Artificial intelligence software can reportedly detect melanomas with 100% accuracy.
A new study presented Wednesday at the European Academy of Dermatology and Venereology Congress 2023 showed that AI can catch potentially fatal cases of cancer in early stages.
“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,” lead author Dr. Kashini Andrew, specialist registrar at University Hospitals Birmingham NHS Foundation Trust, said in a statement.
AI assessed 22,356 patients with suspected skin cancer over two and a half years.
The program detected 189 out of all 190 skin cancers (99.5%) that occurred in this population, as well as 541 out of 585 precancerous lesions (92.5%) and all 59 melanoma cases.
The first AI model, tested in 2021, only detected 85.9% (195 of 227) of melanoma cases, 83.8% (903 of 1,078) of skin cancers and 54.1% (496 of 917) of precancerous lesions.
“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, freeing up more time for patients that need urgent attention,” Andrew said.
However, researchers note that this software should not replace a dermatologist and should be used in tandem with professional care.
“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,” emphasized co-author Dr. Irshad Zaki, consultant dermatologist at UHB NHS Foundation Trust.
A single case of basal cell carcinoma out of 190 was missed — it was later discovered by a dermatologist “safety net,” which further shows that AI should not be the sole detection method.
“The role of AI in dermatology and the most appropriate pathway are debated,” Andrew said.
He added, “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 health care.”