Epidemiologic interpretation of artificial neural networks.

Multilayer neural networks have been faulted for functioning as "black boxes" and for failing to assess the relative importance of the input factors. The aim of this paper is to illustrate how neural networks can classify individuals. The authors investigated the role of weights in the formation of neural networks' decision surfaces and decision regions. The data used were from a case-control study. Two strong determinants of case status were used as input "neurons." Zero, three, and five hidden neurons were used to explore the effect of the number of hidden neurons on the decision surfaces and regions. Mapping of input and output spaces revealed that three hidden neurons were insufficient to fully discriminate cases from controls. Five hidden neurons may be optimal, but at the cost of possible over-fitting. The more complex neural networks were very effective at defining regions of uniform risk in the plane of the initial covariates, and at assigning risk levels. The authors speculate that neural networks will prove useful in epidemiologic problems that require pattern recognition or complicated classification techniques, and that they will be unfavorable in problems that involve distinct effects of distinguishable predictors.

[1]  D Tandberg,et al.  Neural network and linear regression models in residency selection. , 1997, The American journal of emergency medicine.

[2]  Sholom M. Weiss,et al.  An Empirical Comparison of Pattern Recognition, Neural Nets, and Machine Learning Classification Methods , 1989, IJCAI.

[3]  F Alemi,et al.  A comparison of three techniques for rapid model development: an application in patient risk-stratification. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[4]  L. Pitts,et al.  Outcome after severe head injury: an analysis of prediction based upon comparison of neural network versus logistic regression analysis. , 1997, Neurological research.

[5]  Richard Lippmann,et al.  Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.

[6]  R. D'Agostino,et al.  A comparison of performance of mathematical predictive methods for medical diagnosis: identifying acute cardiac ischemia among emergency department patients. , 1995, Journal of investigative medicine : the official publication of the American Federation for Clinical Research.

[7]  P. Lapuerta,et al.  Neural networks as predictors of outcomes in alcoholic patients with severe liver disease , 1997, Hepatology.

[8]  T. Buchman,et al.  A comparison of statistical and connectionist models for the prediction of chronicity in a surgical intensive care unit , 1994, Critical care medicine.

[9]  Randall G. Lee,et al.  Determinants of serious liver disease among patients receiving low-dose methotrexate for rheumatoid arthritis. , 1993, Arthritis and rheumatism.

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

[11]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[12]  G. Dombi,et al.  Prediction of rib fracture injury outcome by an artificial neural network. , 1995, The Journal of trauma.

[13]  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.

[14]  Geoffrey E. Hinton,et al.  How neural networks learn from experience. , 1992, Scientific American.

[15]  Gregg D. Wilensky,et al.  Neural Network Studies , 1993 .

[16]  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.

[17]  Madan M. Gupta.  Fuzzy logic and neural networks , 1992, [Proceedings 1992] IEEE International Conference on Systems Engineering.

[18]  R. Golden,et al.  Predictors of general quality of life in patients with benign prostate hyperplasia or prostate cancer. , 1997, The Journal of urology.

[19]  R. Lippmann,et al.  Coronary artery bypass risk prediction using neural networks. , 1997, Annals of Thoracic Surgery.

[20]  M F Jefferson,et al.  Comparison of a genetic algorithm neural network with logistic regression for predicting outcome after surgery for patients with nonsmall cell lung carcinoma , 1997, Cancer.

[21]  G Reibnegger,et al.  Neural networks as a tool for utilizing laboratory information: comparison with linear discriminant analysis and with classification and regression trees. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Igor V. Tetko,et al.  Neural Network Studies, 2. Variable Selection , 1996, J. Chem. Inf. Comput. Sci..

[23]  G S Doig,et al.  Modeling mortality in the intensive care unit: comparing the performance of a back-propagation, associative-learning neural network with multivariate logistic regression. , 1993, Proceedings. Symposium on Computer Applications in Medical Care.