Mapping the landscape of machine learning models used for predicting transfusions in surgical procedures: a scoping review

Massive transfusion of blood products poses challenges in determining the need for transfusion and the appropriate volume of blood products. This review explores the use of machine learning (ML) models to predict transfusion risk during surgical procedure, focusing on the methodology, variables, and software employed to predict transfusion. This scoping review investigates the development and current state of machine learning models for predicting transfusion risk during surgical procedure, aiming to inform physicians about the field’s progress and potential directions. The review was conducted using the databases Cochrane, Embase, and PubMed. The search included keywords related to blood transfusion, statistical models, and surgical procedures. Peer-reviewed articles were included, while literature reviews, case reports, and non-human studies were excluded. A total of 40 studies met the inclusion criteria. The most frequently studied biological variables included haemoglobin, platelet count, international normalized ratio (INR), activated partial thromboplastin time (aPTT), fibrinogen, creatinine, white blood cells, and albumin. Clinical variables of importance included age, sex, surgery type, blood pressure, weight, surgery duration, american society of anesthesiology (ASA) status, blood loss, and body mass index (BMI). The software employed varied, with Python, R, SPSS, and SAS being the most commonly used. Logistic regression was the predominant methodology used in 20 studies. Our scoping review highlights the need for improved reporting and transparency in methodology, variables, and software used. Future research should focus on providing detailed descriptions and open access to codes of respective models, promoting reproducibility, and enhancing the clinical relevance of transfusion risk prediction models.