According to a new study, the ability of artificial intelligence (AI) software to identify skin cancer has significantly increased, with the latest version of the software now having a 100% melanoma detection rate.
Image Credit: LightField Studios/Shutterstock.com
The study, which was presented on October 11th, 2023, at the European Academy of Dermatology and Venereology (EADV) Congress 2023, followed 22,356 patients with probable skin cancers for 2.5 years.
In addition to detecting melanoma (the most fatal type of skin cancer) with 100% sensitivity (59/59 instances found), the new software properly recognized 99.5% (189/190) of all skin cancers and 92.5% (541/585) of pre-cancerous lesions.
The third version of the AI software represents a substantial advance over the previous model, which detected 85.9% (195/227) of melanoma, 83.8% (903/1078) of all skin cancers, and 54.1% (496/917) of pre-cancerous lesions in 2021.
This study has demonstrated how AI is rapidly improving and learning, with the high accuracy directly attributable to improvements in AI training techniques and the quality of data used to train the AI. The latest version of the software has saved over 1,000 face-to-face consultations in the secondary care setting between April 2022 and January 2023,3 freeing up more time for patients that need urgent attention.
Dr. Kashini Andrew, Study Lead Author and Specialist Registrar at University Hospitals Birmingham NHS Foundation Trust
While the findings are encouraging, the researchers caution that AI should not be utilized as a solo detection tool without the supervision of a Consultant Dermatologist. A solitary incidence of basal cell carcinoma was missed out of 190, which was eventually found during a second read by a dermatologist ‘safety net.’ This illustrates the need to have sufficient clinical oversight of the AI.
We would like to stress that AI should not be used as a standalone tool in skin cancer detection and that AI is not a substitute for Consultant Dermatologists.
Dr. Irshad Zaki, Study Co-Author and Consultant Dermatologist at University Hospitals Birmingham NHS Foundation Trust
Dr Andrew concluded, “The role of AI in dermatology and the most appropriate pathway are debated. Further research with appropriate clinical oversight may allow the deployment of AI as a triage tool. However, any pathway must demonstrate cost-effectiveness, and AI is currently not a stand-alone tool in dermatology. Our data shows the great promise of AI in future provision of healthcare.”