NEW YORK: A novel machine-learning techniques to improve the quality of life for patients by reducing toxic chemotherapy and radiotherapy dosing for an aggressive form of brain cancer has been developed by MIT researchers. One among the scientist behind the new technique was an Indian origin.
Glioblastoma is a malignant tumour that appears in the brain or spinal cord, and the prognosis for adults is no more than five years. Patients are generally administered maximum safe drug doses to shrink the tumour as much as possible, but they still remain at risk of debilitating side effects. The new "self-learning" machine-learning technique could make the dosing regimen less toxic but still effective.
The 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.
It will probably be a while before this AI is used in the real world, but the promise it shows can no doubt help improve the quality of life of patients undergoing treatment.
“If all we want to do is reduce the mean tumour diameter, and let it take whatever actions it wants, it will administer drugs irresponsibly. Instead, we need to reduce the harmful actions it takes to get to that outcome," one of the scientists said.
The findings will be presented at the 2018 Machine Learning for Healthcare conference at Stanford University in California, US.
(With inputs from agencies)