Prediction of lupus nephritis in patients with systemic lupus erythematosus using artificial neural networks.

Abstract

Artificial neural networks are intelligent systems that have been successfully used for prediction in different medical fields. In this study, efficiency of neural networks for prediction of lupus nephritis in patients with systemic lupus erythematosus (SLE) was compared with a logistic regression model and clinicians' diagnosis. Overall accuracy, sensitivity and specificity of the optimal neural network were 68.69, 73.77 and 62.96%, respectively. Overall accuracy of neural network was greater than the other two methods (P-value < 0.05). The neural network was more specific in predicting lupus nephritis (P-value < 0.01), but there was no significant difference between sensitivities of the three methods. Sensitivities of all three methods were greater than their specificities. We concluded that neural networks are efficient in predicting lupus nephritis in SLE patients.