Researchers from the University of Helsinki have developed a model for artificial intelligence. In practice, the AI model allows with a blood test to diagnose skin cancer, determine its prognosis and use therapies with increasing accuracy, writes the university in a Press release.
The research project was conducted in collaboration with HUS Comprehensive Cancer Center, Aalto University and Stanford University. Using the AI model, the team analyzed samples from nearly 500 skin cancer patients and compared them to samples from nearly 1,000 healthy individuals. For the interpretation, the researchers used a different artificial intelligence model developed by Stanford University. From these samples, the researchers calculated the number of immune cells capable of recognizing skin cancer.
Immune cells and new applications
As expected, more immune cells that recognized skin cancer were found in patients with the disease than in healthy patients. Additionally, skin cancer patients with these immune cells benefited more from therapies that activate the immune system than patients who did not have such cells.
“Before this, it was not possible for doctors to predict who would benefit from treatment and who would not. The right approach is extremely important because drug therapies are expensive and severe side effects can often occur, “concludes Dr Jani Huuhtanen of the University of Helsinki and Aalto University. Researchers will now examine whether the AI model works. also for other types of cancer.
