Application of Entropy-Based Attribute Reduction and an Artificial Neural Network in Medicine: A Case Study of Estimating Medical Care Costs Associated with Myocardial Infarction

In medicine, artificial neural networks (ANN) have been extensively applied in many fields to model the nonlinear relationship of multivariate data. Due to the difficulty of selecting input variables, attribute reduction techniques were widely used to reduce data to get a smaller set of attributes. However, to compute reductions from heterogeneous data, a discretizing algorithm was often introduced in dimensionality reduction methods, which may cause information loss. In this study, we developed an integrated method for estimating the medical care costs, obtained from 798 cases, associated with myocardial infarction disease. The subset of attributes was selected as the input variables of ANN by using an entropy-based information measure, fuzzy information entropy, which can deal with both categorical attributes and numerical attributes without discretization. Then, we applied a correction for the Akaike information criterion (ΑICc) to compare the networks. The results revealed that fuzzy information entropy was capable of selecting input variables from heterogeneous data for ANN, and the proposed procedure of this study provided a reasonable estimation of medical care costs, which can be adopted in other fields of medical science.

[1]  Didier Dubois,et al.  Putting Rough Sets and Fuzzy Sets Together , 1992, Intelligent Decision Support.

[2]  Clifford M. Hurvich,et al.  A CORRECTED AKAIKE INFORMATION CRITERION FOR VECTOR AUTOREGRESSIVE MODEL SELECTION , 1993 .

[3]  Erry,et al.  Cost effectiveness of thrombolytic therapy with tissue plasminogen activator as compared with streptokinase for acute myocardial infarction. , 1995, The New England journal of medicine.

[4]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[5]  Nehad N. Morsi,et al.  Axiomatics for fuzzy rough sets , 1998, Fuzzy Sets Syst..

[6]  M. Bourassa,et al.  Depression and health-care costs during the first year following myocardial infarction. , 2000, Journal of psychosomatic research.

[7]  Ric,et al.  COST EFFECTIVENESS OF THROMBOLYTIC THERAPY WITH TISSUE PLASMINOGEN ACTIVATOR AS COMPARED WITH STREPTOKINASE FOR ACUTE MYOCARDIAL INFARCTION , 2001 .

[8]  Jasmina Arifovic,et al.  Using genetic algorithms to select architecture of a feedforward artificial neural network , 2001 .

[9]  Qiang Shen,et al.  Semantics-preserving dimensionality reduction: rough and fuzzy-rough-based approaches , 2004, IEEE Transactions on Knowledge and Data Engineering.

[10]  Qiang Shen,et al.  Centre for Intelligent Systems and Their Applications Fuzzy Rough Attribute Reduction with Application to Web Categorization Fuzzy Rough Attribute Reduction with Application to Web Categorization Fuzzy Sets and Systems ( ) – Fuzzy–rough Attribute Reduction with Application to Web Categorization , 2022 .

[11]  S. Kotsiantis,et al.  Discretization Techniques: A recent survey , 2006 .

[12]  Qinghua Hu,et al.  Information-preserving hybrid data reduction based on fuzzy-rough techniques , 2006, Pattern Recognit. Lett..

[13]  Nadir Yayla,et al.  The investigation of model selection criteria in artificial neural networks by the Taguchi method , 2007 .

[14]  N. Chaiyakunapruk,et al.  Factors affecting health-care costs and hospitalizations among diabetic patients in Thai public hospitals. , 2008, Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research.

[15]  M. Symonds,et al.  A brief guide to model selection, multimodel inference and model averaging in behavioural ecology using Akaike’s information criterion , 2010, Behavioral Ecology and Sociobiology.

[16]  Harun Uguz,et al.  A Biomedical System Based on Artificial Neural Network and Principal Component Analysis for Diagnosis of the Heart Valve Diseases , 2012, Journal of Medical Systems.

[17]  Durdu Ömer Faruk.  A hybrid neural network and ARIMA model for water quality time series prediction , 2010, Eng. Appl. Artif. Intell..

[18]  Wei-Chang Yeh,et al.  Artificial bee colony algorithm-neural networks for S-system models of biochemical networks approximation , 2010, Neural Computing and Applications.

[19]  George C. Anastassopoulos,et al.  Genetic algorithm pruning of probabilistic neural networks in medical disease estimation , 2011, Neural Networks.

[20]  Chung-Ho Hsieh,et al.  Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. , 2011, Surgery.

[21]  Holger R. Maier,et al.  Review of Input Variable Selection Methods for Artificial Neural Networks , 2011 .

[22]  Reza Tavakkoli-Moghaddam,et al.  An integrated Data Envelopment Analysis-Artificial Neural Network-Rough Set Algorithm for assessment of personnel efficiency , 2011, Expert Syst. Appl..

[23]  P. Vilmann,et al.  Efficacy of an artificial neural network-based approach to endoscopic ultrasound elastography in diagnosis of focal pancreatic masses. , 2012, Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association.

[24]  Jinn-Tsong Tsai,et al.  Predicting two-year quality of life after breast cancer surgery using artificial neural network and linear regression models , 2012, Breast Cancer Research and Treatment.

[25]  Jianhua Dai,et al.  Attribute selection based on information gain ratio in fuzzy rough set theory with application to tumor classification , 2013, Appl. Soft Comput..

[26]  Maysam F. Abbod,et al.  Application of Multivariate Empirical Mode Decomposition and Sample Entropy in EEG Signals via Artificial Neural Networks for Interpreting Depth of Anesthesia , 2013, Entropy.

[27]  Diane O. Dunet,et al.  Costs of Hospitalizations with a Primary Diagnosis of Acute Myocardial Infarction Among Patients Aged 18-64 Years in the United States , 2013 .

[28]  Francisco Herrera,et al.  A Survey of Discretization Techniques: Taxonomy and Empirical Analysis in Supervised Learning , 2013, IEEE Transactions on Knowledge and Data Engineering.

[29]  J. Nilsson,et al.  Artificial neural networks predict survival from pancreatic cancer after radical surgery. , 2013, American journal of surgery.

[30]  Richard Jensen,et al.  Unsupervised fuzzy-rough set-based dimensionality reduction , 2013, Inf. Sci..