifery Womens Health, 64, pp.289~297 (2019)
- Kodama I, "Gallstones and gallbladder disorder after gastrectomy for gastric cancer", Int Surg, 81, pp.36~39 (1996)
- Chen LA, "Using data mining strategies in clinical decision making : a literature review", Comput Inform Nurs, 34, pp.448~454 (2016)
- He KY, "Big data analytics for genomic medicine", Int J Mol Sci, 18, pp.412~ (2017)
- Thuluvath PJ, "Reply to : "NASHrelated and cryptogenic cirrhosis similarities extend beyond cirrhosis" : cryptogenic cirrhosis should not be equated with NASH cirrhosis based on UNOS data mining and Bayesian ‘doctrine of chances’", J Hepatol, 69, pp.973~975 (2018)
- Liu MM, "Application of data mining methods to improve screening for the risk of early gastric cancer", BMC Med Inform Decis Mak, 18(Suppl 5), pp.121~ (2018)
- Gurwitz D, "Dual pathways in muscarinic receptor stimulation of phosphoinositide hydrolysis", Biochemistry, 26, pp.633~638 (1987)
- Hauben M, "Application of an empiric Bayesian data mining algorithm to reports of pancreatitis associated with atypical antipsychotics", Pharmacotherapy, 24, pp.1122~1129 (2004)
- Akmese OF, "The use of machine learning approaches for the diagnosis of acute appendicitis", Emerg Med Int, 2020, pp.7306435~ (2020)
- Fatemian AS, "Predictive factors of advanced colonic adenomas and cancer using data mining", Middle East J Dig Dis, 11, pp.192~198 (2019)
- Chen CH, "Prevalence and risk factors of gallstone disease in an adult population of Taiwan : an epidemiological survey", J Gastroenterol Hepatol, 21, pp.1737~1743 (2006)
- Montaño Moreno JJ, "Artificial neural networks applied to forecasting time series", Psicothema, 23, pp.322~329 (2011)
- Bou Assi E, "Bispectrum features and multilayer perceptron classifier to enhance seizure prediction", Sci Rep, 8, pp.15491~ (2018)
- Balakrishnan U, "A hybrid PSO-DEFS based feature selection for the identification of diabetic retinopathy", Curr Diabetes Rev, 11, pp.182~190 (2015)
- Liu HY, "Research on Performance Evaluation on Excessive Medical Treatment Based on Multi-layer Perceptron Net-work", Chinese Hospital Management, 37, pp.27~29 (2017)
- Amini P, "Evaluating the high risk groups for suicide : a comparison of logistic regression, support vector machine, decision tree and artificial neural network", Iran J Public Health, 45, pp.1179~1187 (2016)
- Ramezankhani A, "Applying decision tree for identification of a low risk population for type 2 diabetes. Tehran lipid and glucose study", Diabetes Res Clin Pract, 105, pp.391~398 (2014)
- Shaffer EA, "Epidemiology and risk factors for gallstone disease : has the paradigm changed in the 21st century?", Curr Gastroenterol Rep, 7, pp.132~140 (2005)
- Stinton LM, "Epidemiology of gallbladder disease : cholelithiasis and cancer", Gut Liver, 6, pp.172~187 (2012)
- Aune D, "Body mass index, abdominal fatness and the risk of gallbladder disease", Eur J Epidemiol, 30, pp.1009~1019 (2015)
- Shabanzadeh DM, "Determinants for gallstone formation-a new data cohort study and a systematic review with meta-analysis", Scand J Gastroenterol, 51, pp.1239~1248 (2016)