Geneia case study: Predicting opioid abuse and overdose
Data Science

Geneia case study: Predicting opioid abuse and overdose

October 27, 2020
Geneia’s model accurately identified 80 percent of the people
Chief Data Scientist

The toll of the opioid epidemic has been staggering.

Early research suggest the COVID-19 pandemic has exacerbated the opioid epidemic.

Opioid abuse infographic

Other key data points:

  • Research by the CDC suggests people can become addicted in as few as five days.
  • Overall, overdose and abuse are still relatively rare in these opioid-prescribed populations (~0.7 percent), so using simple filtering rules would be insufficient to capture abuse and overdose cases.

That’s why I’m thrilled to share the news about Geneia’s model to predict opioid abuse and overdose.

For those who have received at least one opioid prescription, the Geneia Data Intelligence Lab (GDI Lab) model*+ predicts that person’s likelihood of an opioid abuse diagnosis or an overdose in the coming six months. Evaluated on several independent datasets, Geneia’s predictive model accurately identified 80 to 88 percent of the people who are likely to have an opioid abuse diagnosis or an overdose event in the next six months.

Geneia’s opioid model is unique. Geneia’s model:

  • Uses 22 variables whereas others use as many as 200 data points to achieve comparable predictive accuracy. Fewer variables make it easier to explain the model’s results to physicians and their patients.
  • Combines the likelihood of an opioid abuse diagnosis and an overdose event. Many models identify one of those outcomes.
  • Can be used with children and adolescents. Opioid models typically are created for people age 18 or older.

To learn more about Geneia’s opioid abuse and overdose model, download the case study.

Explore additional GDI Lab resources such as Best Practices: Using AI in Population Health by clicking here.

Read more

*Certain data used in this study were supplied by International Business Machines Corporation. Any analysis, interpretation, or conclusion based on these data is solely that of the authors and not International Business Machines Corporation.

+Predictive models, by their very nature, contain certain assumptions. This is not an attempt to practice medicine or provide specific medical advice, and it should not be used to make a diagnosis or to replace or overrule a qualified healthcare provider's judgment.