opioid analytics

INDUSTRY INSIGHT

How data and analytics can help mitigate the opioid epidemic

According to the Centers for Disease Control and Prevention, an average of 90 people die each day from opioids in the United States.

President Donald Trump has declared the problem a public health emergency. The underlying causes and impact of this problem are complicated, and there is no one-size-fits-all solution to this crisis. It will take a powerful community of partners -- law enforcement, healthcare, social services, non-profits and the private sector -- working together to begin tackling this problem.

Data and analytics, however, can play an important role in helping communities understand and address the issue.  The key to success is uncovering the connections among patients, providers, pharmacists and associates to find hidden relationships and information-sharing networks.

Exposing the social networks behind criminal opioid enterprises

One of the most common criminal enterprise fueling the opioid epidemic are "pill mills" -- providers, clinics or pharmacies that dispense prescription drugs to those who take them for recreational use or sell them on the black market.  The prescription opioids coming from pill mill operators are often paid for by Medicaid and Medicare taxpayer dollars.

Key partners probing pill mills include state Medicaid fraud control units and the federal Departments of Justice and of Health and Human Services. These investigators typically examine pharmacy and medical claims data, information from Prescription Drug Monitoring Programs and Drug Enforcement Agency files. That’s a great start, but it only scratches the surface.

Pill mills can be multidimensional, consisting of networks of people using identities designed to avoid detection. The key to addressing the pill mills is uncovering the relationships among patients, providers, pharmacists and associates. To accomplish this, agencies need access to disparate, relevant and proven information  -- including public records  and data from providers, pharmacy and claims – as well as advanced linking technology and visualization capabilities that illustrate connections in social networks.

Using social network analytics not only identifies hidden relationships and links, but it also reveals hidden patterns of information sharing and interactions within the potentially fraudulent clusters, such as:

  • Patient relationships with known perpetrators of healthcare fraud/opioid trafficking.
  • Links among recipients, businesses, assets, relatives and associates.
  • Links between licensed and non-licensed providers.
  • Risky relationships among patients, providers, social groups and pharmacies.

Social network analytics also can help investigators triangulate which social groups merit scrutiny for possible opioid trafficking.

Using such data will show, for example, whether patients routinely go out of their way to visit specific doctors for prescriptions or whether the volume of opioids dispensed from pharmacies is appropriate. Similarly, examining this powerful combination of data can also show whether providers, pharmacists and patients have current relationships with criminals known for trafficking drugs.

The role of data and analytics in treatment

We must understand who is at risk of becoming addicted – and not just by relying on patients' clinical profile. Social determinants of health – or information on the conditions where people live, learn, work, and relax -- can play a critical role in stemming the tide of the epidemic. SDOH data can take many forms, but often it is limited to basic identity data readily available to an agency and too often provides only a glimpse into a patient's life. SDOH can be much more effective when it looks at a person as an individual and is informed by robust identity datasets such as those in public records.

By using extensive identity datasets, scoring and analytics, a public health care agency can better engage an at-risk person by asking key questions:

  • Is the patient facing personal hardship, such as a bankruptcy or divorce?
  • Does a patient live in a high-risk neighborhood?
  • Is the patient isolated from work colleagues, friends and/or family?
  • Does the patient’s educational background indicate there may be a low health literacy rate?

By scoring and prioritizing those at risk and those likely to seek help, medical professionals can develop clinical programs and engage additional resources, such as social services programs, tailored to socioeconomic needs.

Next steps

The opioid crisis is unlike any other public health emergency that we have faced. To solve it will require a community of partners ready to examine the underlying issues behind the criminal element spearheading the crisis, as well as the reasons why so many have fallen victim to it. Data, linking and analytics, while only one toolset to help address the problem, are critical.

About the Author

Haywood “Woody” Talcove is CEO, LexisNexis Special Services Inc. and Government, LexisNexis Risk Solutions.

inside gcn

  • pollution (Shutterstock.com)

    Machine learning improves contamination monitoring

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group