Mayo Clinic Develops AI Tool to Detect Surgical Site Infections from Patient Photos

Mayo Clinic's Innovative AI Tool for Surgical Site Infection Detection

Researchers at Mayo Clinic have developed a groundbreaking artificial intelligence (AI) system capable of detecting surgical site infections (SSIs) with high accuracy from patient-submitted postoperative wound photos. This innovation has the potential to revolutionize postoperative care delivery, especially as outpatient operations and virtual follow-ups become increasingly common 1

1

2

The AI System: A Two-Stage Approach

The AI system employs a two-stage model utilizing Vision Transformer technology:

1. Detection of surgical incisions in images
2. Evaluation of infection signs in identified incisions

The model achieved impressive results, with 94% accuracy in detecting incisions and an 81% area under the curve (AUC) in identifying infections 1

1

2

Development and Training

Source: Medical Xpress

The AI-based pipeline was created to automatically identify surgical incisions, assess image quality, and flag signs of infection in photos submitted by patients through online portals. The system was trained on an extensive dataset of over 20,000 images from more than 6,000 patients across nine Mayo Clinic hospitals 1

1

2

Potential Impact on Postoperative Care

Dr. Cornelius Thiels, a hepatobiliary and pancreatic surgical oncologist at Mayo Clinic and co-senior author of the study, emphasized the tool's potential to streamline postoperative care:

"Our AI model can help triage these images automatically, improving early detection and streamlining communication between patients and their care teams." 1

1

The researchers anticipate that this technology could lead to:

1. Faster responses to patient concerns
2. Reduced delays in diagnosing infections
3. Improved care for patients recovering from surgery at home
4. Earlier treatment interventions
5. Decreased morbidity and reduced costs 1

   1

   2

   2

Addressing Algorithmic Bias

An important aspect of the study was the model's consistent performance across diverse groups, addressing concerns about algorithmic bias in AI systems 1

1

2

Related Stories

AI Model Revolutionizes Postoperative Risk Prediction Using Clinical Notes

Remote AI algorithm detects Critical View of Safety in pediatric surgery across hospitals

AI Model GLUCOSE Enhances Blood Sugar Management in Post-Cardiac Surgery Care

AI Breakthrough: New Tool Revolutionizes Detection of Rare Gastrointestinal Diseases

Future Prospects and Ongoing Research

Source: Newswise

While the results are promising, the research team acknowledges the need for further validation. Dr. Hojjat Salehinejad, a senior associate consultant of health care delivery research and co-senior author, stated:

"Prospective studies are underway to evaluate how well this tool integrates into day-to-day surgical care." 1

1

The researchers hope that this AI tool will pave the way for developing more advanced algorithms capable of detecting subtle signs of infection, potentially before they become visually apparent to the care team 1

1

2

Funding and Support

This groundbreaking research was supported by the Dalio Philanthropies Artificial Intelligence/Machine Learning Enablement Award and the Simons Family Career Development Award in Surgical Innovation 2

2

As AI continues to make strides in healthcare, innovations like Mayo Clinic's surgical site infection detection tool demonstrate the potential for technology to enhance patient care, improve outcomes, and revolutionize medical practices.