Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 9, 2025Scientific ReportsOpen Access

Machine learning approaches overcome imbalanced clinical data for intraoral free flap monitoring

View Full Paper
Ask AI
Bookmark
Share

Authors

HKHyounmin KimDKDongwook KimJBJuho Bai

Discussion

Loading...

Member takes

Overview

Observational analysis introduced a deep learning model for intraoral flap monitoring, suggesting improved accuracy in assessments.

Key Points

  • The proposed machine learning model achieved an F1 score of 0.9863, indicating high accuracy in monitoring intraoral flaps.
  • Class weighting and focal loss were implemented to effectively handle the imbalanced clinical data from 131 patients.
  • This analysis analyzed 1877 images of intraoral defects to develop a user-friendly tool for surgeons and caregivers.
  • The model is designed to facilitate timely decision-making regarding salvage procedures in cases of flap complications.

Cite This Study

Kim et al. (2025) studied this question.

synapsesocial.com/papers/68e7d631bd66d359be6265d1https://doi.org/10.1038/s41598-025-15300-5
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Deep Learning Analysis of Intraoperative Physiological Signals for Predicting Surgical Outcomes in Head and Neck Free Flap Surgery: Preliminary Study2026
  2. 2Diagnostic Accuracy of Artificial Intelligence Models for Predicting Postoperative Complications Following Free Flap Reconstruction: A Systematic Review and Meta‐Analysis2025
  3. 3The Role of Artificial Intelligence in Predicting Flap Outcomes in Plastic Surgery: Protocol of a Systematic Review2022 · 8 citations
  4. 4Seeing Beyond the Surgeon’s Eye2026
  5. 5Identifying Venous Insufficiency in Head and Neck Reconstruction Flaps Using Machine Learning and Deep Learning Methods2026