Mayo Clinic researchers have developed an artificial intelligence (AI) system that can detect surgical site infections (SSIs) with high accuracy from patient-submitted postoperative wound photos. The tool, described in a study published in the Annals of Surgery, automates the process of monitoring incisions, potentially transforming postoperative care. The AI system uses a two-stage model: it first identifies whether an image contains a surgical incision and then assesses the presence of infection signs. Trained on over 20,000 images from more than 6,000 patients across nine Mayo Clinic hospitals, the model, based on Vision Transformer, achieved 94% accuracy in detecting incisions and an 81% area under the curve (AUC) in recognizing infections. According to co-senior author Dr. Cornelius Thiels, a hepatobiliary and pancreatic surgical oncologist at Mayo Clinic, the motivation behind this development stems from the increasing need for efficient outpatient monitoring. "This process, currently done by clinicians, is time-consuming and can delay care. Our AI model can help triage these images automatically, improving early detection and streamlining communication between patients and their care teams," he explains. Lead author Dr. Hala Muaddi, a hepatopancreatobiliary fellow at Mayo Clinic, adds that the technology is particularly relevant as outpatient surgeries and virtual follow-ups become more common. "This work lays the foundation for AI-assisted postoperative wound care, which can transform how postoperative patients are monitored," she says. "It allows for faster patient reassurance or earlier identification of problems, reducing the risk of complications and lowering healthcare costs." The researchers envision the AI tool functioning as a frontline screening method, alerting clinicians to concerning incisions and helping them prioritize cases that require immediate attention. This could be especially beneficial in rural or resource-limited settings where access to medical specialists is limited. A significant advantage of the system is its consistent performance across diverse patient groups, addressing concerns about algorithmic bias. "Our hope is that the AI models we developed—and the large dataset they were trained on—have the potential to fundamentally reshape how surgical follow-up is delivered," says Dr. Hojjat Salehinejad, a senior associate consultant of healthcare delivery research and co-senior author. However, the team acknowledges the need for further validation through prospective studies to ensure the tool’s effectiveness in real-world clinical settings. Industry experts view this development as a promising step forward in leveraging AI for enhanced patient care. The ability to automatically screen and flag potential infections can significantly reduce the burden on healthcare providers and improve the speed and accuracy of postoperative monitoring. Mayo Clinic, known for its innovation in healthcare, continues to push the boundaries of AI integration in medical practice, setting a benchmark for other institutions to follow. Further refinement and wider adoption of this technology could revolutionize surgical aftercare, making it more accessible and efficient for both patients and clinicians.