The artificial intelligence model could be used to enable more efficient care for skin cancer patients and could lead to similar breakthroughs in the diagnosis and treatment of other cancers.
Researchers from the University of Helsinki, HUS Comprehensive Cancer Center, Aalto University and Stanford University have developed an artificial intelligence model that predicts which skin cancer patients will benefit from a treatment that activates the immune system. In practice, the AI model makes it possible to diagnose skin cancer by taking a blood test, to determine its prognosis and to target therapies in an ever more precise manner.
The skin cancer study was published in the prestigious Nature Communication log.
The right drug for the right patient
Stimulating the body’s defense system has proven to be a particularly effective therapy against skin cancer. The problem with therapies that activate the immune system lies in the differences between patient groups: while some patients may be considered cured, others derive no benefit from the treatment.
Previous research has not been able to provide doctors with tools to predict who will benefit from a treatment that activates the defense system. Correct targeting of therapies is extremely important, as drug therapies are expensive and serious adverse effects are quite common. »
Jani Huuhtanen, Doctor and PhD student, University of Helsinki and Aalto University
A complex AI model for a simple question
The international research group hypothesized that the immune cells of patients for whom the therapy was ineffective do not recognize skin cancer as an enemy, which is why the patients do not benefit from the treatment.
Using the AI model, the group analyzed samples from nearly 500 skin cancer patients and compared them to samples from nearly 1,000 healthy people. To aid in interpretation, the researchers used another AI model developed by Stanford University’s Mark M. Davis lab. From these samples, the researchers simply calculated the number of immune cells that recognized skin cancer.
As expected, more defensive cells detecting skin cancer were found in melanoma patients than in healthy patients.
“This discovery could in the future help identify skin cancer from a blood sample,” says professor of translational hematology Satu Mustjoki from the University of Helsinki.
Additionally, skin cancer patients who had more defensive cells that recognized skin cancer were more likely to benefit from therapies that activate the immune system than those who lacked such cells.
Focusing the AI model on other types of cancer
The use of AI models in medicine has grown exponentially, but their application to patient care requires long-term collaboration between physicians and AI researchers.
“In future studies, our goal is to explore the use of the currently developed AI model and determine whether it can also predict treatment responses for novel cancer therapies still in development,” says Associate Professor of computational biology and machine learning Harri Lähdesmäki of Aalto. University.
“Our AI model is nimble and adaptable, which allows calculating the number of cancer-detecting defensive cells also in the case of other cancers, including breast cancer, lung cancer and blood cancers,” adds Jani Huuhtanen.
“All of our research is based on open-source software, which makes our AI model available to other researchers and physicians, also enabling its further development,” says Huuhtanen.
#model #enable #effective #care #skin #cancer #patients