Almost 20 years ago, our healthcare system declared war on variations in care, and population health was born. Its rules-based approach to standardizing care is based on averages across a population, and that’s the problem: Nobody’s average.
Why, after nearly 20 years, is now the time to change?
A convergence of needs, resources, and tools is creating the perfect opportunity to dramatically improve population health’s rules-based approach. The number and cost of interventions is rising exponentially, making the already painfully high cost of healthcare in the United States unbearable. Also, an exponential increase in data – and investments to deal with it – shows no signs of slowing, leaving healthcare leaders drowning in data and searching for a return on investment.
Meanwhile, breakthroughs in machine learning and cloud computing are unlocking the value in data to ease the pain caused by escalating interventions. Machine learning is the pinnacle of analytics. It goes a step beyond predictive modeling, which can forecast what will happen next, to predict what will happen in the future under specific sets of conditions. As McKinsey recently pointed out, technology pioneers such as Amazon, Google, and Netflix were rapid adopters of machine learning and have been using the technology to drive growth.
After all, what’s the point of predicting the future if you can’t change it?
Machine learning reveals cause-and-effect relationships in data, not just correlations, making it possible and practical to predict many future “what if” scenarios, to compare outcomes, and use that knowledge to optimize decisions, actions, and investments. Health plans, healthcare providers, pharmaceutical companies, researchers, and others are using machine learning today to improve medication adherence, prevent pre-term births, prevent metabolic syndrome from developing or progressing, and more.
To improve medication adherence, population health rules, HEDIS and NCQA delineated differentiators, use 80 percent adherence as the intervention threshold. It is blind to the potential value intervention would bring to individuals like Ethel, who takes medication to manage a chronic cardiovascular condition. With an adherence level of 82 percent, a rules-based population health program would not select Ethel for intervention.
In contrast, an approach that leverages new data and technology resources looks at many data points, not just Ethel’s adherence level. It delivers person-level insights that help population health leaders plan, implement, and refine care management programs. For each person in a population, for example, the approach evaluates and scores the individual’s risk of a complication related to poor adherence, determines how much change is needed to prevent the health event, predicts each individual’s likelihood to change their behavior, and matches people to the most-efficient effective intervention.
These models of risk, efficacy, engagement, and intervention reveal that Ethel is at high risk of a complication, and a 10 percent improvement in her adherence would prevent a health event predicted to cost $10,000. On this basis, the data-driven approach would select Ethel for intervention.
As this example demonstrates, data-driven approaches are transforming care management and care delivery by enabling person-level decisions on a population-level scale.
In future posts, we will explore how the GNS machine learning technology works to not only see the future, but to optimize it.
Contact us anytime at [email protected].
CEO, Chairman and Co-Founder