EUVIMEDEUVIMED entdecken
Crossref

Prediction of blood donor return behaviour using machine learning

Cheng-Hung Yeh, Chi-Ming Hung iD, Hao-Hsuan Chung, Wei-Jan Su

Vox Sanguinis · 2026-04 · 121 (4) · 453-460

DOI: 10.1111/vox.70139 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Vox Sanguinis, online erschienen am 20.10.2025. Verfasst von Cheng-Hung Yeh und 3 weiteren Autor:innen. Beteiligte Einrichtung: Taiwan Blood Services Foundation Kaohsiung Blood Center, Kaohsiung City, Taiwan, ROC. Hauptthemen laut MEDLINE: Blood Donors, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Kaohsiung Blood Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Objectives Blood donor return behaviour is frequently examined through questionnaires assessing donors' motivations, attitudes, awareness and willingness to donate. An enhanced donor invitation model that better predicts donation dynamics using specific behavioural variables is needed. This study aims to incorporate machine learning into processing blood donor datasets, thereby increasing donor return rates through precision marketing. Materials and Methods This retrospective study was conducted between 1 January 2022 and 31 December 2023, focusing on blood donors whose records were maintained by the Kaohsiung Blood Center in Taiwan. Three machine learning models (MLMs), namely eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and Categorical Boosting (CatBoost), were employed. Each model underwent cross‐validation, and their performance was evaluated using accuracy, average precision, balanced accuracy, F1 score and log loss. The best performing model was selected to generate predictive donor return lists, which were subsequently tested.

Results

All three MLMs demonstrated strong predictive power in generating donor return prediction lists. The performance metrics for the three models were as follows: accuracy: 0.8093, 0.8096 and 0.8106; specificity: 0.9227, 0.9256 and 0.9229. CatBoost was found to be the best performing model. The most influential predictive factors were return donation interval and donation location. Results showed a significant improvement in donor return rates (57.99% vs. 15.54%, p < 0.0001).

Conclusion

MLMs leveraging both behavioural and demographic variables can predict and identify high‐return‐rate donors by prioritizing return thresholds. Precision marketing significantly improves donor return rates, enabling blood banks to rapidly meet transfusion demands during emergencies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Blood DonorsMachine LearningHumansRetrospective StudiesMaleFemaleAdultMiddle AgedTaiwanMotivationSurveys and Questionnaires

Stichwörter der Autor:innen

blood donordonor behaviourdonor retentionmachine learningprecision marketing

Autor:innen und Institutionen

  • Taiwan Blood Services Foundation Kaohsiung Blood Center, Kaohsiung City, Taiwan, ROC.
  • Department of Industrial Management, National Taiwan University of Science and Technology, Taipei City, Taiwan, ROC.

ORCID-Profile: Chi-Ming Hung

Förderung

  • Kaohsiung Blood Center

Zitieren

APA

Yeh, C. H., Hung, C. M., Chung, H. H., & Su, W. J. (2026). Prediction of blood donor return behaviour using machine learning. Vox Sanguinis, 121(4), 453-460. https://doi.org/10.1111/vox.70139

Vancouver

Yeh CH, Hung CM, Chung HH, Su WJ. Prediction of blood donor return behaviour using machine learning. Vox Sanguinis. 2026;121(4):453-460. doi:10.1111/vox.70139

BibTeX
@article{Yeh2026,
  author = {Yeh, Cheng-Hung and Hung, Chi-Ming and Chung, Hao-Hsuan and Su, Wei-Jan},
  title = {Prediction of blood donor return behaviour using machine learning},
  journal = {Vox Sanguinis},
  year = {2026},
  volume = {121},
  number = {4},
  pages = {453--460},
  doi = {10.1111/vox.70139}
}
Kostenlos starten →