A questionnaire has been completed by 99 patients referred for investigation of symptoms after gastric operations. The replies were analysed in an attempt to distinguish patients with a recurrent peptic ulcer from those with no recurrent ulcer. All cases were investigated by barium meal, endoscopy, and oral cholecystography. All recurrent ulcers were confirmed by reoperation and patients with gastric carcinoma, gallstones, or symptomatic hiatus hernia were excluded. The study was retrospective in 40 patients in whom the diagnosis was already confirmed when the questionnaire was analysed and prospective in 59 in whom the diagnosis was originally unknown. The replies were analysed with (a) a small computer using Bayes' theorem, (b) weighted tables, and (c) a discriminant analysis. The computer prediction of the prospective data was 85% accurate. The results of simpler methods were almost as good as the computer prediction, and questions related only to the severity of pain and vomiting accurately distinguished recurrent ulcer from other causes of dyspepsia in 81% of patients.