Application of the fuzzy ARTMAP neural network model to medical pattern classification tasks

This paper presents research into the application of the fuzzy ARTMAP neural network model to medical pattern classification tasks. A number of domains, both diagnostic and prognostic, are considered. Each such domain highlights a particularly useful aspect of the model. The first coronary care patient prognosis, demonstrates the ARTMAP voting strategy involving 'pooled' decision-making using a number of networks, each of which has learned a slightly different mapping of input features to pattern classes. The second domain, breast cancer diagnosis, demonstrates the model's symbolic rule extraction capabilities which support the validation and explanation of a network's predictions. The final domain, diagnosis of acute myocardial infarction, demonstrates a novel category pruning technique allowing the performance of a trained network to be altered so as to favour predictions of one class over another (e.g. trading sensitivity for specificity or vice versa). It also introduces a 'cascaded' variant of the voting strategy intended to allow identification of a subset of cases which the network has a very high certainty of classifying correctly.

[1]  H. Reichenbach-Klinke,et al.  CHAPTER 12 – Tumours, Benign and Malignant , 1965 .

[2]  Chee Peng Lim,et al.  Modified Fuzzy ARTMAP Approaches Bayes Optimal Classification Rates: An Empirical Demonstration , 1997, Neural Networks.

[3]  Robert F. Harrison,et al.  A modified fuzzy ARTMAP architecture for the approximation of noisy mappings , 1995, Neural Networks.

[4]  David G. Bounds,et al.  A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders , 1990, Neural Networks.

[5]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[6]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[7]  Robert F. Harrison,et al.  The Use of Fuzzy ARTMAP to Identify Low Risk Coronary Care Patients , 1995, ICANNGA.

[8]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[9]  John Hallam,et al.  Hybrid problems, hybrid solutions , 1995 .

[10]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[11]  Jeremy Wyatt,et al.  Decision Aids and the Law , 1989, The Lancet.

[12]  Ray L. Somorjai,et al.  Neural network classification of infrared spectra of control and Alzheimer's diseased tissue , 1995, Artif. Intell. Medicine.

[13]  Dana Statton Thompson,et al.  Early identification of patients at low risk of death after myocardial infarction and potentially suitable for early hospital discharge , 1994, BMJ.

[14]  J. Rawles,et al.  Earliest electrocardiographic evidence of myocardial infarction: implications for thrombolytic treatment. The GREAT Group. , 1993, BMJ.

[15]  Robert F. Harrison,et al.  Evaluating a Neural Network Decision-Support Tool for the Diagnosis of Breast Cancer , 1995, AIME.

[16]  Stephen Grossberg,et al.  Fusion Artmap: A Neural Network Architecture for Multi-Channel Data Fusion and Classification , 1993 .

[17]  M. McIntosh,et al.  Earliest electrocardiographic evidence of myocardial infarction: Implications for thrombolytic treatment , 1994 .

[18]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1988, Computer.

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

[20]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[21]  A. Jaffe,et al.  Biochemical Markers of Myocardial Injury Is MB Creatine Kinase the Choice for the 1990s? , 1993, Circulation.

[22]  I. Ellis,et al.  Guidelines for cytology procedures and reporting on fine needle aspirates of the breast , 1994, Cytopathology : official journal of the British Society for Clinical Cytology.

[23]  François E. Cellier,et al.  Artificial Neural Networks and Genetic Algorithms , 1991 .

[24]  Zhe,et al.  A Heuristic for General Rule Extraction From a Multilayer Perceprtron , 1994 .

[25]  Ii Robert J. Marks.  Fuzzy Logic Technology and Applications I , 1994 .

[26]  Michael Egmont-Petersen,et al.  On the quality of neural net classifiers , 1994, Artif. Intell. Medicine.

[27]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[28]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[29]  Robert F. Harrison,et al.  A Prototype Neural Network Decision-Support Tool for the Early Diagnosis of Acute Myocardial Infarction , 1995, AIME.

[30]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[31]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[32]  R. Harrison,et al.  A Comparison of Logistic Regression and Artificial Neural Network Models for the Early Diagnosis of Acute Myocardial Infarction. , 1994 .

[33]  Ah-Hwee Tan,et al.  Rule Extraction, Fuzzy ARTMAP, and Medical Databases , 1993 .

[34]  John A. Self,et al.  Building expert systems, edited by F. Hayes-Roth D.A. Waterman and D.B. Lenat Addison-Wesley, London, 1983 (£27.50) , 1984, Robotica.

[35]  Robert F. Harrison,et al.  A Neural Network Decision-Support Tool for the Diagnosis of Breast Cancer , 1994 .

[36]  Frederick Hayes-Roth,et al.  Building expert systems , 1983, Advanced book program.

[37]  Gerald Sommer,et al.  Pattern Recognition by Self-Organizing Neural Networks , 1994 .

[38]  Stephen Grossberg,et al.  Fuzzy ARTMAP neural network compared to linear discriminant analysis prediction of the length of hospital stay in patients with pneumonia , 1992, [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics.