Related Experiment Video
Updated: May 17, 2026
07:57
An Experimental Human DIEP Flap Model to Investigate Preservation Strategies for Vascularized Composite Allografts and Free Flaps
Published on: December 5, 2025
Development and Validation of FlapCheck.ai, a Fully Automated Artificial Intelligence Model for Postoperative Flap
Aneesh Karir1, Spencer J Ferbers1, Jessica Lancaster2
1Division of Plastic and Reconstructive Surgery, University of Manitoba, Winnipeg, Manitoba, Canada.
Journal of Reconstructive Microsurgery
|May 15, 2026
Summary
FlapCheck.ai, an artificial intelligence (AI) model, accurately assesses postoperative flap viability from clinical images. This tool enables reliable remote monitoring and early detection of flap compromise, crucial for patient outcomes.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Surgical Outcomes
Background:
- Postoperative flap monitoring is essential for detecting and salvaging compromised flaps.
- Shorter hospital stays necessitate remote, user-friendly tools for flap viability assessment.
- FlapCheck.ai is an automated AI model developed for classifying flap viability.
Purpose of the Study:
- To develop and validate an AI model for automated flap viability assessment.
- To evaluate the diagnostic performance of FlapCheck.ai using nonstandardized clinical images.
- To explore the potential of AI in enabling remote outpatient flap monitoring.
Main Methods:
- A retrospective review and literature search yielded 209 postoperative flap images.
- Images were augmented and split into training (1,432 images) and testing (41 images) sets.
- The AI model was trained using Microsoft Azure Custom Vision and evaluated on performance metrics.
Main Results:
- FlapCheck.ai achieved 97.6% accuracy in classifying flap viability.
- The model demonstrated high sensitivity (100%) and specificity (96.8%).
- Area under the ROC curve (AUC) was 0.997, indicating excellent diagnostic performance.
Conclusions:
- An automated AI model, FlapCheck.ai, was successfully developed and validated.
- The model shows potential for reliable outpatient flap monitoring and early detection of compromise.
- Future research will involve expanding datasets and prospective study evaluations.
