NHSBT pilots AI-genomic tool for blood matching

NHS Blood and Transplant (NHSBT) has launched a 12-month feasibility study to evaluate an algorithm called bloodMatcher that combines genomic blood-group data and AI to select donor units for people with sickle cell disorder, according to an NHSBT press release dated May 20, 2026. The study will use DNA-based genotyping for donors and recipients and will enrol around 40 adult participants who need regular transfusions at University College London Hospitals (UCLH), NHSBT states. bloodMatcher will be evaluated against blood selected manually under the current policy, where people with sickle cell disorder are typically matched only on four core blood groups, the press release says. The study is led by NHSBT in partnership with UCLH and the NIHR UCLH Biomedical Research Centre and is funded by the NIHR AI programme, NHSBT, and the UCLH Biomedical Research Centre, per NHSBT. NHSBT and Digital Health report that all standard transfusion safety checks will remain and that an additional clinical scientist review will be included in the study workflow. Dr Sara Trompeter, consultant haematologist and clinical lead for the study, is quoted saying, "The new bloodMatcher algorithm will... be able to select units in a faster, far more advanced way," (Digital Health).

Genomic matching for transfusion extends the antigen profile available for matching beyond conventional serology by using DNA-based genotyping to infer multiple minor blood-group antigens. Industry-pattern observations note that combining extended antigen profiles with matching algorithms shifts the problem from manual lookup to a computational optimisation task that must weigh antigen compatibility, inventory rarity, and temporal availability. For practitioners, that implies integration challenges around reliable genotype-to-phenotype mapping, data quality for donor genotypes, and the design of objective scoring functions to prioritise candidate units without introducing bias toward or against particular donor subpopulations. Industry observers also highlight that algorithmic matching systems in clinical supply chains require clear audit trails and human-in-the-loop checkpoints to satisfy safety and regulatory expectations.

NHSBT reports that alloimmunisation is a material clinical problem for people with sickle cell disorder, citing that around 17% of adults with the condition develop alloantibodies after repeated transfusions (Digital Health). Industry reporting frames genomic-enabled matching as a potential route to reduce transfusion reactions and better preserve rare units by identifying closer antigen matches, which could have operational benefits for inventory management in national blood services. For practitioners, comparable digital interventions in clinical labs and blood services have shown that demonstrable gains depend on representative donor genotyping, longitudinal outcome data, and carefully designed trial endpoints that capture both immunological outcomes and system-level metrics like unit wastage and turnaround time.

Monitor the study's predefined endpoints: whether the investigators publish results on alloimmunisation incidence, transfusion reactions, and any difference in matched-unit utilisation between algorithmic and manual selection. Watch for publications or registry entries describing the algorithm's matching criteria and performance metrics, and for data on the accuracy and cost of the DNA-based genotyping workflow compared with conventional testing, as NHSBT's materials describe the genotyping as faster and cheaper. Observe whether subsequent trial phases expand to multiple centres and how the study handles consent, privacy, and governance for donor genomic data. Finally, practitioners should look for details on human oversight in the matching pipeline, including the role of the clinical scientist review described by NHSBT, and any third-party validation or external audit accompanying the trial results.