Artificial intelligence may soon play a greater role in medical education, particularly as the healthcare sector faces a growing shortage of surgeons. Researchers at Johns Hopkins University have developed an AI tool that provides real-time, personalized feedback to medical students practicing surgical techniques such as suturing.
The system was trained using videos that captured expert surgeons at work, tracking their hand movements during procedures like closing incisions. When students use the tool, it analyzes their technique and immediately sends them text-based feedback comparing their performance to that of experienced surgeons and suggesting specific improvements.
"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," said Mathias Unberath, senior author of the study and an expert in AI-assisted medicine. "The next best thing might be our explainable AI that shows students how their work deviates from expert surgeons."
Unberath explained that while current training often involves watching videos or using existing AI models for skill assessment, these methods do not provide detailed guidance on how to improve. "These models can tell you if you have high or low skill, but they struggle with telling you why," he said. "If we want to enable meaningful self-training, we need to help learners understand what they need to focus on and why."
The new model uses explainable AI techniques so it not only rates student performance but also gives actionable advice for improvement.
A recent study by the team involved 12 medical students with prior suturing experience who were randomly assigned either traditional video-based learning or training with the new AI system. All participants practiced closing an incision with stitches; some received immediate feedback from the AI while others compared their own efforts against instructional videos before trying again.
Findings showed that students who already had some surgical experience learned much faster when coached by the AI than those relying solely on video instruction. "In some individuals the AI feedback has a big effect," Unberath said. "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."
The research team plans further development of the technology to make it more accessible—potentially allowing medical trainees to practice at home using only a suturing kit and smartphone camera. "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," Unberath said. "This will help us scale up training in the medical fields. It's really about how can we use this technology to solve problems."
Other contributors include Lalithkumar Seenivasan, Xinrui Zou; Jeewoo Yoon; Sirui Chu; Ariel Leon; Patrick Kramer; Yu-Chun Ku; Jose L. Porras; Masaru Ishii—all from Johns Hopkins—and Alejandro Martin-Gomez from University of Arkansas.
