AI predicts brain cancer patients’ survival.

New research from King’s College London has shown that artificial intelligence (AI) can predict the survival of brain cancer patients who have received radiotherapy treatment. The use of AI in predicting patient outcomes could provide clinicians with valuable information for treatment planning and enable patients to be referred to life-saving treatments more quickly. This is the first application of AI to predict short-term and long-term survival rates for brain cancer patients. Glioblastoma, a difficult-to-treat cancer, has a survival rate of just 25% after one year of diagnosis. The deep learning model created by the researchers was trained on a dataset of brain cancer patients’ MRI scans, allowing for the accurate prediction of patient outcomes after eight months of radiotherapy treatment. Currently, patients undergo routine scans to determine the effectiveness of chemotherapy, resulting in some patients undergoing ineffective chemotherapy that causes harmful side effects. By providing an immediate and accurate prediction of patient survival, AI can identify patients who would not benefit from chemotherapy and instead explore alternative treatments or clinical trials.