Related Experiment Video
Updated: Mar 1, 2026
08:27
A New Hybrid Quantitative Evaluation Model for Axillary Junctional Hemorrhage in Swine
Published on: December 6, 2024
705
Machine Learning in Assessing Intraoperative Blood Loss: A Systematic Review and Meta-Analysis
Wenlin Zhou1,2, Linglin Pan3, Xinmei Pan4
1Department of Nursing, The International Peace Maternity and Child Health Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
International Nursing Review
|February 28, 2026
Summary
Machine learning models accurately assess intraoperative blood loss, outperforming traditional methods. This technology can improve patient safety by enhancing blood loss estimation in surgical settings.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Medicine
- Surgical Safety
Background:
- Intraoperative bleeding is a significant cause of surgical mortality.
- Accurate blood loss assessment is crucial for preventing adverse outcomes.
- Existing methods for measuring blood loss have limitations.
Purpose of the Study:
- To evaluate the efficacy of machine learning (ML) models in assessing intraoperative blood loss.
- To compare ML-based blood loss assessment with the current gold standard.
- To determine the value of ML in improving surgical patient outcomes.
Main Methods:
- Systematic review and meta-analysis of relevant studies.
- Comprehensive literature search across major databases (Web of Science, PubMed, Embase, Cochrane Library, CINAHL) up to August 18, 2025.
- Pooled analysis of correlation coefficients between ML models and gold standard methods.
Main Results:
- Twelve studies met the inclusion criteria for the meta-analysis.
- A high pooled correlation coefficient was observed between ML models and the gold standard for blood loss assessment.
- Machine learning models demonstrated significant accuracy and reliability.
Conclusions:
- Machine learning models show high accuracy and reliability for intraoperative blood loss assessment.
- Clinical implementation of ML models can enhance blood loss estimation accuracy, potentially reducing perioperative risks.
- ML offers a promising tool for nursing staff to optimize decision-making and improve patient safety.
