Automated development of artificial neural networks for clinical purposes: Application for predicting the outcome of choledocholithiasis surgery

Among various expert systems (ES), Artificial Neural Network (ANN) has shown to be suitable for the diagnosis of concurrent common bile duct stones (CBDS) in patients undergoing elective cholecystectomy. However, their application in practice remains limited since the development of ANNs represents a slow process that requires additional expertize from potential users. The aim of this study was to propose an ES for automated development of ANNs and validate its performances on the problem of prediction of CBDS. Automated development of the ANN was achieved by applying the evolutionary assembling approach, which assumes optimal configuring of the ANN parameters by using Genetic algorithm. Automated selection of optimal features for the ANN training was performed using a Backward sequential feature selection algorithm. The assessment of the developed ANN included the evaluation of predictive ability and clinical utility. For these purposes, we collected data from 303 patients who underwent surgery in the period from 2008 to 2014. The results showed that the total bilirubin, alanine aminotransferase, common bile duct diameter, number of stones, size of the smallest calculus, biliary colic, acute cholecystitis and pancreatitis had the best prognostic value of CBDS. Compared to the alternative approaches, the ANN obtained by the proposed ES had better sensitivity and clinical utility, which are considered to be the most important for the particular problem. Besides the fact that it enabled the development of ANNs with better performances, the proposed ES significantly reduced the complexity of ANNs' development compared to previous studies that required manual selection of optimal features and/or ANN configuration. Therefore, it is concluded that the proposed ES represents a robust and user-friendly framework that, apart from the prediction of CBDS, could advance and simplify the application of ANNs for solving a wider range of problems.

[1]  N D Heaton,et al.  Artificial neural network is superior to MELD in predicting mortality of patients with end-stage liver disease , 2006, Gut.

[2]  Hiroshi Motoda,et al.  Book Review: Computational Methods of Feature Selection , 2007, The IEEE intelligent informatics bulletin.

[3]  I. Hozo,et al.  When Is Diagnostic Testing Inappropriate or Irrational? Acceptable Regret Approach , 2008, Medical decision making : an international journal of the Society for Medical Decision Making.

[4]  E. Elkin,et al.  Decision Curve Analysis: A Novel Method for Evaluating Prediction Models , 2006, Medical decision making : an international journal of the Society for Medical Decision Making.

[5]  Owaid M. Almalki,et al.  Non-invasive assessment of choledocholithiasis in patients with gallstones and abnormal liver function. , 2013, World journal of gastroenterology.

[6]  M. Dolapci,et al.  Practical recommendations for the prediction and management of common bile duct stones in patients with gallstones , 2001, Surgical Endoscopy.

[7]  R. Parks,et al.  Identification of severe acute pancreatitis using an artificial neural network. , 2007, Surgery.

[8]  J. Horwood,et al.  Prospective evaluation of a selective approach to cholangiography for suspected common bile duct stones. , 2010, Annals of the Royal College of Surgeons of England.

[9]  R. Costi,et al.  Diagnosis and management of choledocholithiasis in the golden age of imaging, endoscopy and laparoscopy. , 2014, World journal of gastroenterology.

[10]  R. Cantu,et al.  The prediction of common bile duct stones using a neural network. , 1998, Journal of the American College of Surgeons.

[11]  I. Muir,et al.  Prospective analysis of a scoring system to predict choledocholithiasis , 2000, The British journal of surgery.

[12]  Chong-Ho Choi,et al.  Input feature selection for classification problems , 2002, IEEE Trans. Neural Networks.

[13]  A. Avenell,et al.  Systematic review of the clinical and cost effectiveness of cholecystectomy versus observation/conservative management for uncomplicated symptomatic gallstones or cholecystitis , 2015, Surgical Endoscopy.

[14]  Iztok Hozo,et al.  A regret theory approach to decision curve analysis: A novel method for eliciting decision makers' preferences and decision-making , 2010, BMC Medical Informatics Decis. Mak..

