Fig. 1
From: Machine learning approaches overcome imbalanced clinical data for intraoral free flap monitoring
The precision-recall curve maintains high precision (close to 1.0) for a wide range of recall values, only dropping sharply at very high recall levels. This demonstrates the model’s ability to effectively identify class 1 flaps (those requiring salvage procedure) with minimal errors. The combination of class weighting and Focal loss appears to effectively address the class imbalance problem.
