minSKIN Does a multifaceted intervention improve the competence in the diagnosis of skin cancer by general practitioners? Study protocol for a randomised controlled trial

Background: In Switzerland, skin cancer is one of the most common neoplasms. Melanoma is the most aggressive one and can be lethal if not detected and removed on time. Nonmelanoma skin cancer is more frequent as melanoma; it is seldom lethal but can disfigure patients in advanced stages. General practitioners (GPs) are often faced with suspicious skin lesions of their patients. Methods/Design: Design: Randomised controlled trial (RCT). Population: 60 GPs, randomised into intervention group and control group. Intervention: GPs get a Lumio loupe, a digital camera and continuous feedback based on pictures of skin lesions they send to the Dermatologist. Primary outcome: Competence in the diagnosis of skin cancer by GPs, measured as the percentage of correctly classified pictures of skin lesions. Measurements: At baseline, and prior to any intervention (T-0), GPs will be asked to rate 36 pictures of skin lesions according to their likelihood of malignancy on a visual analogue scale (VAS). After a full day training course with both groups (T-1) and after one year of continuous feedback (T-2) with the intervention group, we will repeat the picture scoring session with both groups, using new pictures. Discussion: We want to determine whether a multifaceted intervention (including technical equipment and a continuous feedback on skin lesions) leads to an improved competence in the diagnosis of skin cancer by GPs. This study addresses the hypothesis that an additional feedback loop, based on pictures performed in daily practice by GPs is superior to a simple educational intervention regarding diagnostic competence. We expect an improvement of the competence in skin cancer diagnosis by GPs in both groups after the full day training course. Beside this immediate effect, we also expect a long term effect in the intervention group because of the continuous problem based feedback.