The United States spends more on health care than do 13 other high-income countries, according to The Commonwealth Fund’s “U.S. Health Care from a Global Perspective” report.
It is estimated that nearly 20 percent of that spend goes to waste, including overtreatment, lack of care coordination, and fraud.
Minimizing wasteful medical spending — spending that could be cut without negatively affecting access to care, quality of care, or health outcomes — represents a significant opportunity to reduce not just direct medical costs but costs associated with insurance premiums, which have been increasing between 3 and 13 percent per year since 2000 and outpacing inflation and earning increases (which usually hover between 2 and 4 percent).[1, 2]
Doing so also has the potential to improve quality in ways that benefit employers, health plans and patients alike.
Predictive analytics — using data and algorithms to predict a particular event — provides a tool to reduce wasteful spending in such areas as unnecessary tests or procedures, inappropriate place of service, and wrong diagnosis or care.
Unnecessary tests or procedures
A commonly cited example of wasteful spending is prostate cancer testing. The U.S. Preventive Services Task Force gives the PSA test (a blood test) a “D” grade, noting that the test often produces false positives and exposes the patient to the subsequent risk and cost of unnecessary treatment.
Further, as the website Choosingwisely.org explains, using imaging scans (such as CT, PET or bone scans) on patients who have been deemed to have early-stage prostate cancer that will not likely spread, exposes the patient to the risk of radiation, high costs, and false positives that could lead to additional stress and the cost and risk of unneeded treatment.
Put simply, the risks outweigh the potential benefits for otherwise healthy men. Predictive analytics can help reduce this wasteful spending by proactively reaching out to men with information about the risks and benefits of such tests and letting them know to question their doctor’s recommendation for prostate cancer tests.
Inappropriate place of service
An illustrative example is the common ordering of an imaging test. The out-of-pocket price for a standard chest x-ray, CT scan, or ultrasound can vary by hundreds of dollars, depending on where the imaging is done. Often the stress, confusion or simple lack of knowledge can lead to such tests being performed at unnecessary expensive facilities.
Take, for example, a doctor who orders an MRI test for a patient. The patient then schedules the MRI at the local hospital, even though the same screening could have been done at a nearby standalone clinic for a fraction of the price. In some of these cases, the individual may not have the comparative information readily available when making a care decision; and an urgent-seeming situation precludes the patient from doing research.
In other cases patients simply don’t know that price differences exist from facility to facility (or how great those differences can be), and therefore don’t choose to shop around. Predictive analytics can be used to proactively intercept individuals who may require an MRI based on risk scoring models and generate awareness of the disparities in price in order to promote shopping around when they actually end up in the market for this service.
Delivering information proactively can save the patient from making a potentially very costly choice that ultimately does not improve their quality of care or health outcomes.
Wrong diagnosis or care
Incorrect diagnoses and/or inappropriate treatment plans account for another portion of wasteful medical spending. For example, a recent update on the Spine Patient Outcomes Research Trial revealed that eight-year outcomes were not significantly different between surgical and nonsurgical treatment for spinal stenosis patients.
Despite this evidence and regardless of the fact that the costs of surgery and lost productivity due to absences at work are significantly greater than those for non-surgical treatments, the rates of spinal stenosis surgery have risen considerably over the past decades.
This source of wasteful spending may be more common than many think. According to a 2012 survey, 37 percent of medical diagnoses are wrong, and 75 percent of treatment plans require a correction.
In these types of examples, predictive analytics can help target patients who have received particular diagnoses and may be heading down a path of treatment for which the outcomes are questionable and equip them with resources (such as information about free expert medical-opinion services) that can help ensure they have the correct diagnoses and treatment plans before moving forward.
Put simply big data (and the predictive analytic applications that use them) helps faster identification high-risk patients; better intervention; and better follow-through from HIPAA-compliant, data-driven monitoring.
A recent Forrester research study shows that predictive analytic technology is on the minds of human resources professionals.
In a survey of 100 such professionals, 62 percent said they would like to use predictive analytics to provide the right care to each employee in order to optimize benefits utilization; half reported that they see value in using this type of technology to direct employees to the right provider.
Predictive analytics gives HR professionals real-time insight, allowing them to connect with the right people at the right time (i.e. before they make a potentially costly or harmful choice).
The Forrester research study concluded that hyper-personalized messaging can help employees use the right benefits, in the right way, and at the right time — and big data and predictive analytics are needed to create and execute these messages. Organizations wishing to adopt these technologies should look at these five key capabilities.
The ability to engineer predictive analytics into existing benefits hubs or implement a single-source portal.
The ability to ingest a myriad of data, including demographics data; clinical data, such as medical and pharmacy claims and data from labs, biometrics, and wearables; encounter/program utilization data; environmental data, such as weather, pollen and air quality; contextual data, such as location or device; and self-reported data that provides as close to a real-time picture of the employee’s prioritized needs and opportunities as possible.
Predictive analytics to build personalized benefits profiles for each employee and covered spouse that “learns” about the individual with each interaction with benefits and during specific life events.
Hyper-personalized push messages to employees and covered dependents when they need it.
The ability to monitor the impact of messages on benefit utilization and costs.
Utilizing technologies with these capabilities promises to be a more reliable way to reduce wasteful health care spending, thus saving money for patients and payers and reducing the risk, harm, and cost of unneeded or ineffective care.