An international comparison of haemoglobin deferral prediction models for blood banking

Iron status in Dutch and Finnish blood donor and general populations: A cross-cohort comparison study

BACKGROUND AND OBJECTIVES

Blood donors are at risk of developing iron deficiency (ID) (ferritin <15 μg/L, World Health Organization definition). Blood services implement different strategies to mitigate this risk. Although in Finland risk group-based iron supplementation is in place, no iron supplementation is provided in the Netherlands. We aim to describe differences in ferritin levels and ID prevalence in donor and general populations in these countries.

MATERIALS AND METHODS

Six cohorts, stratified based on sex, and for women age, in the Netherlands and Finland were used to evaluate differences in ferritin levels and ID between donor populations (Donor InSight-III and FinDonor 10,000) and general populations (Prevention of Renal and Vascular End-Stage Disease [PREVEND], FinRisk 1997 and Health 2000) and newly registered Dutch donors. Multivariable logistic regression was used to quantify associations of various explanatory factors with ID.

RESULTS

In total, 13,443 Dutch and 13,933 Finnish subjects were included. Donors, except for women aged ≤50 years old in Finland, had lower median ferritin levels compared with the general population and new donors. Dutch regular blood donors had higher or similar prevalence of ID as compared with the Dutch general population, including new donors. In contrast, Finnish donors showed similar prevalence of ID compared with the general population, except for a markedly lower prevalence in ≤50-year-old women who routinely receive iron supplements when donating.

CONCLUSION

Iron status in blood donors differs from that in the general population. The Finnish blood service donor management policy, for example, iron supplementation for risk groups, seemingly protects young female blood donors from developing ID.

Predicting haemoglobin deferral using machine learning models: Can we use the same prediction model across countries?

BACKGROUND AND OBJECTIVES

Personalized donation strategies based on haemoglobin (Hb) prediction models may reduce Hb deferrals and hence costs of donation, meanwhile improving commitment of donors. We previously found that prediction models perform better in validation data with a high Hb deferral rate. We therefore investigate how Hb deferral prediction models perform when exchanged with other blood establishments.

MATERIALS AND METHODS

Donation data from the past 5 years from random samples of 10,000 donors from Australia, Belgium, Finland, the Netherlands and South Africa were used to fit random forest models for Hb deferral prediction. Trained models were exchanged between blood establishments. Model performance was evaluated using the area under the precision-recall curve (AUPR). Variable importance was assessed using SHapley Additive exPlanations (SHAP) values.

RESULTS

Across the validation datasets and exchanged models, the AUPR ranged from 0.05 to 0.43. Exchanged models performed similarly within validation datasets, irrespective of the origin of the training data. Apart from subtle differences, the importance of most predictor variables was similar in all trained models.

CONCLUSION

Our results suggest that Hb deferral prediction models trained in different blood establishments perform similarly within different validation datasets, regardless of the deferral rate of their training data. Models learn similar associations in different blood establishments.

The added value of ferritin levels and genetic markers for the prediction of haemoglobin deferral

BACKGROUND AND OBJECTIVES

On-site haemoglobin deferral for blood donors is sometimes necessary for donor health but demotivating for donors and inefficient for the blood bank. Deferral rates could be reduced by accurately predicting donors' haemoglobin status before they visit the blood bank. Although such predictive models have been published, there is ample room for improvement in predictive performance. We aim to assess the added value of ferritin levels or genetic markers as predictor variables in haemoglobin deferral prediction models.

MATERIALS AND METHODS

Support vector machines with and without this information (the full and reduced model, respectively) are compared in Finland and the Netherlands. Genetic markers are available in the Finnish data and ferritin levels in the Dutch data.

RESULTS

Although there is a clear association between haemoglobin deferral and both ferritin levels and several genetic markers, predictive performance increases only marginally with their inclusion as predictors. The recall of deferrals increases from 68.6% to 69.9% with genetic markers and from 79.7% to 80.0% with ferritin levels included. Subgroup analyses show that the added value of these predictors is higher in specific subgroups, for example, for donors with minor alleles on single-nucleotide polymorphism 17:58358769, recall of deferral increases from 73.3% to 93.3%.

CONCLUSION

Including ferritin levels or genetic markers in haemoglobin deferral prediction models improves predictive performance. The increase in overall performance is small but may be substantial for specific subgroups. We recommend including this information as predictor variables when available, but not to collect it for this purpose only.