Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Predicting Free Flap Viability: Integrating Lactate and Glucose Measurements with Artificial Intelligence
0
Zitationen
4
Autoren
2025
Jahr
Abstract
Introduction: In reconstructive surgery, free flaps are a superior method for resurfacing defects. While free flap viability is typically monitored by subjective clinical examination, lactate and glucose levels in free flaps, which can affect tissue metabolism during ischaemia and reperfusion, can help predict viability. This study aims to review previous research and provide a theoretical basis for using artificial intelligence in lactate and glucose measurement as a means of assessing flap viability.Method: The primary databases used to retrieve the key medical literature presented in this study were book references and Google Scholar, PubMed and Science Direct, using search terms related to the topic. Only articles written in English and published less than ten years ago were included.Results: Lactate levels detect perfusion impairment earlier than clinical signs or other biochemical markers while glucose monitoring can indicate underlying metabolic dysregulation or physiological stress, helps early detection of complications. Combining lactate and glucose measurements enhances diagnostic accuracy and allows for timely interventions for flap viability. Studies confirm this dual monitoring is a practical, unbiased, and has the potential to be developed into an artificial intelligence tool to improve patient outcomes.Conclusion: Lactate and glucose measurements in free flap monitoring have distinct benefits. Lactate detects ischaemia and reflects tissue metabolism, while glucose monitors energy metabolism and systemic health. Combining these leading to improved flap survival rates. With accessible tools, this approach improves patient care and outcomes in reconstructive surgery.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 13.521 Zit.
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
2020 · 7.647 Zit.
Calculation of average PSNR differences between RD-curves
2001 · 4.088 Zit.
Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration
2001 · 3.884 Zit.
Vertebral fracture assessment using a semiquantitative technique
1993 · 3.603 Zit.