Artificial intelligence (AI) technology has become a formidable player in the rapidly evolving healthcare landscape, so much so that 56% of US healthcare leaders find that AI has brought greater value than expected. One of the most notable areas where AI has found a substantial impact is in the field of dermatology.

A study, presented on October 11 at the European Academy of Dermatology and Venereology (EADV) Congress 2023, reveals that a new AI software demonstrated a remarkable 100% sensitivity in detecting melanoma – the most severe form of skin cancer.

Over a 2.5-year period, the research team assessed 22,356 patients with suspected skin cancers, showcasing the prowess of the third version of the AI software. Besides melanoma, the tool also demonstrated an impressive 99.5% accuracy in detecting all types of skin cancers and a notable 92.5% accuracy in identifying pre-cancerous lesions.

The progression from the initial model, tested in 2021, highlights the rapid advancements in AI technology. The first version detected 85.9% of melanoma cases, 83.8% of all skin cancers, and 54.1% of precancerous lesions. The latest findings underscore how AI is evolving and learning, with improvements attributed to enhanced training techniques and the quality of data used for training.

Dr. Kashini Andrew, the lead author and Specialist Registrar at University Hospitals Birmingham NHS Foundation Trust, emphasized the tangible impact of the latest software. “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.

Despite the encouraging results, the research team emphasizes that AI should not be considered a standalone detection tool and must be used in conjunction with the expertise of a Consultant Dermatologist. The study identified a single case of basal cell carcinoma that was initially missed by the AI but later detected during a second read by a dermatologist, highlighting the crucial role of clinical oversight.

Dr. Andrew added, “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.”

The groundbreaking study marks a significant stride in leveraging AI for early detection of skin cancer, offering hope for improved patient outcomes and a more efficient healthcare system.

As technology continues to advance, the collaborative efforts of AI and medical professionals could pave the way for transformative changes in the field of dermatology and beyond.