Improve discrimination power of serum markers for diagnosis of cholangiocarcinoma using data mining-based approach.

OBJECTIVE Cholangiocarcinoma (CCA) is usually fatal because of the absence of tests for early detection and lack of effective therapy. Tumor markers with adequate diagnostic values are of clinical significance. This study is aimed to improve the diagnostic power of serum markers using the computational data mining technique to develop a combined diagnostic model that yielded the best diagnostic values for CCA. DESIGN AND METHODS Eight CCA-associated markers-carcinoembryonic antigen, carbohydrate antigen 19-9, alkaline phosphatase (ALP), and gamma glutamyl transferase, biliary-ALP, mucin5AC, CCA-associated carbohydrate antigen (CCA-CA) and CA-S27-were used as the inputs for the C4.5 decision tree classification model and the selected model was confirmed by ANN analyses. Eight serum markers for CCA were determined in the training set of 85 histologically proven-CCA patients and 82 control subjects. The chosen set of combined markers that gave the best diagnostic values for CCA was then validated in the testing set of 22 CCA patients and 60 controls. RESULTS A decision tree diagram built by the C4.5 algorithm suggested the serial analysis of CCA-CA and ALP for distinguishing CCA patients from non-CCA subjects with all diagnostic parameters ≥95%. The combined tests showed a precise diagnosis in the testing set. CONCLUSIONS The C4.5 model indicates the combined markers of CCA-CA and ALP that produced the more precise diagnosis for CCA.

[1]  A. Malehi Diagnostic classification scheme in Iranian breast cancer patients using a decision tree. , 2014, Asian Pacific journal of cancer prevention : APJCP.

[2]  Min Lu,et al.  Utility of serum CA19-9 in diagnosis of cholangiocarcinoma: in comparison with CEA. , 2004, World journal of gastroenterology.

[3]  Roger Williams,et al.  Serum tumor markers for the diagnosis of cholangiocarcinoma in primary sclerosing cholangitis. , 1995, Gastroenterology.

[4]  C. Blaya,et al.  The role of serum liver enzymes in the diagnosis of choledocholithiasis. , 2000, Hepato-gastroenterology.

[5]  Ercan Erdis,et al.  Decision tree analysis of construction fall accidents involving roofers , 2015, Expert Syst. Appl..

[6]  Annekatrin Metz,et al.  ombined use of multi-seasonal high and medium resolution satellite magery for parcel-related mapping of cropland and grassland , 2014 .

[7]  S. Wongkham,et al.  A new mucin antibody/enzyme-linked lectin-sandwich assay of serum MUC5AC mucin for the diagnosis of cholangiocarcinoma. , 2007, Cancer letters.

[8]  Chau-Chen Torng,et al.  A retrospective analysis of prognostic indicators in dental implant therapy using the C5.0 decision tree algorithm , 2013 .

[9]  Y. Tian,et al.  The clinical value of serum CEA, CA19-9, and CA242 in the diagnosis and prognosis of pancreatic cancer. , 2005, European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology.

[10]  T. Uenishi,et al.  Cytokeratin-19 fragments in serum (CYFRA 21-1) as a marker in primary liver cancer , 2003, British Journal of Cancer.

[11]  A. Vadivel,et al.  A fuzzy rule-based approach for characterization of mammogram masses into BI-RADS shape categories , 2013, Comput. Biol. Medicine.

[12]  S. Wongkham,et al.  State of serum markers for detection of cholangiocarcinoma. , 2012, Asian Pacific journal of cancer prevention : APJCP.

[13]  N. Kinukawa,et al.  Clinical significance of serum RCAS1 levels detected by monoclonal antibody 22-1-1 in patients with cholangiocellular carcinoma. , 2003, Journal of hepatology.

[14]  S. Wongkham,et al.  Clinical value of biliary alkaline phosphatase in non-jaundiced cholangiocarcinoma , 2004, Journal of Cancer Research and Clinical Oncology.

[15]  David G. Stork,et al.  Pattern Classification , 1973 .

[16]  S. Glaser,et al.  The function of alkaline phosphatase in the liver: Regulation of intrahepatic biliary epithelium secretory activities in the rat , 2000, Hepatology.

[17]  Heike Allgayer,et al.  Activation of Src kinase in primary colorectal carcinoma , 2002, Cancer.

[18]  S. Kubo,et al.  Serum Cytokeratin 19 Fragment (CYFRA21-1) as a Prognostic Factor in Intrahepatic Cholangiocarcinoma , 2008, Annals of Surgical Oncology.

[19]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[20]  K R Hess,et al.  Classification and regression tree analysis of 1000 consecutive patients with unknown primary carcinoma. , 1999, Clinical cancer research : an official journal of the American Association for Cancer Research.

[21]  G. Jhangri,et al.  Prospective study of biliary strictures to determine the predictors of malignancy. , 2000, Canadian journal of gastroenterology = Journal canadien de gastroenterologie.

[22]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[23]  Hui Chen,et al.  Diagnosis of pancreatic carcinoma based on combined measurement of multiple serum tumor markers using artificial neural network analysis , 2014, Chinese medical journal.

[24]  Susan M. Chang,et al.  Prognostic factors for survival of patients with glioblastoma: recursive partitioning analysis. , 2004, Neuro-oncology.

[25]  Yoshiki Narimatsu,et al.  A novel serum carbohydrate marker on mucin 5AC , 2011, Cancer.

[26]  Mevlut Ture,et al.  The comparisons of prognostic indexes using data mining techniques and Cox regression analysis in the breast cancer data , 2009, Expert Syst. Appl..

[27]  Jing Wang,et al.  Comparison of hospital charge prediction models for gastric cancer patients: neural network vs. decision tree models , 2009, BMC health services research.

[28]  Douglas R. Smith,et al.  Top-Down Synthesis of Divide-and-Conquer Algorithms , 1985, Artif. Intell..

[29]  Hai-rim Shin,et al.  Comparison of incidence of intrahepatic and extrahepatic cholangiocarcinoma--focus on East and South-Eastern Asia. , 2010, Asian Pacific journal of cancer prevention : APJCP.

[30]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[31]  Y. G. Li,et al.  Clinical significance of serum tumour M2-PK and CA19-9 detection in the diagnosis of cholangiocarcinoma. , 2009, Digestive and liver disease : official journal of the Italian Society of Gastroenterology and the Italian Association for the Study of the Liver.

[32]  Sulin Pang,et al.  C5.0 Classification Algorithm and Application on Individual Credit Evaluation of Banks , 2009 .

[33]  Yoshiki Narimatsu,et al.  CA‐S27: A novel Lewis a associated carbohydrate epitope is diagnostic and prognostic for cholangiocarcinoma , 2013, Cancer science.

[34]  Alice E. Smith,et al.  Bias and variance of validation methods for function approximation neural networks under conditions of sparse data , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[35]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .