Skin manifestations articles from across Nature Portfolio

In a large-scale study involving 389 board-certified dermatologists and 459 primary-care physicians from 39 countries, the impact of a deep learning-aided decision support system on physicians’ diagnostic accuracy was tested across 46 skin diseases and for both light and dark skin tones.

Every injury of the skin undergoes a process known as wound healing. When wound healing is disrupted, excessive scars, such as hypertrophic scars and keloid lesions, can develop. This Primer summarizes the epidemiology, mechanisms, diagnosis and treatment of scars, as well as discussing how scars can affect an individual’s quality of life.

In a large-scale digital experiment on dermatology diagnosis, we found that specialists and generalists achieved diagnostic accuracy of 38% and 19%, respectively. With decision support from a fair deep learning system, the diagnostic accuracy of physicians improved by more than 33%, but the gap in accuracy of generalists widened across skin tones.

The elastic modulus of the superficial and deep layers of the skin can be dynamically measured via wearable conformal electromagnetic devices consisting of a vibratory actuator and a soft strain-sensing sheet.

A detailed report on the involvement of skin in vasculitis enriches existing disease definitions and nomenclature, and could improve the diagnosis of these manifestations. The exercise also emphasizes the need for collaboration across different medical specialties in the study of vasculitis.