By Thomas R. Mika
“Big data” is helping physicians predict conditions ranging from sepsis to metabolic syndrome, a condition that can lead to chronic heart disease, stroke and diabetes. However, using big data in oncology seems to be the ultimate goal. Cancer is a nuanced disease, and as such, it can be difficult for physicians to determine the best treatment approach. Can big data help?
To clarify why the big data-cancer relationship might represent a special case, a specific insight comes into play. It involves the importance of getting over the “more is better” fallacy. Big data allows researchers to obtain an unprecedented quantity of information about cancer patients, and it is tempting to be impressed by the sheer volume of it all. But more data does not equal better data—the most complete quantitative profile of a patient is still just a collection of numbers, and until properly interpreted it is useless. Cancer is the ultimate personalized disease; no two cases are ever identical. As a result, a particular case of cancer might not be able to be discussed meaningfully in abstract terms—or serve as a predictive tool—without reference to the particular patient it afflicts.
Far from a case of Luddite thinking in medicine, this conclusion derives its force from the realities and limitations of our knowledge of cancer today. The tremendous range in the origin and progression of each form of cancer necessitates a level of decision-making that might never be reducible to algorithmic form. Another issue is tolerance for false positives and false negatives. For healthcare, and especially oncology, a false positive when it comes to predicting an individual’s response to targeted therapies might cause life-changing levels of anxiety, or worse, unneeded and often radical or toxic treatment. A false negative is equally bad, giving the illusion of good health that might cause a patient to pass the point at which treatment could have been life-saving. Until the tools for the analysis of cancer and the metabolic pathways it exploits are much more refined—a process that might take decades—there will be a need for human judgment in the interpretation of big data, and in no other area of medicine is this so clear as in oncology.
This does not mean that we should not continue to refine the use of big data in cancer care; only that we should be aware that there is more to proper insight than what an algorithm might manage on its own.
This philosophy is reflected in the activities of the company I lead, CollabRx. We are a provider of expert systems that inform therapeutic decision-making in oncology, and are developing two key tools: Therapy Finder™, a series of web-based expert system apps designed to enable oncologists and patients to learn which tests should be considered for tumor molecular analysis and how to use the results of those tests to evaluate therapy options, including approved and investigational drugs and clinical trials; and the Genetic Variant Annotation™ (GVA™) Service, a fully automated and scalable medical informatics solution to inform patient treatment planning by seamlessly pairing the results of genetic sequencing tests with clinically actionable and continuously updated knowledge.
We have also developed an app called CancerRx. Even the most knowledgeable oncologist can benefit from CancerRx, since the cancer treatment landscape changes quickly. The CancerRx app is a mobile resource designed to help oncologists navigate the complex landscape of oncology therapeutic options. It currently offers in-depth explanations of different treatment options for lung cancer, melanoma, metastatic breast cancer and colorectal cancer.
These explanations and advice come from leading experts in the field. Users can research drugs and therapies based on tumor profiles, the different stages as well as treatment history. In addition to weighing the pros and cons of different treatment options, CancerRx helps physicians identify the most relevant clinical trials that offer investigational therapies. This app also provides summaries and links to clinical findings published in top-tier medical journals. CancerRx comes with a special “daily oncology newsfeed” feature from the online medical news service MedPage Today, complete with real-time updates. All of the knowledge and research found in the app is curated from our highly qualified expert advisory network of more than 75 leading physicians, scientists and researchers from the nation’s most renowned academic and medical institutions.
Regarding the ultimate value of big data in cancer care, we are all waiting for more evidence pro or con. However, it seems sensible to me that no computer will push human experts out of the picture entirely.
Thomas R. Mika is President & CEO of CollabRx, Inc., a developer of cloud-based expert systems to inform healthcare decision-making.