An international comparison of haemoglobin deferral prediction models for blood banking.
donor health
haemoglobin deferral
haemoglobin measurement
prediction
Journal
Vox sanguinis
ISSN: 1423-0410
Titre abrégé: Vox Sang
Pays: England
ID NLM: 0413606
Informations de publication
Date de publication:
Jun 2023
Jun 2023
Historique:
revised:
04
02
2023
received:
02
11
2022
accepted:
01
03
2023
medline:
16
6
2023
pubmed:
17
3
2023
entrez:
16
3
2023
Statut:
ppublish
Résumé
Blood banks use a haemoglobin (Hb) threshold before blood donation to minimize donors' risk of anaemia. Hb prediction models may guide decisions on which donors to invite, and should ideally also be generally applicable, thus in different countries and settings. In this paper, we compare the outcome of various prediction models in different settings and highlight differences and similarities. Donation data of repeat donors from the past 5 years of Australia, Belgium, Finland, the Netherlands and South Africa were used to fit five identical prediction models: logistic regression, random forest, support vector machine, linear mixed model and dynamic linear mixed model. Only donors with five or more donation attempts were included to ensure having informative data from all donors. Analyses were performed for men and women separately and outcomes compared. Within countries and overall, different models perform similarly well. However, there are substantial differences in model performance between countries, and there is a positive association between the deferral rate in a country and the ability to predict donor deferral. Nonetheless, the importance of predictor variables across countries is similar and is highest for the previous Hb level. The limited impact of model architecture and country indicates that all models show similar relationships between the predictor variables and donor deferral. Donor deferral is found to be better predictable in countries with high deferral rates. Therefore, such countries may benefit more from deferral prediction models than those with low deferral rates.
Sections du résumé
BACKGROUND AND OBJECTIVES
OBJECTIVE
Blood banks use a haemoglobin (Hb) threshold before blood donation to minimize donors' risk of anaemia. Hb prediction models may guide decisions on which donors to invite, and should ideally also be generally applicable, thus in different countries and settings. In this paper, we compare the outcome of various prediction models in different settings and highlight differences and similarities.
MATERIALS AND METHODS
METHODS
Donation data of repeat donors from the past 5 years of Australia, Belgium, Finland, the Netherlands and South Africa were used to fit five identical prediction models: logistic regression, random forest, support vector machine, linear mixed model and dynamic linear mixed model. Only donors with five or more donation attempts were included to ensure having informative data from all donors. Analyses were performed for men and women separately and outcomes compared.
RESULTS
RESULTS
Within countries and overall, different models perform similarly well. However, there are substantial differences in model performance between countries, and there is a positive association between the deferral rate in a country and the ability to predict donor deferral. Nonetheless, the importance of predictor variables across countries is similar and is highest for the previous Hb level.
CONCLUSION
CONCLUSIONS
The limited impact of model architecture and country indicates that all models show similar relationships between the predictor variables and donor deferral. Donor deferral is found to be better predictable in countries with high deferral rates. Therefore, such countries may benefit more from deferral prediction models than those with low deferral rates.
Substances chimiques
Hemoglobins
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
430-439Subventions
Organisme : Australian Government
Organisme : Punainen Risti Veripalvelu
Organisme : Stichting Sanquin Bloedvoorziening
ID : PPOC 18-14/L2337
Informations de copyright
© 2023 The Authors. Vox Sanguinis published by John Wiley & Sons Ltd on behalf of International Society of Blood Transfusion.
Références
Spekman MLC, van Tilburg TG, Merz E-M. Do deferred donors continue their donations? A large-scale register study on whole blood donor return in The Netherlands. Transfusion. 2019;59:3657-65.
Custer B, Chinn A, Hirschler NV, Busch MP, Murphy EL. The consequences of temporary deferral on future whole blood donation. Transfusion. 2007;47:1514-23.
Baart AM, de Kort WLAM, Moons KGM, Vergouwe Y. Prediction of low haemoglobin levels in whole blood donors. Vox Sang. 2011;100:204-11.
Nasserinejad K, van Rosmalen J, de Kort W, Rizopoulos D, Lesaffre E. Prediction of hemoglobin in blood donors using a latent class mixed-effects transition model. Stat Med. 2016;35:581-94.
Toivonen J, Koski Y, Turkulainen E, Prinsze F, Parolo PDB, Heinonen M, et al. Prediction and impact of personalized donation intervals. Vox Sang. 2022;117:504-12.
Russell WA, Scheinker D, Custer B. Individualized risk trajectories for iron-related adverse outcomes in repeat blood donors. Transfusion. 2022;62:116-24.
Vinkenoog M, van Leeuwen M, Janssen MP. Explainable haemoglobin deferral predictions using machine learning models: interpretation and consequences for the blood supply. Vox Sang. 2022;117:1262-70.
Baart AM, Timmer T, de Kort WLAM, van den Hurk K. Lifestyle behaviours, ethnicity and menstruation have little added value in prediction models for low haemoglobin deferral in whole blood donors. Transfus Med. 2020;30:16-22.
Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell. 2020;2:56-67.
Hb-predictor Docker Image via Docker Hub [cited 2022 Sep 27]. Available from https://hub.docker.com/r/toivoja/hb-predictor
GitHub source for Hb deferral prediction. 2022.
R Core Team. R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing; 2020.
Wickham H, François R, Henry L, Müller K. RStudio. dplyr: A Grammar of Data Manipulation. 2022.
Wickham H, Girlich M. RStudio. tidyr: Tidy Messy Data. 2022.
Wickham H, Chang W, Henry L, Pedersen TL, Takahashi K, Wilke C, et al. ggplot2: Create Elegant Data Visualisations Using the Grammar of Graphics. 2022.
Anderson JA. Separate sample logistic discrimination. Biometrika. 1972;59:19-35.
Paalvast Y, Moazzen S, Sweegers M, Hogema B, Janssen M, van den Hurk K. A computational model for prediction of ferritin and haemoglobin levels in blood donors. Br J Haematol. 2022;199:143-52.
Janssen MP. Why the majority of on-site repeat donor deferrals are completely unwarranted…. Transfusion. 2022;62:2068-75.
Bäckman S, Valkeajärvi A, Korkalainen P, Arvas M, Castrén J. Venous sample is superior to repeated skin-prick testing in blood donor haemoglobin second-line screening. Vox Sang. 2020;115:617-23.