A robot shows that machines may one day replace human surgeons.

Nearly four decades ago, the Defense Advanced Research Projects Agency (DARPA) and NASA began pushing projects that would make remote surgery possible, whether on the battlefield or in space. From those initial efforts emerged surgical robotic systems like Da Vinci , which function as an extension of the surgeon, allowing minimally invasive procedures to be performed with remote controls and 3D vision. But that's still just a human using a sophisticated tool. Now, the incorporation of generative artificial intelligence and machine learning into the control of systems like Da Vinci is beginning to make the emergence of autonomous surgical robots imaginable.

This Wednesday, the journal Science Robotics published the results of a study conducted by researchers from Johns Hopkins and Stanford Universities. They present a system capable of autonomously performing several steps in surgery, learning from videos of humans operating and receiving commands in natural language, just as a medical trainee would.

As with human learning, the team of scientists has been incorporating the steps necessary to complete a surgery into its training. Last year, the Johns Hopkins team, led by Axel Krieger, trained the robot to perform three basic surgical tasks: handling a needle, elevating body tissue, and suturing. This training was carried out through imitation and a machine learning system similar to the one used by ChatGPT, but replacing words and text with a robotic language that translates the angles of the machine's movement into mathematics.

In the new experiment, two experienced human surgeons demonstrated gallbladder removal surgeries on pig tissue outside the animal. Thirty-four gallbladders were used to collect 17 hours of data and 16,000 trajectories that the machine used to learn. The robots then, without human intervention and with eight gallbladders they had never seen before, were able to perform with 100% accuracy some of the 17 tasks required to remove the organ, such as identifying certain ducts and arteries, grasping them precisely, strategically placing clips, and cutting with scissors. During the experiments, the model was able to correct its own errors and adapt to unforeseen situations.

In 2022, this same team performed the first autonomous robotic surgery on a living animal: a laparoscopy on a pig. But that robot required specially marked tissue, within a controlled environment, and following a set surgical plan. In a statement from his institution, Krieger said it was like teaching a robot to drive along a carefully mapped route. The new experiment he just presented would be—for the robot—like driving on an unfamiliar road based only on general knowledge of how a car handles.

José Granell , head of the Department of Otorhinolaryngology and Head and Neck Surgery at HLA Moncloa University Hospital and a professor at the European University of Madrid, believes that the work of the Johns Hopkins team "is beginning to approach something that comes close to real surgery." "The problem with robotic soft tissue surgery is that biology has a lot of intrinsic variability, and even if you know the technique, in the real world there are many possible scenarios," explains Granell. "Asking a robot to work a bone is easy, but with soft tissue, everything is more difficult because it moves. It's unpredictable how it will react when you push, how much it will move, whether when it grabs an artery it will break if I pull too hard," continues this surgeon, and emphasizes: "This technology changes the way we train the succession of gestures that constitutes surgery."

For Krieger, this advancement takes us “from robots that can perform specific surgical tasks to robots that truly understand surgical procedures.” The leader of the team that made this breakthrough with the help of generative AI asserts: “It’s a crucial distinction that brings us significantly closer to clinically viable autonomous surgical systems, capable of navigating the messy and unpredictable reality of real-life patient care.”

Francisco Clascá , professor of Human Anatomy and Embryology at the Autonomous University of Madrid, welcomes the progress, but points out that "it's a very simple surgery" and is performed on organs from "very young animals, which don't have the level of deterioration and complications of a 60- or 70-year-old person, which is when this type of surgery is typically needed." Furthermore, the robot is still much slower than a human performing the same tasks.

A goal that “is very far away”

Mario Fernández, head of the Head and Neck Surgery department at the Gregorio Marañón General University Hospital in Madrid, considers the advancement interesting, but believes that replacing human surgeons with machines "is a long way off." He warns against the fascination with technology without considering its real benefits; and also its price, which means it's not accessible to everyone.

“I know a hospital in India, for example, where they have a robot and can perform two surgical sessions per month, operating on two patients. A total of 48 per year. For them, robotic surgery may be a way to play and learn, but it's not a reality for the patients there,” says Fernández, who believes that “we should appreciate” technological advances, but that surgery should be valued for what it offers patients. As a contrary example, he cites “a technique called transoral ultrasound surgery , which was developed in Madrid and is available worldwide, is performed on six patients per day.”

Krieger believes their proof of concept demonstrates that it's possible to perform complex surgical procedures autonomously and that their imitation learning system can be applied to more types of surgeries, something they will continue to test with other interventions.

Looking ahead, Granell points out that, in addition to continuing to overcome technical challenges, the process of robot adoption will be slow because in surgery, "we are very conservative about patient safety." He also raises philosophical questions such as overcoming the first and second laws of robotics proposed by Isaac Asimov: "A robot may not injure a human being nor, through inaction, allow a human being to come to harm" and "a robot must obey the orders given it by a human being except where such orders would conflict with the First Law." This specialist points out the apparent contradiction posed by the fact that human surgeons "do cause harm, seeking the benefit of the patient; and this is a dichotomy that [for a robot] will have to be resolved."