Enhancing melanoma detection in primary care with AI

The mobile app developed uses AI to analyze images of suspected skin lesions, aiding physicians in distinguishing melanomas from non-threatening skin changes. Magnus Falk, a senior associate professor at Linköping University and a study lead, highlighted the novelty of applying AI in this context, emphasizing its potential to streamline primary care diagnostics.

Differentiating melanoma from other skin changes poses a challenge, even for seasoned physicians. Early detection is crucial, given melanoma's severity. However, the lack of established AI support in assessing skin lesions within Swedish healthcare points to a significant gap the app aims to fill.

"Primary care physicians encounter many skin lesions every day and with limited resources need to make decisions about treatment in cases of suspected skin melanoma. This often results in an abundance of referrals to specialists or the removal of skin lesions, which in the majority of cases turn out to be harmless. We wanted to see if the AI support tool in the app could perform better than primary care physicians when it comes to identifying pigmented skin lesions as dangerous or not, in comparison with the final diagnosis," says Panos Papachristou, researcher affiliated with Karolinska Institutet and specialist in general practice, main author of the study and co-founder of the company that developed the app.

The researchers plan to conduct a larger, follow-up study across several countries to further assess the app's utility as an active decision support tool. This initiative, supported by Region Östergötland and the Analytic Imaging Diagnostics Arena (AIDA), underscores the ongoing effort to integrate AI technologies into healthcare for improved patient outcomes.

Linköping University's study represents a significant advancement in the application of AI for melanoma detection. By offering a reliable tool for primary care physicians, the app promises to enhance the accuracy of melanoma diagnoses, ultimately leading to better patient care and outcomes.

MEDICA-tradefair.com; Source: Linköping University