Superior skin cancer classification by the combination of human and artificial intelligence

With the advancement of artificial intelligence in medical diagnostics, many reader studies have been carried out to determine whether man or machine is the better diagnostician [1x[1]Esteva, A. et al. Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. In these past studies, in particular in the field of skin cancer detection, man and machine were always regarded as competitors. However, this setting does not reflect clinical reality, where team-based diagnoses are considered to be more accurate than individual diagnoses [5x[5]Barnett, M.L. et al. Collective intelligence meets medical decision-making: the collective outperforms the best radiologist.