Skip to main content

The Human Side of AI: Predicting Spine Surgery Outcomes

The Cedars-Sinai Department of Computational Biomedicine is harnessing artificial intelligence to help spine surgeons assess risks and predict outcomes of surgery. Photo by Cedars-Sinai.
The Cedars-Sinai Department of Computational Biomedicine is harnessing artificial intelligence to help spine surgeons assess risks and predict outcomes of surgery. Photo by Cedars-Sinai.
The Cedars-Sinai Department of Computational Biomedicine is harnessing artificial intelligence to help spine surgeons assess risks and predict outcomes of surgery. Photo by Cedars-Sinai.

Cedars-Sinai Department of Computational Biomedicine Develops Artificial Intelligence Tools to Help Spine Surgeons Predict Patient Outcomes and Address Medication Issues Before They Arise

Ever since Corey Walker, MD, became a spine surgeon, the traditional measure of success focused on how well a patient was able to walk, bend or move after spine surgery. Now, with the help of artificial intelligence, Walker is measuring success differently.

Corey T. Walker, MD

Corey T. Walker, MD

“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,” Walker said.

Walker’s team, in collaboration with the Cedars-Sinai Department of Computational Biomedicine, is using artificial intelligence and machine learning to predict which patients are most likely to successfully manage their pain post-surgery, and which patients might need additional assistance.

“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,” said Jason Moore, PhD, chair of the Department of Computational Biomedicine and acting professor of Medicine.

The algorithm makes a prediction based on a subset of the data, then tests its own predictions against new subsets, and continually improves and updates the methodology as it learns more. While clinical trials usually test one or two variables at a time, algorithms like these crunch thousands of variables at a time.

“The more data you feed it, the better,” Walker said. “We look at everything from a patient’s blood pressure to their age, to what types of medications they were taking before surgery and how long they’ve been on those medications.”

But what happens when the algorithm does identify a patient as likely to struggle with weaning from pain medications?

“It becomes an ethical question,” 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.”

Jason Moore, PhD

Jason Moore, PhD

Walker said previous studies have suggested that certain techniques, like weaning a patient off pain medication before surgery or changing the pain medication before surgery, can have an impact on the patient’s need for pain medications after surgery.

But Moore said it’s not enough to teach physicians to utilize artificial intelligence. Artificial intelligence has a lot to learn, as well.

“We need to teach AI to understand the value of humans,” he said.

Moore said that human involvement with artificial intelligence begins with the types of questions physicians and investigators are asking.

“Formulating questions is still a uniquely human activity, which relies on a depth, breadth and synthesis of knowledge of different kinds,” Moore said. “It also relies on creative thought and imagination, and asking the right questions is key.”

Read more on the Cedars-Sinai Blog: Artificial Intelligence at Cedars-Sinai


LEARN MORE

FOR PROFESSIONALS

CONNECT