Drug overdose is the leading cause of accidental death in the U.S., with 52,404 lethal drug overdoses in 2015. Opioid addiction is driving this epidemic, with 20,101 overdose deaths related to prescription pain relievers, and 12,990 overdose deaths related to heroin in 2015, according to a report from the Centers for Disease Control and Prevention (CDC).
What’s behind this unfortunate trend? It is multifactorial. Paradoxically, improvements in healthcare over the last 20-some years are abetting the opioid epidemic. Hip replacements, knee replacements, spinal surgery and other procedures are now commonplace. More surgeries mean more patients who need pain relievers to help them with recovery – and then the subsequent potential for opioid addiction.
It is no longer safe to assume that opioid addicts hail from the segment of the population that uses street drugs. Today, it is much more difficult to identify and understand the people who might be addicted to opioids, because all kinds of people – the high school athlete, the middle-aged professional, the retired grandmother -- are prescribed opioids for myriad reasons and then are at risk for developing an addiction. This diversity is what has made prescription opioid addiction so difficult to manage. These patients become very skillful at obtaining their opiates from their pharmacy and not a dealer.
See also: The True Face of Opioid Addiction
With all of these changes, the experienced urban criminal detective is no longer the go-to resource used to identify opioid addicts. Alternatively, behavioral analytics is doing the job by making it possible to:
#1: Understand the potential for developing an opioid addiction among various populations.
For example, healthcare organizations could pull in information from the CDC, claims, electronic medical records and geo-spatial data to check if a geographic area has a large number of obese community members, who might have issues with hip, knee, ankle and lower back pain. Or, this data analysis could help identify areas where a significant number of patients present themselves to emergency departments to treat painful injuries in the wake of car or sporting accidents. Or, the analysis could identify when patients see more than one primary provider and have a list of pain conditions. As such, it’s possible to identify populations who are more likely to be prescribed opioids – and, subsequently, more apt to develop an addiction.
#2: Uncover patients with hidden opioid dependencies, including those on withdrawal medications.
An analysis of 800,000 Medicaid patients in a reasonably affluent state showed that 10,000 of them were taking a medication used to wean patients off a dependency on opiates. This particular medication is very expensive and difficult to obtain. Physicians need a specific certification to prescribe it. So it is safe to assume that the actual number of patients using prescription opiates is two to three times higher.
Those numbers aren’t always obvious, however, because the prescriptions may be obscured under diagnoses for other conditions such as depression. Indeed, more than half of uninsured non-elderly adults with opioid addiction had a mental illness in the prior year and more than 20% had a serious mental illness, such as depression, bipolar disorder or schizophrenia, according to the Kaiser Family Foundation. The result is that, without sophisticated behavioral analytics, it can be difficult to determine all the patients who are addicted to opioids.
Opiate monthly usage can be tracked, and variations in usage patterns is a strong clue.
And, what you don’t know can have a significant impact on care, costs and risk. For example, if the per member per month (PMPM) reimbursement for the year is $2,000, a patient – who is using this medication for withdrawal from an opiate dependency and is a diabetic – could end up costing an accountable care organization $10,000, five times the $2,000 per member per month reimbursement for the year. Healthcare organizations that use behavioral analytics will know they need to address the addiction first, removing it as a barrier to treating other chronic conditions.
See also: Is There an Answer to Opioid Crisis?
#3: Identify probable opioid fraud and abuse.
Analytics that rely on multiple behavioral data points can be leveraged to identify purchasing and prescribing patterns with a high probability of abuse. For example, analytics can be used to identify patients/members who are seeing more than 10 physicians or filling prescriptions at more than 10 pharmacies – an indicator for drug-seeking behavior. What’s challenging, however, is being able to discern legitimate reasons for these patterns, such as an oncology patient who is receiving multiple prescriptions from several different specialists. Next-generation analytics help by bringing in additional data, such as showing the locations of prescribers, pharmacies and the patient’s home on a map (geospatial analytics). Clustering in one location is likely to be normal, while filling several prescriptions at locations far away from the patient’s home can be a strong indicator of a problem.
These are just a few of the ways that behavioral analytics can be used to identify and manage opioid addiction. Can you think of other ways that behavioral analytics are currently being used – or could be used in the future?
