Skin cancer detection tools powered by AI are improving. Not everyone is benefitting

Imagine you’re getting out of the shower one morning and you notice a mole on your thigh that you’ve never seen before. It’s reddish brown, bumpy and surprisingly large. Is it a benign mole, or is it melanoma? A slew of new artificial intelligence tools claim they can help you figure it out. Some are smartphone apps that anyone can download to scan their skin at home, while others are software programs designed to be used directly by clinicians in a doctor’s office. As a computer engineer studying how tools like these perform in real-world clinical settings, I know that finding a way to accurately use AI in dermatology would be immensely valuable to patients around the world. It could offer broad access to medical expertise, providing lifesaving screenings to remote areas or underresourced communities where dermatologists are scarce. But at the moment, these tools have a crucial shortcoming that researchers will have to resolve: They are increasingly accurate for people with light skin—but they have a massive blind spot when it comes to analyzing darker skin. Skin-deep accuracy The central myth of AI is that it functions objectively. In reality, an AI model is simply a pattern-mat…