AI Tool Identifies Novel Genetic Signatures to Personalize Cancer Therapies

Lung cancer and bladder cancer are among the most commonly diagnosed cancers globally. Researchers have now developed artificial intelligence (AI) models designed to personalize immune therapies for oncology patients.

In a new study, scientists at the Institute of Science of Data and Artificial Intelligence (DATAI) at the University of Navarra (Pamplona, Spain) analyzed data from over 3,000 patients diagnosed with lung and bladder cancers. By employing machine learning models, the researchers discovered new genetic signatures unique to each stage of these cancers and created a system known as the "IFIT index" (Index of "Physical Immunity"). This system is aimed at personalizing therapies to enhance their effectiveness. The IFIT index measures a patient's immunological fitness, categorizing them based on their risk at various stages of the disease. This approach allows for predicting how well a patient will respond to treatment depending on the activity of their immune system in different stages of cancer treatment.

Image: The artificial intelligence models can personalize immune therapies in oncology patients (Photo courtesy of 123RF)

The research, published in the Journal for ImmunoTherapy of Cancer, is based on an analysis of the cancer immunity cycle (CIC), which looks at how immune system signals affect the success of immunotherapy. Using this framework and AI tools, the researchers identified specific patterns of cellular activity linked to the molecular stages of the disease and developed the IFIT index. This innovation highlights the potential of AI in advancing personalized medicine and offers new prospects in the fight against cancer. The team also indicated that this technique will continue to be refined through future collaborative studies involving other cancer types.

"Immunotherapy represents one of the most promising frontiers in the fight against cancer, and by using artificial intelligence models, we can further fine-tune treatments based on each patient's immune profile," said Rubén Armañanzas, leader of DATAI's laboratory Digital Medicine and one of the lead authors of the study.