According to a press release from the EADV, novel artificial intelligence (AI) software may effectively detect skin cancer and precancerous lesions. The findings were presented by Andrew et al at the EADV Congress 2023. In testing previous versions of the AI software, researchers observed 85.9%, 83.8%, and 541% detection rates for melanoma, all skin cancers, and precancerous lesions, respectively. In the new study, the researchers analyzed the efficacy of the third version of the AI software by assessing 22,356 patients with suspected skin cancer over a period of 2.5 years. They found that the AI software demonstrated 100% sensitivity for detecting melanoma—and had detection rates of 99.5% for all skin cancers and 92.5% for precancerous lesions. Despite the potential of the software, the researchers stressed the continued need for support from consultant dermatologists acting as safety nets to help identify cancers missed by the technology. “Further research with appropriate clinical oversight may allow the deployment of AI [software] as a triage tool. Our data show the great promise of AI [software] in future provision of health care,” concluded lead study author Kashini Andrew, MBBS, MSc, MRCP, a specialist registrar at the University Hospitals Birmingham National Health Service Foundation Trust.
October 25, 2023