Neural networks in the diagnosis of malignant ovarian tumours

Objective To assess the role of neural networks in predicting the likelihoo d if malignancy in women presenting with ovarian tumours. Design Retrospective case study. Setting University Department of Obstetrics and Gynaecology, SI James's Hos pital, Leeds. Methods Information from 217 cases with histologically proven benign, borde rline or malignant tumours was extracted for study. Four variables (age, ul trasound findings with and without colour Doppler imaging and CA125) were e ntered in the neural network classifier. The neural network results were co mpared with logistic regression analysis. Results When used in the neural network the variables of age, CA125 and ult rasound score produced the best result with a sensitivity of 95% and a corr esponding specificity of 78% in predicting malignancy. Logistic regression gave a sensitivity or 82% for a specificity of 51%. Conclusion The neural network is a goad method of combining diagnostic vari ables and may be a useful predictor of malignancy in women presenting with ovarian tumours. A comparison of the performance of the neural network with conventional diagnostic methods would be warranted prior to use in clinica l practice.