Background and objective: Liver cancer is the second leading cause of death compare to other cancer in Taiwan. Many cancer patients died in developing countries because late stage at diagnosis and limited access to timely and standard treatment. Identifying attributes or risk factor of liver cancer in patients can help early detection of liver cancer. Some risk factors of liver cancer maybe a global risk factor which have same behavior in all people in population, while other risk factors of liver cancer maybe a local risk factor which behave differently among people in different cluster or different group. Data mining techniques will be used to find the risk factor of liver cancer.
Methods: Study cohorts were obtained from NHIRD of Taiwan in 2005 – 2011 and their disease history, age, sex, living place and job history were obtained as the possible risk factor. The numbers of study cohorts are 824357 patients, which consists of 2663 liver cancer patients and 821694 non liver cancer patients. Feature reduction by selecting attribute which has closest Jaccard’s distance with liver cancer was done and resulted with 32 attributes. Logistic regression was used to identify global risk factor of liver cancer. Hierarchical clustering and association rule were used to identify local risk factor of liver cancer.
Results: Potential global risk factors for liver cancer are viral hepatitis, chronic liver disease, cirrhosis, male, gastric ulcer, and diabetes mellitus. Potential local risk factors of liver cancer are cataract, essential hypertension, hypertensive heart disease, and diabetes mellitus. Diabetes mellitus is identified to be the risk factor of liver cancer in most of people, but not in all of people in population, so it is identified as both global risk factor and local risk factor. As global risk factor, viral hepatitis, chronic liver diseases and cirrhosis, male, gastric ulcer, and diabetes mellitus increased the risk of liver cancer by 5.30, 4.32, 4.62, 1.72, and 1.60 respectively.
Conclusion: This study provides the application of data mining in healthcare to found new risk factor of liver cancer. This study can assure the risk factor of liver cancer which already been identified by many prior research. This study also found new risk factor of liver cancer which is gastric ulcer. This study also proposed that risk factor of liver cancer may behave differently in different group or cluster.

Taiwan, M.o.H.a.W. Health Promotion Administration Annual Report: Promoting Your Health. 2014; Available from: www.hpa.gov.tw.
Jemal, Ahmedin, et al. "Global cancer statistics." CA: a cancer journal for clinicians 61.2 (2011): 69-90.
European Association for Study of Liver. "EASL-EORTC clinical practice guidelines: management of hepatocellular carcinoma." European journal of cancer (Oxford, England: 1990) 48.5 (2012): 599.
Ananthakrishnan, Ashwin, Veena Gogineni, and Kia Saeian. "Epidemiology of primary and secondary liver cancers." Seminars in interventional radiology. Vol. 23. No. 1. Thieme Medical Publishers, 2006.
Chuang, Shu-Chun, Carlo La Vecchia, and Paolo Boffetta. "Liver cancer: descriptive epidemiology and risk factors other than HBV and HCV infection."Cancer letters 286.1 (2009): 9-14.
Ferenci, Peter, et al. "Hepatocellular carcinoma (HCC): a global perspective."Journal of clinical gastroenterology 44.4 (2010): 239-245.
Sherman, Morris. "Hepatocellular carcinoma: New and emerging risks."Digestive and Liver Disease 42 (2010): S215-S222
Yu, Ming-Whei, et al. "Hepatitis B virus genotype and DNA level and hepatocellular carcinoma: a prospective study in men." Journal of the National Cancer Institute 97.4 (2005): 265-272.
Yoo, Illhoi, et al. "Data mining in healthcare and biomedicine: a survey of the literature." Journal of medical systems 36.4 (2012): 2431-2448.
Ravisankar, Pediredla, et al. "Detection of financial statement fraud and feature selection using data mining techniques." Decision Support Systems 50.2 (2011): 491-500.
Kirkos, Efstathios, Charalambos Spathis, and Yannis Manolopoulos. "Data mining techniques for the detection of fraudulent financial statements." Expert Systems with Applications 32.4 (2007): 995-1003.
