For a long time, physicians have recognized that the tools they have aren't powerful enough to treat complex diseases, like cancer. In addition to data science and models, clinicians also needed actual products — tools that physicians and researchers can draw upon to answer questions they regularly confront, such as “what clinical trials are available for this patient that I’m seeing right now?” In this episode, our host Kyle interviews guests Alex Grigorenko and Iker Huerga from Memorial Sloan Kettering Cancer Center to talk about how data and technology can be used to prevent, control and ultimately cure cancer.
A lot has been said during the past several years about how precision medicine and how genetic testing is going to revolutionize the way diseases like cancer are treated. Although genetic testing brings a lot of promise to advance our understanding of cancer and provide more precise and effective treatments, progress has been slow due to significant amount of manual work that is still needed to understand genomics.
MSK’s Cancer Center has been working with data scientists to help doctors make better cancer treatment choices. The human interaction between patient and physician will continue to be important, but data scientists will have a measurable impact on the future of healthcare.
Meanwhile, there’s a huge desire to treat patients with novel treatments. Clinical trials are not organized well in terms of what clinical trial you want. Hence, Alex Grigorenko’s team has been developing a recommender based of the current understanding of a patient’s history and medical records to see which clinical trials can be recommended for the patient. With the tools Alex’s team has been developing, the machine can learn what part of the medical record matters.
MSKCC recently launched a competition, in which participants would develop an algorithm that can distinguish and interpret genetic mutations that contribute to tumor growth from neutral mutations. The reason for this competition is that the interpretation of genetic mutations is currently all done manually, which is a very time-consuming task where a clinical pathologist has to manually review and classify every single genetic mutation based on evidence from text-based clinical literature. Hence, for this competition, MSKCC provided an expert-annotated knowledge base of manually annotated thousands of mutations for participants to develop an algorithm that, using this knowledge base as a baseline, automatically classifies genetic variations.