AI predicts postoperative opioid use
An artificial intelligence tool based on data from patients’ electronic medical records correctly identified which patients would need high doses of opioids after surgery, according to findings presented at Anesthesiology 2020.
“Being able to target the right treatment to the right patient is important to not only to reduce opioid use, but also to ensure that patients receive the treatment that is right for them,” Mieke S. Soens, MD, an instructor of anesthesia at Brigham and Women's Hospital, told Healio Primary Care.
In a two-part study, Soens and colleagues gathered data from 5,994 patients scheduled to receive general anesthesia and undergo surgical procedures without a peripheral nerve block. Of these, 1,287 were administered more than 90 morphine milligram equivalents in the first 24 hours after surgery.
In the first part of the study, the researchers used 163 potential factors to predict high pain after surgery based on a literature search and input from experts. Based on those factors, they created three machine learning algorithm models — logistic regression, random forest and artificial neural networks. The algorithms compiled data from patient medical records and shortened the list of predictive factors down to 21 that most accurately predicted patients’ pain severity and their potential need for opioids after surgery.
In the second part of the study, Soens and colleagues compared the models’ predictions for opioid use and the patients’ actual opioid use. They found that all three models had comparable accuracy overall: 81% for logistic regression and random forest, and 81% for artificial neural networks.
“Our model will allow the surgical and anesthesia teams to create a tailored personalized approach for each patient that maximize nonopioid analgesic strategies for patients, including nerve blocks and epidurals,” Soens said. “Patients can experience less pain and get optimal doses of opioid pain medication after surgery, and we also hope to reduce the risk for chronic opioid use.”
The researchers hope to partner with EMR vendors to integrate their model into more health systems, Soens said.
“The amount of work that has to be done and associated costs would depend on the EMR system,” she said. “While this tool is mostly designed to help perioperative care teams create an individualized pain management approach for the surgical patient, the tool would also be available for primary care physicians, as long as they have access to the patient’s EMR.”
Perspective
Anita Gupta, DO, PharmD, MPP
In the United States, many prescriptions for opioids following surgery serve as an unintended gateway to long-term opioid use. We know that more than 50 million surgical procedures happen in the U.S. annually and an estimated 2.6 million Americans will become persistent users of opioids following initial exposure after surgery in the hospital. Reducing opioids exposure in the postoperative setting is a crucial way to help curb the opioid epidemic.
Surgery plays a dual role in the opioid epidemic. It can be the initial introduction to opioids for many patients and can lead to unused pills becoming available for misuse and abuse. To address the opioid epidemic, much attention has been focused on reducing the widespread use of opioids to treat patients with chronic pain. While there is no question that this population is most prone to dependence and addiction, not enough scrutiny has been given to another significant population at risk of long-term consequences related to opioid overexposure — that is, patients who have just undergone surgery. Prior studies have shown that when fewer opioids are used to treat patients, these patients are less likely to experience adverse events.
Therefore, it is imperative that we begin to use the power of data intelligence and machine learning to address the opioid crisis, as Soens and colleagues do in this research. They identified patients at high risk for experiencing more severe pain and higher opioid requirements after surgery, which guided physicians to choose individually targeted analgesic approaches without the use of time-consuming EMRs. The challenges ahead will be how we validate these approaches for all populations of patients in diverse populations to ensure equity and trust to reduce the risk for chronic opioid use long term across the world.
References
Anita Gupta, DO, PharmD, MPP
Adjunct assistant professor of anesthesiology, critical care medicine and pain medicine, Johns Hopkins University School of Medicine
Member, American Society of Anesthesiologists, American Society of Regional Anesthesiology and Pain Medicine and the Milken Institute Faster Cures Business Council.
Disclosures: Gupta reports serving as a board director of several public and private sector organizations, as an appointed member of the National Academies of Sciences Global Forum, National Quality Forum and previously serving as an advisor to the FDA’s Anesthetic, Analgesic, Drug Products Advisory Committee.