Severe renal artery stenosis (RAS) is a relatively uncommon com plication after renal transplantation but is a curable cause of hyper tension, which demands reliable early diagnosis to reduce morbid ity, mortality and graft loss. Captopril renography has been used for a number of years as a method of detecting RAS but controversy still exists as to the diagnostic accuracy of this test and as to the most appropriate interpretation criteria with which to establish a positive result. This report presents the results of using artificial neural networks to impartially assess these interpretation criteria. Data comprised 31"" Tc-MAGS captopril renography investigations undertaken on hypertensive renal transplant patients with a suspected diagnosis of RAS. Each renogram study was correlated with an arteriogram as the" gold standard". Training of the network was performed using the round-robin technique. An accuracy of 95% could be achieved by considering perfusion index, time-to-peak activity, accumulation index and ex cretion index for both pre-and post-challenge studies. This varied as the parameters were either included or excluded. Artifical neural network analysis is a useful technique to evaluate the most appropriate criteria for interpreting captopril transplant renog raphy investigations.