A Neural Network Trained to Identify the Presence of Myocardial Infarction Bases Some Decisions on Clinical Associations That Differ from Accepted Clinical Teaching

An artificial neural network trained to identify the presence of myocardial infarction has been shown to function with a high degree of accuracy. The effects on network diagnosis of some of the clinical input variables used by this network have previously been shown to be dis tributed over two distinct maxima. Analysis of the basis for this distribution by studying the specific patterns in which these variables had significantly different impacts on network diagnosis revealed that the differential impacts were due to the contexts in which the variables whose effects were bimodally distributed were placed. These contexts were defined by the values of the other input data used by the network. In a number of instances, the clinical relationships implied by these associations were divergent from prior knowledge about factors predictive of myocardial infarction. One implication of these findings is that this network, which has been shown to perform with a high degree of diagnostic accuracy, may be doing so by identifying relationships between inputted information that are divergent from accepted teaching. Key words: neural network; clinical decisions; nonlinear association. (Med Decis Making 1994;14:217-222)

[1]  J. Stechmiller,et al.  Prognostic Efficacy of Early Clinical Categorization of Myocardial Infarction Patients , 1977, Circulation.

[2]  A. Dannenberg,et al.  Enhancement of Clinical Predictive Ability by Computer Consultation) , 1979, Methods of Information in Medicine.

[3]  R B D'Agostino,et al.  The usefulness of a predictive instrument to reduce inappropriate admissions to the coronary care unit. , 1980, Annals of internal medicine.

[4]  Jeffrey A. Stem,et al.  A computer-derived protocol to aid in the diagnosis of emergency room patients with acute chest pain. , 1982, The New England journal of medicine.

[5]  R B D'Agostino,et al.  A predictive instrument to improve coronary-care-unit admission practices in acute ischemic heart disease. A prospective multicenter clinical trial. , 1984, The New England journal of medicine.

[6]  B. Psaty,et al.  Predictors of myocardial infarction in emergency room patients , 1985, Critical care medicine.

[7]  E F Cook,et al.  Acute chest pain in the emergency room. Identification and examination of low-risk patients. , 1985, Archives of internal medicine.

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[10]  E F Cook,et al.  Sensitivity of routine clinical criteria for diagnosing myocardial infarction within 24 hours of hospitalization. , 1987, Annals of internal medicine.

[11]  G W Rouan,et al.  Clinical characteristics and natural history of patients with acute myocardial infarction sent home from the emergency room. , 1987, The American journal of cardiology.

[12]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[13]  E F Cook,et al.  A computer protocol to predict myocardial infarction in emergency department patients with chest pain. , 1988, The New England journal of medicine.

[14]  Emile Servan-Schreiber,et al.  A Connectionist Approach to the Diagnosis of Dementia , 1988 .

[15]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[16]  William G. Baxt,et al.  Use of an Artificial Neural Network for Data Analysis in Clinical Decision-Making: The Diagnosis of Acute Coronary Occlusion , 1990, Neural Computation.

[17]  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.

[18]  W. Baxt.  Use of an artificial neural network for the diagnosis of myocardial infarction. , 1991, Annals of internal medicine.

[19]  R. L. Kennedy,et al.  The early diagnosis of heart attacks: a neurocomputational approach , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[20]  Russell C. Eberhart,et al.  Neural network paradigm comparisons for appendicitis diagnoses , 1991, [1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium.

[21]  W. Baxt.  Analysis of the clinical variables driving decision in an artificial neural network trained to identify the presence of myocardial infarction. , 1992, Annals of emergency medicine.