MIT researchers have developed an Artificial Intelligence (AI) system that can help reduce toxic chemotherapy dosing for the most aggressive form of brain cancer, potentially improving patient quality of life.
Glioblastoma is a malignant tumor that enters the brain or spinal cord and the prognosis for adults is no more than five years.
Patients must withstand a combination of radiotherapy and several medications taken each month.
Physicians generally administer maximum safe drug doses to shrink the tumor as much as possible. However, these potent drugs still cause debilitating side effects in patients.
Researchers from the Massachusetts Institute of Technology describe a model that could make dosing schemes less toxic but still effective. Driven by a "self-learning" machine learning technique, the model considers the treatment regimes currently used and iteratively adjusts the dosages. It usually finds an optimal treatment plan with the lowest possible potency and frequency of doses, which should still reduce tumor size to a level comparable to that of conventional therapies.