Voice of Commonwealth

Artificial intelligence to predict opoid risks

Share

Science & Technology, Canada (Commonwealth Union) – Opioids are a class of drugs that are commonly used to rescue pain. They work by binding to specific receptors in the brain and spinal cord, reducing the perception of pain and producing a sense of euphoria. Opioids can be prescribed by doctors for short-term pain relief, such as after surgery or injury, or for chronic pain management. However, they also have a high potential for abuse and addiction, and their misuse has become a major public health concern. In recent years, the opioid epidemic has led to a significant increase in opioid-related overdoses and deaths. As a result, there has been a growing emphasis on understanding the risks and benefits of opioid use, as well as developing alternative pain management strategies.

University of Alberta (U of A) scientists together with the College of Physicians and Surgeons of Alberta joined hands to analyze health data and enhance monitoring of prescriptions.

Scientists at the University of Alberta are applying a form of artificial intelligence (AI) to assist physicians obtain a better ability to forecast the patients with a higher chance of adverse effects from opioid prescriptions.

The recently published study saw the partnership forming a machine learning model to evaluate the chance of an emergency department visit, hospitalization or fatality within 30 days of obtaining an opioid prescription. The machine learning permits computers to seek out patterns in large volumes of data, obtaining greater accuracy over time as they proceed to validate and retrain with updated details.

The research model cross-referenced pharmacy information with administrative health data, where the records were produced each time a patient had engagements on the health-care system, that included emergency department and doctor visits along with blood tests and scans. The researchers monitored anonymized records for 853,324 adults in Alberta in 2018 and 2019, when 6,181,025 opioid prescriptions had been filled and 77,326 adverse events were indicated.

Doctors maintain guidelines to find out the patients that have an increased risk but they are unable to identify everyone as they often have limited details, as indicated by Dean Eurich, an epidemiologist as well as a professor for the School of Public Health.

“Machine learning can expand the number of variables that we’re going to look at from a couple dozen to 5,000, so we can rely on your labs, your hospitalizations, your physician visits, medications you have taken in the past — all that information can now be put into the model to predict where you are in the spectrum in terms of a low risk or a high risk of having a poor outcome,” said Eurich.

“The human mind just can’t process that many pieces of information at once.”

The model was produced together with the health information company Okaki and the College of Physicians and Surgeons of Alberta, who are as their part as administrators of the Tracked Prescription Program have the role of daily monitoring of opioid prescriptions, one of many measures implemented to lower the ongoing opioid crisis responsible for 1346 Albertans’ lives last year.

The model forecasted adverse patient outcomes having 90% accuracy, as indicated by Eurich, who expects to make the next move for the study within 6 months by conducting and testing the model in real time as a component of the surveillance system of the college.

Doctors having higher risk patients are to be alerted so they can select to prescribe another drug, have a lesser dose or monitor the patient more closely.

“This is a tool to help clinicians to manage their patients who are very complex and to help patients get better outcomes from their therapies,” said Eurich.

Read more

More News