EDMONTON — Amid an opioid crisis in Canada, University of Alberta researchers are using a form of artificial intelligence to help doctors predict which patients are at risk of adverse outcomes from prescription drugs — with an accuracy rate of 90 per cent.
As part of recently published research, the team, in collaboration with health information company Okaki and the College of Physicians and Surgeons of Alberta, created a machine learning model that analyzes administrative health data to more accurately determine if a patient will have poor outcomes from opioid prescriptions. Machine learning uses computers to find patterns in large volumes of data, improving its accuracy as information is updated.
By cross-referencing pharmacy data with administrative records for each time a patient interacts with the healthcare system, the model estimates the risk of an emergency department visit, hospitalization or death within 30 days of filling an opioid prescription.
The model tracked anonymized records for 853,324 adult Albertans in 2018 and 2019, when 6,181,025 opioid prescriptions were filled and 77,326 adverse events were reported.
“The human mind just can't process that many pieces of information at once,” explained Dean Eurich, an epidemiologist and professor in the School of Public Health.
According to Eurich, doctors follow guidelines to determine which patients are at higher risk but they don’t catch everyone because there’s often limited information.
“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,” Eurich explains.
The ongoing opioid crisis took 1,346 Albertans' lives in 2022. Using the model, the goal is to help inform doctors in real time on potentially high risk patients so they can choose to prescribe a different drug, give a smaller dose or provide closer follow up.
Within the next six months Eurich expects to implement and pilot test the model in real time as part of the college’s surveillance system.
More information can be found here. To speak with Dean Eurich, please contact:
Sarah Vernon | University of Alberta communications associate | svernon@ualberta.ca