AI and Blood Banking: Predicting Transfusion Demand. A Systematic Review of Patient-Individual to Regional Forecasting Approaches

Retrospective Registration Notice: This is a retrospective registration of a completed systematic review. Purpose: This systematic review synthesizes the current evidence on artificial intelligence (AI) and machine learning (ML) applications for blood transfusion demand prediction. Findings are organized into a four-tier framework based on prediction scope: (1) patient-individual, (2) procedure-related, (3) facility/inventory management, and (4) regional/national forecasting. Methods: Conducted following PRISMA 2020 guidelines. PubMed, Web of Science, and Scopus were searched from January 2015 to December 2025. Studies applying AI/ML to transfusion demand prediction reporting quantitative performance metrics were included. Risk of bias was assessed using PROBAST. Narrative synthesis was performed due to study heterogeneity. Conflict of Interest: ME has published primary research in this field.