Healthcare Analytics, Population Health Management, Healthcare Big Data

Analytics in Action News

Predictive Analytics to Explore Link between Opioids, Suicide Risk

Kaiser Permanente researchers will use predictive analytics and machine learning to examine potential connections between opioid abuse and suicide risk.

Predictive analytics will explore the link between opioids and suicide risk

Source: Thinkstock

By Jessica Kent

- A three-year, $1.4 million Kaiser Permanente study will leverage predictive analytics and machine learning to understand the relationship between opioid use and suicide risk, allowing researchers to develop improved tools for identifying high-risk patients.

Both suicide deaths and opioid-related overdose deaths are on the rise in the US. Citing the National Center for Health Statistics, Kaiser Permanente noted that suicide rates increased by 27 percent between 1999 and 2015. Over the same period, the rate of suicides where opioid abuse was a contributing cause doubled.

“We’ve done preliminary work suggesting that 22 to 37 percent of opioid-related overdoses are, in fact, suicides or suicide attempts,” said Bobbi Jo Yarborough, PsyD, an investigator at the Kaiser Permanente Center for Health Research in Portland, Oregon.

“While health care settings are ideal places to intervene to prevent suicides, clinicians aren’t able to easily determine which of their patients are at elevated risk. Our ultimate goal is to develop the most accurate suicide risk prediction tools and put them into the hands of clinicians. If our study is successful, clinicians will have a powerful new resource in the fight against suicide.”

Investigators from the Mental Health Research Network helped develop the existing suicide prediction models, which include a large number of variables. The models take into account numerous patient factors, such as medical conditions, mental health and substance use disorder diagnoses, current and past prescriptions, and healthcare use patterns.  

Using these variables, researchers can predict the likelihood of a suicide attempt within 90 days of a mental health or primary care outpatient visit.

During the new study, the research team will leverage Kaiser Permanente’s electronic health record (EHR) system to develop additional tools for providers to help prevent future suicides.

Investigators will create machine learning algorithms using variables such as illicit or prescribed opioid use, opioid use disorder, discontinuation or substantial dose reduction of prescription opioids, and prior non-fatal opioid-related overdoses.

Additionally, the team will evaluate whether the strength of these factors vary between men and women.

The study will include the seven Mental Health Research Network sites that contributed to the development of the existing suicide prediction model.

Researchers from these sites will work with a dataset that includes approximately 24 million medical visits, 35,000 suicide attempts, and 2600 suicide deaths.

With the development of these new predictive models, Kaiser Permanente expects to build on its suicide prevention efforts and further understand the relationship between opioid abuse and suicide.

“We know that opioid use, opioid overdose and suicide are related, but we need much more specific information to guide our efforts at prevention,” said Gregory Simon, MD, MS in public health, principal investigator of the Mental Health Research Network and a co-investigator on the new study.

“The findings from this study will be a great asset to the public health community.”


Join 25,000 of your peers

Register for free to get access to all our articles, webcasts, white papers and exclusive interviews.

Our privacy policy

no, thanks

Continue to site...