Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Sep 21, 2025

A Pre-clinical Rat Model for the Study of Ischemia-reperfusion Injury in Reconstructive Microsurgery

A Pre-clinical Rat Model for the Study of Ischemia-reperfusion Injury in Reconstructive Microsurgery

Published on: November 8, 2019

Flap failure prediction in microvascular tissue reconstruction using machine learning algorithms.

Yu-Cang Shi¹, Jie Li¹, Shao-Jie Li¹

¹Department of Plastic Surgery, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, Guangdong Province, China.

World Journal of Clinical Cases

|June 1, 2022

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Symmetry-breaking charge separation: from charge generation to functional charge utilization.

Chemical science·2026

Same author

Bending-Induced Vibrational Landscape Reorganization Governs Energy Dissipation in Perylene Bisimides.

Angewandte Chemie (International ed. in English)·2026

Same author

Electron-injection-induced global aromaticity enables stable open-shell nanopillars with intense mid-infrared magnetic circular dichroism.

Chemical science·2026

Same author

Alternating Donor-Acceptor Thienoacenes Featuring Up to 23 Linearly Fused Rings.

Organic letters·2025

Same author

Direct Synthesis of K-Region Functionalized Polycyclic Aromatic Hydrocarbons via Twofold Intramolecular C-H/C-H Arylation.

Organic letters·2024

Same author

Self-Assembled Bent Perylenediimides.

Angewandte Chemie (International ed. in English)·2024

Machine learning models can predict microvascular free flap failure, identifying high-risk patients. Key factors include age, BMI, and ischemia time, aiding clinical decision-making.

Area of Science:

Plastic Surgery
Biomedical Engineering
Data Science in Medicine

Background:

Microvascular tissue reconstruction is vital for tissue defects.
Flap failure leads to increased hospital stay, costs, and patient distress.
Identifying risk factors for flap failure is crucial for improving outcomes.

Purpose of the Study:

Develop machine learning (ML) models to predict flap failure.
Identify key risk factors associated with flap failure.
Screen high-risk patients for proactive intervention.

Main Methods:

Utilized data from 946 patients undergoing microvascular free flap reconstruction.
Developed and compared three ML models: random forest, support vector machine, and gradient boosting.

Keywords:

Flap failure Machine learning Microvascular procedure Random forest Risk factors

More Related Videos

A Model of Free Tissue Transfer: The Rat Epigastric Free Flap

A Model of Free Tissue Transfer: The Rat Epigastric Free Flap

Published on: January 15, 2017

Engineered Vascularized Muscle Flap

Engineered Vascularized Muscle Flap

Published on: January 11, 2016

Related Experiment Videos

Last Updated: Sep 21, 2025

A Pre-clinical Rat Model for the Study of Ischemia-reperfusion Injury in Reconstructive Microsurgery

A Pre-clinical Rat Model for the Study of Ischemia-reperfusion Injury in Reconstructive Microsurgery

Published on: November 8, 2019

A Model of Free Tissue Transfer: The Rat Epigastric Free Flap

A Model of Free Tissue Transfer: The Rat Epigastric Free Flap

Published on: January 15, 2017

Engineered Vascularized Muscle Flap

Engineered Vascularized Muscle Flap

Published on: January 11, 2016

Evaluated model performance using AUC, accuracy, precision, recall, and F1 score.

Main Results:

Flap failure occurred in 3.6% of patients.
The random forest classifier achieved the highest performance (AUC = 0.770).
Top predictive variables included age, BMI, ischemia time, smoking, and diabetes; only age, BMI, and ischemia time were statistically significant.

Conclusions:

ML algorithms, particularly random forest, effectively categorize patients at high risk of flap failure.
Flap failure is multifactorial, necessitating further investigation into identified risk factors.
ML model application can enhance clinical decision-making and improve patient outcomes.