How analytics empowers precision medicine
In the world of medicine, trial and error is largely the norm today. Doctors make a "most likely" diagnosis consistent with symptoms and prescribe treatment accordingly—treatment that might include drugs, devices or surgery. If the treatment doesn't work, the doctor most likely alters dosage or prescribes something else. This iterative cycle is repeated until the diagnosis and treatment present the desired clinical outcome.
The bad news is that this paradigm has reached a point of diminishing returns, as evidenced by the fact that most drugs prescribed in the United States today are effective with fewer than 60 percent of treated patients. The good news is that new technology could transform trial-and-error medicine, replacing it with an evidence-driven paradigm—one in which each patient receives care, medication and treatment predicated on his or her unique genomic profile and its attributes.
This is known as precision medicine or sometimes personalized medicine. The first step of precision medicine is mapping a person’s genomic profile. Then, by analyzing and correlating vast pools of genomic data, researchers and doctors can identify variances and biomarkers for potential diseases, which will shape what treatment is best, assuring the best therapeutic outcome with minimal adverse effects. This type of treatment is made possibly by genomic profiling platforms, electronic health records (EHRs), analytics tools for self-service data discovery, visual and predictive analytics with machine learning, and other new tools.
Thus, personalized or precision medicine is essentially the ability to tailor treatments, as well as prevention strategies, to the unique characteristics of each person. Meanwhile, the closest real-world analogy to this process would be a recruitment system that matches a person’s job to his or her education, experience and skill sets as laid out in a profile to ensure the best fit for the job.
In recent years, precision medicine has attracted significant hype and sometimes pessimism from a number of quarters (including, perhaps unsurprisingly, the pharma industry). It's sometimes perceived as “avant garde” -- a grandiose vision that is way out there and not yet ready for useful value delivery to real-world patients and consumers. But considering we can already present real-world examples, it's clear that precision medicine holds promise and is poised to continue replacing trial-and-error approaches.
One of the pre-eminent areas of application of precision medicine for personalized healthcare delivery pertains to the diagnosis and treatment of cancer. Here, personalization can take several different forms, such as looking at the person’s genomic profile to determine if he/she has certain genetic mutations that could put them at a higher risk for developing cancer, and whether they can handle specific drugs and treatment protocols; or testing a patient’s tumor or cancer to figure out the best treatment protocols that will deliver the optimal outcomes
One real-world example involves breast cancer treatment. Certain kinds of breast cancer are not candidates for chemotherapy alone. But Herceptin, a monoclonal antibody delivered by Genentech, has been found to be particularly efficacious as a first-line treatment with chemotherapy for aggressive forms of breast cancer in women whose tumors have an overabundance of HER2, a protein that promotes cell growth.
Herceptin has been found to reduce the likelihood of cancer spreading to other parts of the body in such patients by a remarkable 53 percent, compared with traditional chemotherapy alone. This is compelling from both an outcomes perspective and a cost-benefit perspective. The tests to detect whether a breast cancer patient has an overabundance of HER2 protein (and thereby is a candidate for Herceptin) cost a mere $400. Plus, the test potentially saves thousands of dollars by preventing the cancer in HER2 patients from spreading to other parts of the body and by not treating HER2-negative patients with a drug that won’t do anything.
In essence, this kind of precision medicine means the "mass customization” of cancer treatment.
Another game-changing example comes from the Inova Translational Medicine Institute (ITMI), which is at the forefront of precision medicine delivery in the United States. ITMI captures genomic profiles of every newborn infant and their parents, and then analyzes these for variances and mutations using visual analytics software. By visualizing the data, doctors can proactively identify, at birth, biomarkers for chronic diseases like heart disease, chronic obstructive pulmonary disease (COPD), cancer, Alzheimer’s disease. This helps physicians and clinicians tailor the treatment each infant receives.
A biomarker is a biological molecule found in blood, tissue or body fluids that can be used to identify the presence of an abnormal process or disease. For example, a biomarker may be secreted by a certain type of tumor, or it could be a physical response by the body’s immune system to the presence of a tumor. By identifying biomarkers, researchers and physicians can determine whether a specific treatment is appropriate for a specific tumor type and track their ongoing presence or absence as a measure of how well the body responds to a treatment.
ITMI is also a leader in integrating genomic data with patient information from its Epic electronic medical records system. This helps ITMI track progress over time to ensure that chronic diseases can actually be prevented before they occur, which is key to bending the cost curve.
These are just two examples that show how precision medicine can have a tangible impact, not just on health and outcomes, but on cost. And as already demonstrated, healthcare IT and analytics—including EHRs, self-service data discovery, visual and predictive analytics leveraging machine learning—are core and mission-critical to making precision medicine a reality.