According to a recent study, a significant shift towards precision medicine has been observed, where AI is used not only to diagnose a disease a person already has, but also to predict who is most likely to get the disease in the future. Researchers at the University of Gothenburg analyzed health data from nearly 6 million Swedish adults. Unlike traditional screening, which primarily looks at age and gender, this AI model was given big data, including past medical diagnoses, detailed medication history, and sociodemographic data.
The most advanced models correctly identified future melanoma patients in 73% of cases. For comparison, models using only age and gender were only 64% accurate. The researchers were able to identify very small groups where the risk of developing melanoma within five years was up to 33%. Because melanoma can spread rapidly once it crosses the skin, early detection is the most effective way to reduce mortality.
“Our study shows that data already available within health care systems can be used to identify individuals at high risk of melanoma,” said Martin Gilstedt, doctoral student at the University of Gothenburg.
Because universal screening is both expensive and time-consuming, healthcare systems could use this AI to send targeted screening invitations to individuals at highest risk. Although the results are promising, the researchers noted that this AI risk score requires policy changes and further clinical validation before it becomes a standard part of your medical record.
“Our analysis shows that selective testing of smaller, higher-risk groups can lead to more accurate surveillance and more efficient use of health care resources,” said Sam Polesi, lead author of the study.
The study showed that AI models trained on large amounts of registry data could become important for more risk-tailored screening and future strategies. Nonetheless, the researchers emphasize that further research and policy decisions are necessary before this method can be incorporated into routine health care.
