Study: Researchers Use EHR Data to Predict Future Chronic Opioid Use

March 23, 2018
Researchers at the University of Colorado Anschutz Medical Campus are working to develop statistical models to better predict which patients will be prescribed opioid medications long-term following discharge from a hospital stay.

Researchers at the University of Colorado Anschutz Medical Campus are working to develop statistical models to better predict which patients will be prescribed opioid medications long-term following discharge from a hospital stay.

In a study published in the Journal of General Internal Medicine, the researchers note that opioids are commonly prescribed in the hospital, yet, little is known about which patients will progress to chronic opioid therapy (COT) following discharge.

In the U.S. last year, more than 63,000 people died of a drug overdose, with opioids involved in 75 percent of those deaths. According to the 2015 National Survey of Drug Use and Health, over 2 million people in the US had a prescription opioid use disorder.

“Doctors and patients are increasingly aware of the dangers associated with overprescribing of opioids,” Susan Calcaterra, a fellow in addiction medicine at the CU School of Medicine, said in a release about the study. “We can assist physicians in making informed decisions about opioid prescribing by identifying patient characteristics which put them at risk progressing to chronic opioid use.

Researchers aimed to develop a prediction model to identify hospitalized patients at highest risk of progressing to chronic opioid use following hospital discharge. To develop the prediction model, they accessed data available in the electronic health record (EHR) from Denver Health Medical Center, an urban, safety net hospital.

Researchers defined chronic opioid therapy (COT) as either receiving a 90-day or greater supply of oral opioids with less than a 30-day gap in supply over a 180-day period, or filling ten or more opioid prescriptions over one year.

By accessing EHR data, researchers identified patient-specific variables which were highly associated with the progression to COT. These variables included having a history of substance use disorder, past year receipt of a benzodiazepine, an opioid medication or a non-opioid analgesic, receipt of an opioid at hospital discharge and high opioid requirements during hospitalization. Having a surgical procedure during the hospitalization was not associated with progression to COT, according to the researchers.

The model correctly predicted chronic opioid therapy in 79 percent of the patients and no COT correctly in 78 percent of the patients.

According to the authors, no prediction model has been published to identify hospitalized patients at high-risk of future COT. There are useful prediction tools to assess the patient’s risk of opioid misuse including the Screener and Opioid Assessment for Patients with Pain (SOAPP-R) and the Opioid Risk Tool (ORT). “However, these tools have not been validated in the hospital setting and they can be too time-consuming to consistently administer in a busy clinical setting,” the researchers wrote.

 “Application of such a predictive model within the EHR could identify patients at high risk for future chronic opioid use to allow clinicians to provide early patient education about pain management strategies and, when able, to wean opioids prior to discharge while incorporating alternative therapies for pain into discharge planning,” the researchers wrote.

“This prediction model could be incorporated into the electronic health record and would activate when a physician orders opioid medication. It would inform the physician of their patient’s risk for developing COT and may impact their prescribing practices,” Calcaterra said.

She continued, “All of the data required to assess risk are already available in the electronic health record, the physician would not need to input additional information. This tool would be inexpensive to implement and helpful in busy hospital settings where physicians make important health care decisions on patients they may have only met the day before. Researchers plan to validate this model in other health care systems to tests its ability to predict COT in other patient populations.”

Sponsored Recommendations

Care Access Made Easy: A Guide to Digital Self Service

Embracing digital transformation in healthcare is crucial, and there is no one-size-fits-all strategy. Consider adopting a crawl, walk, run approach to digital projects, enabling...

Powering a Digital Front Door with a Comprehensive Provider Directory

Learn how Geisinger improved provider data accuracy, SEO, and patient acquisition with a comprehensive provider directory.

Data-driven, physician-focused approach to CDI improvement

Organizational profile Sisters of Charity of Leavenworth (SCL) Health* has been providing care since it originated in the 1600s in France as the Daughters of Charity. These religious...

Luminis Health improved quality and financial outcomes with advanced CDI technology and consulting from 3M

In the beginning, there were challengesBefore partnering with 3M Health Information Systems (HIS), Luminis Health’s clinical documentation integrity (CDI) program faced ...