Perioperative Blood Management in General Surgery: Recent Advances, Current Limitations, and the Emerging Role of Artificial Intelligence—A Narrative Review

Long Zhang,1 Guoxin Liu,1 Shuyuan Guo,1 Yan Wu,1 Jing Yu,1 Xin Song,2 Hao Jiang11Department of General Surgery, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, Heilongjiang, 157011, People’s Republic of China; 2Department of Pathology, Mudanjiang Cancer Hospital, Mudanjiang, Heilongjiang, 157011, People’s Republic of ChinaCorrespondence: Hao Jiang, Department of General Surgery, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, Heilongjiang, 157011, People’s Republic of China, Email jh67896@163.comAbstract: Patient blood management (PBM) is a patient-centered approach to blood use that aligns with modern medical practice. It is based on multidisciplinary collaboration and evidence-based medicine. Its aim is to improve clinical outcomes by correcting preoperative anemia, reducing perioperative blood loss, standardizing transfusion practices, and optimizing the management of coagulation function. Patients undergoing general surgery, particularly complex liver surgery or gastrointestinal cancer surgery, often face preoperative anemia, intraoperative bleeding, increased transfusion requirements, and postoperative coagulation abnormalities. These factors make perioperative blood management more complex. This narrative review searched PubMed, Web of Science, Google Scholar, and the China National Knowledge Infrastructure (CNKI) for relevant studies published over the past 10 years. It summarizes recent advances, current limitations, and challenges in the clinical translation of perioperative blood management in general surgery. This review focuses on the assessment and management of preoperative anemia, bleeding control and hemostatic strategies, transfusion management, coagulation monitoring, and thrombotic risk management. It also discusses recent advances and current limitations in the use of artificial intelligence (AI) and machine learning (ML) for risk prediction, clinical decision support, and individualized management. Current evidence suggests that PBM may help optimize perioperative care in general surgery. AI/ML may also support clinical decision-making by predicting bleeding risk, estimating transfusion requirements, and stratifying thrombotic risk. However, studies specifically focusing on general surgery patients remain limited. Most available evidence comes from cardiac surgery, orthopedics, or other surgical populations. In addition, current prediction models still have several limitations, including insufficient external validation, a lack of prospective evaluation, and limited interpretability. Therefore, these models should currently be used only as tools to support clinical judgment. Therefore, future studies should include more multicenter prospective research in general surgery populations. AI/ML-assisted decision support should also be further explored within standardized PBM pathways to improve the precision and standardization of perioperative blood management in general surgery.Keywords: perioperative blood management, general surgery, artificial intelligence, machine learning