We describe pattern recognition analysis of six cardiovascular reflex tests and its application in the diagnosis of autonomic neuropathy. A discriminating model was performed by SIMCA method using the results of 85 healthy subjects. The prediction ability of the model was then verified with data from 95 patients at risk for autonomic neuropathy. Specificity resulted 93% and sensitivity 97%. The method increases the diagnostic efficiency of the tests, being particularly useful in patients with borderline autonomic involvement.