Precision Medicine: How will we get there?
November 20, 2015
Precision medicine has become a buzz phrase in recent times with the President announcing the Precision Medicine Initiative earlier this year. Instead of a "One size fits all" approach, precision medicine gives clinicians tools to better understand the complex mechanisms underlying a patient’s health, disease, or condition, and to better predict which treatments will be most effective.
Achieving this goal will require understanding differences between individuals and how these impact each person’s health. A recent study in CELL is a great example of this model. The researchers were able to analyze the impact of many variables of each participant and the impact of these variables on blood sugar levels. They found large variations in post-prandial sugar levels which were not fully explained by known factors like insulin resistance. They then used machine learning to develop models to predict post-prandial sugar levels. They validated these models in a second set of participants. Using these models they were able to design diets that were better at improving post-prandial sugar levels than standard diets that relied on measures like glycemic loads.
A key part of this study was the use of sensors and wearable devices that tracked the participants' activity and sugar levels. The other notable feature was the use of machine learning to develop algorithms for predictive models. As we get into the realm of big data we will have to turn to computers to help make sense of these numbers. These tools will help manage health of individuals and populations.
It is high time that our medical schools and residency programs partner with computer science programs to codevelop curricula and implement project-based learning to leverage these tools and techniques to improve the health of our patients.
Neil Mehta, MBBS, MS
Assistant Dean, Education Technology, Cleveland Clinic Lerner College of Medicine
Web Editor, JGIM