Machine Learning for Intraoperative Bleeding Prediction in Patients Undergoing Surgery: Scoping Review - Takeaways - MDSpire

Machine Learning for Intraoperative Bleeding Prediction in Patients Undergoing Surgery: Scoping Review

  • By

  • Shiqiong Yan

  • Ping Zhang

  • Wanwan Qiao

  • Sijia Xie

  • Huan Hu

  • Yi Gao

  • Linli Xie

  • Jie Jing

  • June 10, 2026

  • 0 min

Share

  • 1

    Perioperative bleeding significantly increases patient mortality and postoperative complications, highlighting the need for effective blood loss prediction.

  • 2

    Current clinical methods for estimating intraoperative blood loss are often inaccurate, leading to erroneous transfusion decisions and increased risk of complications.

  • 3

    Machine learning (ML) methods show promise in improving predictive accuracy for intraoperative bleeding compared to traditional models.

  • 4

    Existing research on ML for bleeding prediction is fragmented, focusing on single procedures and lacking robust external validation.

  • 5

    This scoping review aims to evaluate ML algorithms for predicting intraoperative bleeding and identify key challenges in their clinical implementation.

Original Source(s)

Machine Learning for Intraoperative Bleeding Prediction in Patients Undergoing Surgery: Scoping Review

  • by Shiqiong Yan, Ping Zhang, Wanwan Qiao, Sijia Xie, Huan Hu, Yi Gao, Linli Xie, Jie Jing

  • June 10, 2026

Related Content

Case Report: Giant coronary artery aneurysm with cardiac compression successfully managed by surgical resection and bypass in a normolipidemic patient

CD25+CD27+CD70− alloantigen-specific Tregs: promising stable immunotherapy for transplantation

Case Report: A rare case of esophageal squamous cell carcinoma with metastases to the pancreas and stomach