Researchers Develop AI Model to Make Cancer Treatment Less Toxic

By MedImaging International staff writers
Posted on 20 Aug 2018

Researchers from the Massachusetts Institute of Technology (Cambridge, MA, USA) have developed an artificial intelligence model that “learns” from patient data to make cancer-dosing regimens less toxic but still effective.

In a paper presented at the 2018 Machine Learning for Healthcare conference at Stanford University, MIT Media Lab researchers have detailed a novel machine-learning technique to improve the quality of life for patients by reducing toxic chemotherapy and radiotherapy dosing for glioblastoma, the most aggressive form of brain cancer. The “self-learning” machine-learning technique looks at the current treatment regimens in use and iteratively adjusts the doses, eventually finding an optimal treatment plan, with the lowest possible potency and frequency of doses that should still reduce tumor sizes to a degree comparable to that of traditional regimens.

Image: Researchers aim to improve the quality of life for patients suffering from glioblastoma with a machine-learning model that makes chemotherapy and radiotherapy dosing regimens less toxic but still as effective as human-designed regimens (Photo courtesy of MIT).

In simulated trials of 50 patients, the machine-learning model designed treatment cycles that reduced the potency to a quarter or half of nearly all the doses while maintaining the same tumor-shrinking potential. It skipped doses altogether several times and scheduled administrations only twice a year instead of monthly.

The model is a major improvement over the conventional “eye-balling” method of administering doses, observing how patients respond, and adjusting accordingly, according to Nicholas J. Schork, a professor and director of human biology at the J. Craig Venter Institute, and an expert in clinical trial design. “[Humans don’t] have the in-depth perception that a machine looking at tons of data has, so the human process is slow, tedious, and inexact,” he said. “Here, you’re just letting a computer look for patterns in the data, which would take forever for a human to sift through, and use those patterns to find optimal doses.”

According to Schork, the work could be of particular interest to the US FDA, which is currently looking for ways to leverage data and artificial intelligence to develop health technologies. Regulations still need be established, he said, “but I don’t doubt, in a short amount of time, the FDA will figure out how to vet these [technologies] appropriately, so they can be used in everyday clinical programs.”

Related Links:
Massachusetts Institute of Technology