Artificial intelligence (AI) could assist in bridging the education gap by coaching medical students as they practise surgical techniques.
A new tool, trained on videos of expert surgeons at work, provides students with real-time, personalised advice as they practice suturing.
Initial trials suggest AI can be an influential substitute teacher for more experienced students.
Senior author Mathias Unberath is an expert in AI-assisted medicine and focuses on how people interact with AI.
He said: ‘We’re at a pivotal time. The provider shortage is ever-increasing, and we need to find new ways to provide more and better opportunities for practice. Right now, an attending surgeon who already is short on time needs to come in and watch students practise, and rate them, and give them detailed feedback – that just doesn’t scale. The next best thing might be our explainable AI that shows students how their work deviates from expert surgeons.’
Developed at Johns Hopkins University, the model incorporates what’s known as ‘explainable AI’, an approach to AI that will rate how well a student closes a wound and then also tell them precisely how to improve.
The team trained their model by tracking the hand movements of expert surgeons as they closed incisions. When students try the same task, the AI texts them immediately to tell them how they compare to an expert and how to refine their technique.
The team conducted a first-of-its-kind study to determine whether students learned more from the AI than from watching videos. They randomly assigned 12 medical students with suturing experience to train with one of the two methods.
All participants practised closing an incision with stitches. Some received immediate AI feedback, while others tried to compare their actions to a surgeon in a video. Then everyone tried suturing again.
Compared with students who watched videos, students coached by AI and those with more experience learned much faster.
Unberath said: ‘In some individuals, the AI feedback has a big effect. Beginner students still struggled with the task, but students with a solid foundation in surgery, who are at the point where they can incorporate the advice, it had a great impact.’
Next the team plans to refine the model to make it easier to use. They hope to create a version that students could use at home eventually.
Unberath said: ‘This will help us scale up training in the medical fields. It’s really about how we can use this technology to solve problems.’
You can watch the AI model in action here.
