Microsoft is taking their Machine Learning prowess and applying it to research into cancer care.
While some of their approaches are at the basic science level, many are applicable to a practicing oncologist.
One team of researchers is using machine learning and natural language processing to help the world’s leading oncologists figure out the most effective, individualized cancer treatment for their patients, by providing an intuitive way to sort through all the research data available.
Yet another group of researchers has created powerful algorithms that help scientists understand how cancers develop and what treatments will work best to fight them.
These approaches are looking for ways to unlock all of the disparate research available and pair it with the as-of-now unstructured data within a provider's EMR to find patients that could benefit from the results of these studies. Each patient's conditions could be algorithmically matched against all available research to give a doctor treatment options that may not have otherwise been known to that doctor.
Another is pairing machine learning with computer vision to give radiologists a more detailed understanding of how their patients’ tumors are progressing.
Using machine learning to find otherwise hidden insights in diagnostic imagery will give oncologists additional information to help them with their treatment plans.
Machine learning provides us a huge opportunity to augment the abilities of today's oncologists - to give them more information, and greater depths of information, enabling them to make build more-targeted treatment plans, faster than ever. We known that in cancer the earlier we identify the disease and apply the right treatment, the better the outcomes - machine learning can help.