Machine Learning Models for Predicting High Risk for Pain
Some patients have severe pain after surgery. Some do not. Why? And how can we predict who would benefit from a pain management plan that’s personalized presurgery for maximal postsurgery pain relief? Bring in the artificial intelligence. New research presented at the Anesthesiology annual meeting examines nonopioid alternatives—other medications or epidurals, nerve blocks, etc—to postsurgical pain. Machine learning can go through electronic medical records to find predictive factors for postsurgical pain, such as pre-existing pain, previous opioid use, female gender, BMI, younger age.
Instead of using questionnaires, which can be time-consuming, “We plan to integrate the [machine learning] models with our electronic medical records to provide a prediction of post-surgical pain for each patient,” said Mieke A. Soens, MD, lead author of the study and an anesthesiologist at Brigham and Women’s Hospital and anesthesiology instructor at Harvard Medical School in Boston. “If the patient is determined to be at high risk for severe post-surgical pain, the physician anesthesiologist can then adjust the patient’s anesthesia plan to maximize non-opioid pain management strategies that would reduce the need for opioids after surgery.”
Read the full press release.
Did you enjoy this article?
Subscribe to the PAINWeek Newsletter
and get our latest articles and more direct to your inbox