How AI-Assisted Surgery Is Improving Surgical Outcomes

Robots enabled with artificial intelligence are increasingly assisting microsurgical procedures to help reduce surgeon variations that could affect patient recovery. Following the successful outcome of AI-assisted surgery last year, experts said they expect to see more robot-aided procedures in the next few years.

“Artificial intelligence can help surgeons perform better,” said Dr. John Birkmeyer, chief clinical officer at Sound Physicians, a national practice of 3,000 doctors and medical practitioners offering acute care management. “We know that a surgeon’s skill, particularly with new or difficult procedures, varies widely, with huge implications for patient outcomes and cost. AI can both reduce that variation, and help all surgeons improve – even the best ones. It’s important to leverage that digital feedback.”

While AI-assisted surgery is still in its infancy, Birkmeyer said it is progressing rapidly as health systems collect and integrate data into their processes.

Advanced analytics and machine learning techniques are being used concurrently to help uncover critical insights and best practices from the billions of data elements associated with robotic-assisted surgery, Birkmeyer said.

This will help reduce surgical variation and its attendant inefficiencies and poor outcomes, as surgeons better understand the techniques that align with better outcomes. In addition, those insights can link to a patient’s post-operative and long-term health outcomes.

AI helps surgeons determine what is happening during a complex surgery by providing real-time data points about the movements the surgeon makes during the procedure, Birkmeyer said.

In addition, AI is being used to provide analysis of a surgeon’s technical abilities with products like Caresyntax’s qvident, a Web-based surgical risk and quality management tool, designed to eliminate the “black box” of surgical visibility.

The tool provides medical professionals a workspace to manage and leverage surgical content to help identify and reduce risk, improve quality, and facilitate data-enabled training.

Example of AI-assisted surgery

In fall of 2017, Maastricht University Medical Center in the Netherlands used an AI-assisted surgery robot to suture small blood vessels – some no larger than .03 millimeters – and up to .08 millimeters across.

The patient was suffering from lymphedema, a chronic condition where fluid builds up and causes swelling, commonly occurring as a side effect of breast cancer treatment. Microsurgery is a relatively new and potentially much better treatment for the condition, the medical center stated. The procedure involves connecting lymphatic vessels to blood vessels to restore the flow of lymphatic fluid and alleviate the swelling.

A robot created by Microsure, a spin-off company of Eindhoven University of Technology and the Maastricht University Medical Center, was used in the procedure.

The robotic system is controlled by a surgeon, whose hand movements are converted into smaller, more precise movements that are performed by a set of “robot hands.”

The device also uses AI to stabilize any tremors in the surgeon’s movements, to ensure the robot correctly performs the procedure.

According to the medical center, the AI-assisted surgery went well, and the patient is recovering. Microsure said the center plans to use the robot for other microsurgery procedures.

In the next few years, Birkmeyer said he expects to see the medical profession using AI to make sense of complex digital signatures associated with robotic and videoscopic procedures to provide actionable feedback to surgeons on how to improve.

“That post hoc analysis function could be a reality in the very near term,” Birkmeyer said. “The longer-term challenge and opportunity is using AI to improve surgical operations in real time – either via surgeon feedback or, potentially, by automating certain technical tasks, like parking assist on a new car.”