Investigation into the Strengths and Limitations of Artificial Neural Networks: An Application to an Adult ICU Patient Database
Colleen M. Ennett, Monique Frize · PubMed Central · 1998
The objective was to determine the optimal operating conditions for an artificial neural network (ANN) to estimate outcomes. The simulations involved using the 51 inputs while changing the desired output variable. Comparing the correct classification rate (CCR) of an ANN with that of a constant predictor (CP) results indicates the minimum number of sample patterns an ANN requires for minimally acceptable outcome estimation, and establishes the limitation of the ANN as a useful tool.