A Big Data Approach to Tackling the Opioid Crisis
A predictive analytics platform to identify who may be at risk of developing an addiction to opioids.
DataStax and Deloitte, United States
The United States is in the midst of an opioid epidemic that claims the lives of more than 130 people each day. It began in the 1990s, with the over-prescription of opioids to treat all sorts of pain and was made much worse when people began moving to more potent kinds of opioids, such as heroin and synthetic opioids like fentanyl.
According to the direst predictions, the United States risks losing the equivalent of a whole American city in just one decade to the crisis. But the problem isn't just confined to the US. The World Health Organization's information sheet on opioid abuse states that in 2016 an estimated 27 million people across the world suffered from opioid use disorders.
Tackling what’s been called the most complex public health issue of our time involves a whole range of interventions on both the demand and the supply side. While there is no single path to bring the epidemic under control, a data-driven approach may prove to be an effective way of reducing opioid misuse.
One way of fighting the opioid crisis with data is with Opioid360, a predictive analytics platform created by DataStax and Deloitte that’s designed to identify individuals at risk of becoming opioid addicts. The tool collects de-identified data from 30 public data sets spanning 5,000 data elements to build profiles of people that may be at higher risk of developing an opioid addiction. It helps healthcare providers understand three things: who is most at risk; the barriers to treatment; and the best interventions.
Identifying Who’s at Risk
One of the problems that doctors currently face is that if two people of the same age present with the same type of illness such as back pain it's very difficult to predict who might end up becoming addicted to opioids and who might be resilient.
To get to the answer, Opioid360 analyzes the relationship between several datasets that have traditionally remained disparate. In so doing the sophisticated data tool builds 'personas' that provide deep insights into how to prevent and treat addiction.
So to go back to our previous illustration of two people with back pain, using the platform will make it easier to identify which of them may be at risk of becoming addicted. For example, if one earned a high salary, owned their own home and their demographic information suggested a healthy lifestyle, they could be at a lower risk. However, the other person might be identified as being at risk if they have far to travel for their healthcare, don’t have access to transport and live in area where people are typically on low incomes.
Opioid360 not only identifies who is at risk, but it also suggests the best treatment options for that individual based on barriers to treatment, such as having little or no access to public transport.
During a demonstration of the technology at DataStax's Accelerate conference in Washington in May 2019 Meera Kanhouwa, managing director at Deloitte Consulting & MissionGraph, explained the system like this:
“Look at this akin to Amazon. When you buy one children’s book, it will then tell you that the people who bought that book also bought these other books. You’re getting recommendations and it is 100% de-identified. That’s big data in the cloud, changing behavior. There is no reason you can’t use that for healthcare. So it's the same idea, right?
“We know not only the social determinants, the medical data, claims data, or Medicare claims data, plus local geographic search and social media data.
“Why couldn't you, and why shouldn't we, as a matter of protocol, ingest that data to improve our knowledge and have information nudges about the patients that we are taking care of on a daily basis?”
At the time of writing this article in June 2019, Opioid360 is undergoing trials at several facilities across the United States,
Next Story »