A controlled trial of three referral methods for patients with third molars.

Aim To evaluate the accuracy, sensitivity and specificity of three primary to secondary care referral strategies. Method Thirtytwo primary care dental practitioners (GDPs) were randomly all ocated one of three referral strategies: current practice (control strategy ); a neural network embedded within a computer program and a paper-based cl inical algorithm. One hundred and seven patients were assessed for lower th ird molar treatment: 47, 30 and 30 in each group, respectively. Clinical de tails were assessed by a panel of experts against a gold standard for third molar removal (the National Institutes of Health criteria). The accuracy s ensitivity, specificity, positive and negative predictive values were calcu lated for each strategy. Results The referral decisions made by the GDPs in the control group displa yed greater accuracy and sensitivity but poorer specificity (0.83; 4.97; 0. 22) compared with the neural network (0.67; 0.56; 0.79) and clinical algori thm (0.73; 0.56; 0.93). Conclusions It was concluded that incorporation of the clinical algorithm i nto primary care was the most appropriate option. The computer neural netwo rk performed less well than either current practice or the clinical algorit hm.