When a patient shows a suspicious mole, the first step is often a screening to see if it needs a biopsy. In a large study across Australia and New Zealand, researchers looked at how artificial intelligence (AI) helped nurses during these screenings. They compared nurses using AI decision support against those using standard methods to see if the technology changed how they managed skin lesions.
The study looked at over one million skin lesions from more than 98,000 patients. The results showed that nurses using AI were more likely to detect malignancies, which are cancerous growths. Specifically, the AI group found 25.5 malignancies per 1,000 lesions, while the group without AI found 15.7. The AI also led to more recommendations for immediate action or safety-netting, which means extra steps to ensure a patient is monitored closely.
While the results are promising, it is important to note that this was an observational study, not a randomized trial. This means the researchers could not prove that the AI caused the better results, only that the two methods were associated with different outcomes. More prospective studies are needed to confirm these findings before they can be fully relied upon in every clinic.