Overview
A team of researchers at Mayo Clinic has created an artificial intelligence (AI) system capable of accurately detecting surgical site infections (SSIs) from postoperative wound photos submitted by patients. This innovation could significantly enhance postoperative care.
Research Details
Published in the Annals of Surgery, the study outlines an AI-based pipeline that:
- Automatically identifies surgical incisions
- Assesses image quality
- Flags signs of infection in patient-submitted photos
The AI system was trained on over 20,000 images from more than 6,000 patients across nine Mayo Clinic hospitals.
Motivation Behind the Research
According to Cornelius Thiels, D.O., a co-senior author of the study, the motivation stemmed from the need for timely outpatient monitoring of surgical incisions. He noted:
“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.”
How the AI Model Works
The AI employs a two-stage model:
- Detects whether an image contains a surgical incision.
- Evaluates if that incision shows signs of infection.
The model, known as Vision Transformer, achieved:
- 94% accuracy in detecting incisions
- 81% area under the curve (AUC) in identifying infections
Implications for Postoperative Care
Dr. Hala Muaddi, the first author of the study, stated:
“This work lays the foundation for AI-assisted postoperative wound care, which can transform how postoperative patients are monitored.”
The researchers believe this technology could:
- Provide faster responses to patients
- Reduce delays in diagnosing infections
- Support better care for patients recovering at home
Future Prospects
With further validation, the AI tool could serve as a frontline screening mechanism, alerting clinicians to concerning incisions. It may also lead to the development of algorithms that detect subtle signs of infection before they are visually apparent, allowing for:
- Earlier treatment
- Decreased morbidity
- Reduced healthcare costs
Dr. Muaddi emphasized the potential benefits for both patients and clinicians, particularly in rural or resource-limited settings.
Conclusion
While the results are promising, the research team acknowledges that further validation is necessary. Dr. Hojjat Salehinejad, another co-senior author, expressed hope that their AI models could reshape surgical follow-up practices.
This research was supported by the Dalio Philanthropies Artificial Intelligence/Machine Learning Enablement Award and the Simons Family Career Development Award in Surgical Innovation.