Chauhan, Ritu, Harleen Kaur, and M. Afshar Alam. "Data clustering method for discovering clusters in spatial cancer databases." International Journal of Computer Applications (0975–8887) Volume (2010).
Mullins, Irene M., et al. "Data mining and clinical data repositories: Insights from a 667,000 patient data set." Computers in biology and medicine 36.12 (2006): 1351-1377.
Delen, Dursun, Glenn Walker, and Amit Kadam. "Predicting breast cancer survivability: a comparison of three data mining methods." Artificial intelligence in medicine 34.2 (2005): 113-127.
Jonsdottir, Thora, et al. "The feasibility of constructing a Predictive Outcome Model for breast cancer using the tools of data mining." Expert Systems with Applications 34.1 (2008): 108-118.
Karabatak, Murat, and M. Cevdet Ince. "An expert system for detection of breast cancer based on association rules and neural network." Expert Systems with Applications 36.2 (2009): 3465-3469.
Li, Lihua, et al. "Data mining techniques for cancer detection using serum proteomic profiling." Artificial intelligence in medicine 32.2 (2004): 71-83.
Fayyad, Usama, Gregory Piatetsky-Shapiro, and Padhraic Smyth. "From data mining to knowledge discovery in databases." AI magazine 17.3 (1996): 37.
Tai, Yueh-Ming, and Hung-Wen Chiu. "Comorbidity study of ADHD: applying association rule mining (ARM) to National Health Insurance Database of Taiwan." International journal of medical informatics 78.12 (2009): e75-e83.
Kim, Hye Soon, et al. "Comorbidity study on type 2 diabetes mellitus using data mining." The Korean journal of internal medicine 27.2 (2012): 197-202.
Shin, A. Mi, et al. "Diagnostic analysis of patients with essential hypertension using association rule mining." Healthcare informatics research 16.2 (2010): 77-81.
Kurosaki, Masayuki, et al. "Data mining model using simple and readily available factors could identify patients at high risk for hepatocellular carcinoma in chronic hepatitis C." Journal of hepatology 56.3 (2012): 602-608.
Folino, Francesco, Clara Pizzuti, and Maria Ventura. "A comorbidity network approach to predict disease risk." Information Technology in Bio-and Medical Informatics, ITBAM 2010. Springer Berlin Heidelberg, 2010. 102-109.
Folino, Francesco, and Clara Pizzuti. "A comorbidity-based recommendation engine for disease prediction." Computer-Based Medical Systems (CBMS), 2010 IEEE 23rd International Symposium on. IEEE, 2010.
Ward Jr, Joe H. "Hierarchical grouping to optimize an objective function."Journal of the American statistical association 58.301 (1963): 236-244.
Plasse, Marie, et al. "Combined use of association rules mining and clustering methods to find relevant links between binary rare attributes in a large data set." Computational Statistics & Data Analysis 52.1 (2007): 596-613.
Peng, Chao-Ying Joanne, Kuk Lida Lee, and Gary M. Ingersoll. "An introduction to logistic regression analysis and reporting." The Journal of Educational Research 96.1 (2002): 3-14.
Agrawal, Rakesh, Tomasz Imieliński, and Arun Swami. "Mining association rules between sets of items in large databases." ACM SIGMOD Record. Vol. 22. No. 2. ACM, 1993.
Agrawal, Rakesh, and Ramakrishnan Srikant. "Fast algorithms for mining association rules." Proc. 20th int. conf. very large data bases, VLDB. Vol. 1215. 1994.
Jaccard, Paul. "The distribution of the flora in the alpine zone. 1." New phytologist 11.2 (1912): 37-50.
Velázquez, Rosario F., et al. "Prospective analysis of risk factors for hepatocellular carcinoma in patients with liver cirrhosis." Hepatology 37.3 (2003): 520-527.
Perz, Joseph F., et al. "The contributions of hepatitis B virus and hepatitis C virus infections to cirrhosis and primary liver cancer worldwide." Journal of hepatology 45.4 (2006): 529-538.
