Study Offers EHR-Based Approach To Predicting Post-Hospital Opioid Use

With opioid abuse a raging epidemic in the United States, hospitals are looking for effective ways to track and manage opioid treatment effectively. In an effort to move in this direction, a group of researchers has developed a model which predicts the likelihood of future chronic opioid use based on hospital EHR data.

The study, which appears in the Journal of General Internal Medicine, notes that while opioids are frequently prescribed in hospitals, there has been little research on predicting which patients will progress to chronic opioid therapy (COT) after they are discharged. (The researchers defined COT as when patients were given a 90-day supply of opioids with less than a 30-day gap in supply over a 180-day period or receipt of greater than 10 opioid prescriptions during the past year.)

To address this problem, researchers set out to create a statistical model which could predict which hospitalized patients would end up on COT who had not been on COT previously. Their approach involved doing a retrospective analysis of EHR data from 2008 to 2014 drawn from records of patients hospitalized in an urban safety-net hospital.

The researchers analyzed a wide array of variables in their analysis, including medical and mental health diagnoses, substance and tobacco use, chronic or acute pain, surgery during hospitalization, having received opioid or non-opioid analgesics or benzodiazepines during the past year, leaving the hospital with opioid prescriptions and milligrams of morphine equivalents prescribed during their hospital stay.

After conducting the analysis, researchers found that they could predict COT in 79% of patients, as well as predicting when patients weren’t on COT 78% of the time.

Being able to predict which patients will end up on COT after discharge could prove to be a very effective tool. As the authors note, using EHR data to create such a predictive model could offer many benefits, particularly the ability to identify patients at high risk for future chronic opioid use.

As the study notes, if clinicians have this information, they can offer early patient education on pain management strategies and where possible, wean them off of opioids before discharging them. They’ll also be more likely to consider incorporating alternative pain therapies into their discharge planning.

While this data is exciting and provides great opportunities, we need to be careful how we use this information. Done incorrectly it could cause the 21% who are misidentified as at risk for COT to end up needing COT. It’s always important to remember that identifying those at risk is only the first challenge. The second challenge is what do you do with that data to help those at risk while not damaging those who are misidentified as at risk.

One issue the study doesn’t address is whether data on social determinants of health could improve their predictions. Incorporating both SDOH and patient-generated data might lend further insight into their post-discharge living conditions and solidify discharge planning. However, it’s evident that this model offers a useful approach on its own.

About the author

Sunny Tara

Sunny is a serial entrepreneur on a mission to improve quality of care through data science. Sunny’s latest venture CareCognitcs, a digital health company that applies consumer loyalty and data science to transform patient behavior. Sunny has an impressive track record of Strategy, Business Development, Innovation and Execution in the Healthcare, Casino Entertainment, Retail and Gaming verticals. Sunny is the Co-Chair for the Las Vegas Chapter of Akshaya Patra foundation (www.foodforeducation.org) since 2010. Sunny brings great practical insights into the use of technology and data in healthcare.

2 Comments

  • The first step to finding those at risk is to screen ALL patients for previous drug and alcohol abuse/use. Unlike the smoking questions which screen for previous smoking, the drug alcohol questions do not have the did you ever drink/drug follow up and if so, how long and how much. This would be a step in the right direction.

    People who have perhaps struggled with the question could suddenly admit to physicians or on a form as a slight admission that might help them. It is a disease of denial which has a stigma. People have no problem admitting they smoke. Many professionals who have recovered from addictions and are fearful of repercussions will not answer feeling it is not relelavent to physicians if don’t currently use. If the questions are not asked, those people recovering for many years or even a few, will view no follow ups as being irrelevant to healthcare providers.

    I had been given unwanted and unnecessary opioids after a procedure having been mistaken for an inpatient instead of outpatient in a hospital. I was shocked to get my records to see I was pumped full of opioids after my procedure. That was done without any consciousness on my part. I was kept over night without orders and without any pain meds and none asked. Gee, tylenol or ibuprofen is what I had been told would do the trick post surgically. Newly recovering addicts, would be set off by waking up and hallucinating. It is what is previously done for fun. When I told the surgeon how long I had been recovering (more than 30 years), I asked why there were no follow ups to drug/alcohol questions when the question asks only if you drink or use drugs. He replied “in your case it was so long ago it didn’t matter”.

    All I can say to that is that most other addicts/alcoholics could be triggered back into being active caused by healthcare providers that do not use the important “did you ever drink or use drugs, when and how long?”. These are the same questions posed with smoking. Those are useful to determine cancer precursors. They are also useful for having a discussion with people with a daily battle of being in recovery to gain some support with there other than the stigma attached to drug/alcohol abuse. It is a disease and yet my surgeon was thinking I was cured. Well, every day for 34 years, yes.

  • Joyce,
    Thanks for sharing. I agree with your perspectives. Most doctors don’t understand the nature of addiction and how what you describe would help. I like your idea of asking about this.

Click here to post a comment
   

Categories