Spine surgeon Corey Walker, MD, is collaborating with the Cedars-Sinai Department of Computational Biomedicine to use AI and machine learning for predicting postoperative pain management in patients.
Previously, Dr. Walker and other spine physicians have focused on patient movement to judge pain outcomes.
Now, machine learning can use factors to predict which patients will be able to successfully manage pain after a procedure and which patients will need ongoing help from physicians.
"The unique thing we're doing with this project is really focusing in on the pain medication part of it, because opioid addiction continues to be a challenge, and we are looking for ways to improve pain management after surgery," Dr. Walker said in a July 11 press release from Los Angeles-based Cedars-Sinai.
Machine algorithms are able to use several factors including blood pressure, age, and medical and medication history to determine pain management outcomes.
As the machines test their own algorithms against patient outcomes, they will continue to update and improve methodology, creating more accurate predictions down the line.
"This project uses artificial intelligence algorithms to analyze millions of data points and predict which patients may need additional help with pain management after surgery," Jason Moore, PhD, chair of the Department of Computational Biomedicine and acting professor of medicine, said in the press release.
When algorithms predict that a certain patient might struggle to wean off of pain medications, Dr. Walker said doctors can take steps to begin the weaning process before surgery, not just after. They can also switch up the type of pain medication used before surgery to mitigate the possibility of dependence.
"It becomes an ethical question," Dr. Walker said. "I definitely do not think the answer is that they go without the surgery or treatment, but rather that we engage the pain management team and other specialists early on in the process."
While AI has its perks, there is still a learning curve both for physicians and the intelligence itself.
"We need to teach AI to understand the value of humans," Dr. Moore said. "Formulating questions is still a uniquely human activity, which relies on a depth, breadth and synthesis of knowledge of different kinds. It also relies on creative thought and imagination, and asking the right questions is key."