Glioblastoma is the most aggressive form of brain cancer with a prognosis of no more than five years in adults. However its treatment is also just as aggressive in which doctors general administer the maximum drug dose (that falls within safety levels) to try and shrink the tumor as much as possible. As you might expect, this does have some pretty bad side effects.
However researchers from MIT Media Lab are proposing the use of AI that could make the administration of the drugs less toxic. How this works is through the use of a self-learning model where the AI will study treatment regimens that are already in use, and will then be able to adjust the doses until it finds an optimal plan.
This will involve giving patients the lowest possible potency of the drug and frequency of doses, that will still result in the tumor being shrunk to levels that are comparable to the traditional method. In a simulated trial of 50 patients, the AI managed to reduce the dosage to as little as a quarter of what is normally given, but yet managing to shrink the tumor by as much as the traditional way.