One-hundred and ninety-eight elderly subjects attending their general practitioners (GPs) were asked to complete the 15 item Geriatric Depression Scale (GDS15). Analysable results were obtained from 194 (98%). Of these, 67 (34%) scored above the GDS15 cut-off (4/5) for significant depressive symptomatology. 87.6% found the questionnaire to be acceptable and only 3.6% found it very difficult or very stressful. The GDS15 had a high level of internal consistency (Cronbach's alpha = 0.80). All the individual items of the GDS15 associated significantly (P < 0.01) with total score and 'caseness'. A single question "do you feel that your life is empty?" identified 84% of 'cases'. In an attempt to devise short scales to screen elderly primary care patients for depression, the data were subjected to logistic regression analysis. Ten (GDS10), four (GDS4) and on (GDS1) item versions were generated. Agreement between these short scales and the GDS15 in the original sample was 95, 91 and 79% respectively. Cronbach's alpha was 0.72 for the GDS10 and 0.55 for the GDS4. The short scales were then validated in an independent sample of 120 patients in whom both GDS data and the results of a detailed psychiatric interview (the Geriatric Mental Status Schedule, GMS) were available. The sensitivity and specificity of the GDS10 against GMS caseness were 87 and 77% (cut-off 3/4); those of the GDS4 were 89 and 65% (cut-off 0/1) and 61 and 81% (cut-off 1/2). Sensitivity and specificity for the GDS1 were 59 and 75%. It is concluded that these short scales may be useful in helping GPs and practice staff to identify elderly patients with significant depressive symptoms.