[15]  E. DeLong,et al.  Predicting the presence of choledocholithiasis in patients with symptomatic cholelithiasis. , 1996, The American journal of gastroenterology.

[16]  C. Dziri,et al.  Validation of the Lacaine-Huguier predictive score for choledocholithiasis: prospective study of 380 patients. , 2012, Journal of visceral surgery.

[17]  Enver Zerem,et al.  Artificial neural network predicts the need for therapeutic ERCP in patients with suspected choledocholithiasis. , 2014, Gastrointestinal endoscopy.

[18]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[19]  B. Edwin,et al.  Prediction of common bile duct stones prior to cholecystectomy: a prospective validation of a discriminant analysis function. , 1998, Archives of surgery.

[20]  Miroslav Stojadinovic M,et al.  Regression tree for choledocholithiasis prediction , 2015, European journal of gastroenterology & hepatology.

[21]  P. Kokol,et al.  Comprehensive Decision Tree Models in Bioinformatics , 2012, PloS one.

[22]  Irfan A. Essa,et al.  Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[24]  John W Pickering,et al.  New metrics for assessing diagnostic potential of candidate biomarkers. , 2012, Clinical journal of the American Society of Nephrology : CJASN.

[25]  H. Fujita,et al.  Computer-aided diagnosis of hepatic fibrosis: preliminary evaluation of MRI texture analysis using the finite difference method and an artificial neural network. , 2007, AJR. American journal of roentgenology.

[26]  R. Costi,et al.  Scoring system to predict asymptomatic choledocholithiasis before laparoscopic cholecystectomy , 2003, Surgical Endoscopy And Other Interventional Techniques.

[27]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[28]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[29]  O. Adorisio,et al.  Preoperative risk factors for common bile duct stones: defining the patient at high risk in the laparoscopic cholecystectomy era. , 2004, Journal of laparoendoscopic & advanced surgical techniques. Part A.

[30]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[31]  D. Sargent,et al.  Comparison of artificial neural networks with other statistical approaches , 2001, Cancer.

[32]  Antanas Verikas,et al.  Feature selection with neural networks , 2002, Pattern Recognit. Lett..

[33]  Wei Chen,et al.  The transformation of surgery patient care with a clinical research information system , 2013, Expert Syst. Appl..

[34]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection: A Data Mining Perspective , 1998 .

[35]  Deniz Erdogmus,et al.  Feature selection in MLPs and SVMs based on maximum output information , 2004, IEEE Transactions on Neural Networks.

[36]  Marco Vivarelli,et al.  Prediction of significant fibrosis in hepatitis C virus infected liver transplant recipients by artificial neural network analysis of clinical factors , 2006, European journal of gastroenterology & hepatology.

[37]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[38]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[39]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[40]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[41]  Iztok Hozo,et al.  Dual processing model of medical decision-making , 2012, BMC Medical Informatics and Decision Making.

[42]  Amir-Masoud Eftekhari-Moghadam,et al.  Knowledge discovery in medicine: Current issue and future trend , 2014, Expert Syst. Appl..

[43]  D G Altman,et al.  What do we mean by validating a prognostic model? , 2000, Statistics in medicine.

[44]  J. Barkun,et al.  Nonoperative imaging techniques in suspected biliary tract obstruction. , 2006, HPB : the official journal of the International Hepato Pancreato Biliary Association.

[45]  Tao Xi,et al.  MicroRNA-125b Induces Metastasis by Targeting STARD13 in MCF-7 and MDA-MB-231 Breast Cancer Cells , 2012, PloS one.

[46]  Xiao-Hu Yu,et al.  Efficient Backpropagation Learning Using Optimal Learning Rate and Momentum , 1997, Neural Networks.

[47]  Amitabh Chak,et al.  Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model , 2003, The Lancet.

[48]  Nenad Filipovic,et al.  Evolutionary assembled neural networks for making medical decisions with minimal regret: Application for predicting advanced bladder cancer outcome , 2014, Expert Syst. Appl..