A study of the entire Swedish adult population, analyzing registry data on age, gender, diagnosis, and socio-economic status, found that artificial intelligence (AI) models were able to predict melanoma incidence with almost 73% accuracy.
A collaboration between the University of Gothenburg and Chalmers University of Technology applied an analytical AI model to a data pool containing more than 6 million Swedish adults.
Using registry data from 6,036,186 people, the AI was able to identify small groups at high risk of developing melanoma with a high level of accuracy, based on demographic factors such as age and gender.
This data focuses on over 38,000 cancer diagnoses
When only age and gender were incorporated into the registry data, the AI model was able to distinguish between people who later developed melanoma with about 64% accuracy. A more advanced model leveraging comprehensive demographic data increased accuracy to 73%.
Providing the model with diagnostic, medication, and sociodemographic data can identify a smaller high-risk group with a 33% risk of developing melanoma within five years.
Of the 6,036,186 people studied through registry data, 38,582 (0.64%) were diagnosed with melanoma during the 5-year study.
Make your cancer screening strategy more efficient
“Our study shows that data already available within the healthcare system can be used to identify individuals at high risk of melanoma,” says Martin Gilstedt, PhD student at Sahlgrenska Academy, University of Gothenburg and statistician at the Department of Dermatology and Venereal Diseases at Sahlgrenska University Hospital.
“Although this is not a form of decision support currently available in routine healthcare, our results clearly demonstrate that registry data can be used more strategically in the future.”
The study, published in Acta Dermato-Venereologica, was led by Sam Polesie, associate professor of dermatology and venereology at the University of Gothenburg and dermatologist at Sahlgrenska University Hospital.
“Our analysis suggests that selectively screening small, high-risk groups could lead to both more accurate monitoring and more efficient utilization of health care resources. This includes incorporating population data into precision medicine and complementing clinical assessments.”
The paper cautions that the use of AI models trained on registry data is still evolving and requires further research. However, early results like those from this study suggest that AI has the potential to make future skin cancer screening strategies more effective.
Source link
