I’m an actuary. That means I use numbers to try to understand human behavior, manage risk, and evaluate the likelihood that a particular thing will happen in the future.
Most people associate my work with green eyeshades and the morbid business of predicting how long someone is likely to live. But actuaries are on the ground floor of precision medicine, which will rely in part on number-fueled predictive modeling.
If you’ve ever bought something on Amazon or watched movies on Netflix, you’ve been the beneficiary — or the target — of predictive modeling: If you liked “Shrek,” you might like “Kung Fu Panda.” In health care, predictive analytics are used to identify leading indicators of disease, spot patient trends, and help health care providers establish effective treatments. And as the health care industry embraces precision medicine to provide customized treatment, it will need to adopt more precise predictive models to identify high-risk patients and tailor interventions to meet their needs.
In today’s ever-changing landscape, the health actuary is part clinician, epidemiologist, health economist, and statistician. He or she combines financial, operational, and clinical data, such as information from electronic medical records, pharmacy use, and lab results, to provide insights on both individual patients and overall population health.
I see a future where predictive modeling helps health care companies not only suggest healthy behaviors but also convince patients and consumers to adopt them. Predictive modeling techniques can be applied to information that can influence an individual’s decision to use preventive care, accurately take prescribed medication, book a doctor appointment, lose weight, or become more physically active.
The trick will be identifying the trigger that gets him or her to act.
Insurers must understand their patient populations, including the barriers they face to achieving better health. To create solutions, insurers must first understand the psychology of motivation and what leads individuals to change their behavior. That’s where the precision approach comes into play.
Technology companies and political campaigns have been analyzing personal habits and behaviors for years to predict what people will buy or how they will vote. The property and casualty side of the auto insurance industry uses credit scores to help predict the odds that a driver will file a claim. People with better credit scores tend to get more favorable rates.
By combining clinical data and non-health-related indicators, such as hobbies and lifestyle attributes, predictive modelers will be able to determine how to increase the likelihood of strong patient participation in their own care management programs.
Amazon pioneered the personal recommendation by leveraging predictive analytics. Netflix perfected it by using predictive models to understand its members’ streaming habits and suggest movies they may like. Neither of these companies get involved in more complicated aspects of human life. If Netflix recommends a bad movie, there’s no loss other than a couple of hours.
In health care, the stakes are higher. Although using predictive modeling to influence behavior won’t be as easy as convincing someone to click on a movie, it may save more than a few lives.