Any large health organization that seeks to care for large numbers of individuals faces a daunting problem: how to best allocate scarce resources. Recent history would suggest that the industry hasn’t been handling the allocation problem very well. By some estimates, up to 40% of healthcare spending is wasted. Waste comes in several forms: failure to deliver care according to best practices, uncoordinated or fragmented care, over-treatment, and fraud. Identifying these sources of waste can be tricky. Fixing the problem is trickier yet.
While there are several culprits responsible for waste in healthcare spending, one major player has proven particularly difficult to manage: lack of ability to predict health outcomes. This lack of predictive power, results in sheer guesswork when it comes to the allocation of resources such as home care services. To be more accurate, prediction has been difficult until the recent advent of big data. Large-scale data analytics may soon provide the tools we need to make sure that precious healthcare dollars are spent wisely. To explain how this works, it may be useful to compare healthcare spending to weather prediction.
How Healthcare is Like Meteorology
Predicting healthcare outcomes is much like predicting the weather. In the days prior to computerized weather modeling, it was difficult, depending on where you lived, to predict chances of rain 48 hours into the future, to say nothing of accurately declaring a 5-day forecast. The New England Hurricane of 1938 caught weathermen completely off-guard, with devastating consequences for residents of Long Island. Early 20th century meteorologists simply did not have access to sophisticated analytics that could integrate thousands of pieces of data into a coherent picture. Today, accurate storm forecasts permit resources to be allocated appropriately well in advance of major storms (Hurricane Katrina notwithstanding: The meteorologists predicted the storm accurately; the response is another story).
Similarly, healthcare organizations in the past had access to large amounts of data (usually in the form of insurance claims) but they lacked the means to make sense of these data, or to learn lessons that could help them allocate resources to individual patients. For example, when individuals were admitted to the hospital following a heart attack, physicians and nurses created discharge plans based on practice guidelines that were, at best the result of carefully-designed clinical trials. In practice, these discharge plans were often based on judgment and experience, not on data.
Enter Big Data
How will the next generation of “healthcare meteorologists” improve outcomes for individual patients? By means of predictive analytics! Today, when a patient is admitted to the hospital for a heart attack, their individual case is compared with millions of prior cases whose outcomes are already known. Predictive analytics allows caregivers to input all of the patient’s unique data and generate a plan that is most likely to result in the best possible outcome. In this patient’s case, this would mean preventing hospital re-admission, choosing the appropriate level of post-acute care, and allowing them to return home as healthy as possible.
The promise of big data does not end when the patient leaves the hospital. Integrated systems of communication between the patient, their care providers, home care agencies and post-acute care facilities allow the system to learn from every patient who experiences a health event. Predictive analytics systems are designed to improve their outputs over time.
The Future of Big Data in Healthcare
In the past, decision-making in healthcare was often driven by templates and top-down practice guidelines. These worked well-enough, but big data promises to provide even better outcomes. Big data in healthcare creates decision-making processes that place the patient, not a bureaucratic, template-generating machine, at the center. The patient’s individual preferences and needs are the starting point. From there, healthcare providers will employ accurate, constantly improving data to draw a map of the shortest distance between the patient and the desired outcome, health and well-being. Today’s healthcare “weather forecasters” never had it so good.