Gd. Tourassi et Ce. Floyd, THE EFFECT OF DATA SAMPLING ON THE PERFORMANCE EVALUATION OF ARTIFICIAL NEURAL NETWORKS IN MEDICAL DIAGNOSIS, Medical decision making, 17(2), 1997, pp. 186-192
Purpose. To study the effect of data sampling on the predictive assess
ment of artificial neural networks (ANNs) for medical diagnostic tasks
. Methods. Three statistical techniques were used to evaluate the diag
nostic performances of ANNs: 1) cross validation, 2) round robin, and
3) bootstrap. These techniques are different sampling plans designed t
o reduce the small-sample estimation bias and variance contributions.
The study was based on two networks, one developed for the diagnosis o
f pulmonary embolism (1,064 cases) and the other developed for the dia
gnosis of breast cancer (206 cases). Results. The three sampling techn
iques produced different performance estimates for both networks. The
estimates varied substantially depending on the training sample size a
nd the training-stopping criterion. Conclusion. The predictive assessm
ent of ANNs in medical diagnosis can vary substantially based on the c
omplexity of the problem, the data sampling technique, and the number
of cases available.