Zen, Yoh, et al. "Hepatocellular carcinoma arising in non‐alcoholic steatohepatitis." Pathology international 51.2 (2001): 127-131.
Yoshioka, Yoko, et al. "Nonalcoholic steatohepatitis: cirrhosis, hepatocellular carcinoma, and burnt-out NASH." Journal of gastroenterology 39.12 (2004): 1215-1218.
Marrero, Jorge A., et al. "NAFLD may be a common underlying liver disease in patients with hepatocellular carcinoma in the United States." Hepatology 36.6 (2002): 1349-1354.
De Maria, Nicola, Mauro Manno, and Erica Villa. "Sex hormones and liver cancer." Molecular and cellular endocrinology 193.1 (2002): 59-63.
Naugler, Willscott E., et al. "Gender disparity in liver cancer due to sex differences in MyD88-dependent IL-6 production." Science 317.5834 (2007): 121-124.
Davila, J. A., et al. "Diabetes increases the risk of hepatocellular carcinoma in the United States: a population based case control study." Gut 54.4 (2005): 533-539.
Lee, Mei-Yueh, et al. "The association of diabetes mellitus with liver, colon, lung, and prostate cancer is independent of hypertension, hyperlipidemia, and gout in Taiwanese patients." Metabolism 61.2 (2012): 242-249.
Giovannucci, Edward, et al. "Diabetes and cancer: a consensus report." CA: a cancer journal for clinicians 60.4 (2010): 207-221.
Platz, Elizabeth A., et al. "Alcohol consumption, cigarette smoking, and risk of benign prostatic hyperplasia." American journal of epidemiology 149.2 (1999): 106-115.
Kristal, Alan R., et al. "Dietary patterns, supplement use, and the risk of symptomatic benign prostatic hyperplasia: results from the prostate cancer prevention trial." American journal of epidemiology 167.8 (2008): 925-934.
Crispo, Anna, et al. "Alcohol and the risk of prostate cancer and benign prostatic hyperplasia." Urology 64.4 (2004): 717-722.
Parsons, J. Kellogg. "Modifiable Risk Factors for Benign Prostatic Hyperplasia and Lower Urinary Tract Symptoms: New Approaches to Old Problems." (2007).
Huang, Jia-Qing, Subbaramiah Sridhar, and Richard H. Hunt. "Role of Helicobacter pylori infection and non-steroidal anti-inflammatory drugs in peptic-ulcer disease: a meta-analysis." The Lancet 359.9300 (2002): 14-22.
Leodolter, A., et al. "A meta‐analysis comparing eradication, healing and relapse rates in patients with Helicobacter pylori‐associated gastric or duodenal ulcer." Alimentary pharmacology & therapeutics 15.12 (2001): 1949-1958.
Malfertheiner, Peter, Francis KL Chan, and Kenneth EL McColl. "Peptic ulcer disease." The Lancet 374.9699 (2009): 1449-1461.
Avenaud, Philippe, et al. "Detection of Helicobacter species in the liver of patients with and without primary liver carcinoma." Cancer 89.7 (2000): 1431-1439.
Leone, Nicola, et al. "Helicobacter pylori seroprevalence in patients with cirrhosis of the liver and hepatocellular carcinoma." Cancer detection and prevention 27.6 (2003): 494-497.
Wu, Xiong‐Zhi, and Dan Chen. "Helicobacter pylori and hepatocellular carcinoma: correlated or uncorrelated?." Journal of gastroenterology and hepatology 21.2 (2006): 345-347.
Huang, Y., et al. "Identification of helicobacter species in human liver samples from patients with primary hepatocellular carcinoma." Journal of clinical pathology 57.12 (2004): 1273-1277.
Sahasrabuddhe, Vikrant V., et al. "Nonsteroidal anti-inflammatory drug use, chronic liver disease, and hepatocellular carcinoma." Journal of the National Cancer Institute 104.23 (2012): 1808-1814.