Researchers at Johns Hopkins University have developed a groundbreaking AI tool that provides real-time feedback to medical students practicing surgical techniques. This innovation aims to mitigate the growing shortage of surgeons and significantly improve medical training.
Faced with an increasing shortage of surgeons, a team at Johns Hopkins University has developed a pioneering artificial intelligence tool designed to coach medical students through complex surgical procedures.
The innovative technology, designed to provide real-time, personalized feedback, was recently showcased at the International Conference on Medical Image Computing and Computer Assisted Intervention. The AI system, trained using videos of expert surgeons, offers detailed guidance to students as they practice suturing.
“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 practice, and rate them, and give them detailed feedback — that just doesn’t scale,” senior author Mathias Unberath, an expert in AI-assisted medicine, said in a news release.. “The next best thing might be our explainable AI that shows students how their work deviates from expert surgeons.”
Currently, medical students rely heavily on videos of experts performing surgeries to learn new techniques. While existing AI models can rate students’ performances, they often fall short in providing specific, actionable feedback.
According to Unberath, these models fail to explain what students are doing right or wrong, which is crucial for effective self-training.
“These models can tell you if you have high or low skill, but they struggle with telling you why,” he added. “If we want to enable meaningful self-training, we need to help learners understand what they need to focus on and why.”
The team utilized “explainable AI,” a method that not only rates a student’s performance but also provides detailed instructions for improvement.
The AI was trained by analyzing the hand movements of expert surgeons as they closed incisions. When students perform the same task, the AI offers immediate feedback, comparing their technique to that of the experts and suggesting ways to refine it.
“Learners want someone to tell them objectively how they did,” added first author Catalina Gomez, a Johns Hopkins doctoral student in computer science. “We can calculate their performance before and after the intervention and see if they are moving closer to expert practice.”
The researchers conducted a controlled study to evaluate the efficacy of the AI coaching method against traditional video-based learning. They randomly assigned 12 medical students with suturing experience to train using one of the two methods. Initial results showed that more experienced students coached by AI learned significantly faster than those who used videos.
“In some individuals, the AI feedback has a big effect,” Unberath added. “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, saw a great impact.”
Moving forward, the team aims to refine the AI model to make it more accessible and user-friendly, potentially enabling students to practice at home with basic equipment and a smartphone.
“We’d like to offer computer vision and AI technology that allows someone to practice in the comfort of their home with a suturing kit and a smart phone,” added Unberath. “This will help us scale up training in the medical fields. It’s really about how can we use this technology to solve problems.”
Source: Johns Hopkins University