Comparative Study of Machine Learning Algorithms for Blood Donor Availability

Author

K. Manicka Dharsini, Dr. Nancy Jasmine Goldena

Abstract

 Efficient identification of available blood donors is an important requirement in emergency healthcare situations, where delays in locating suitable donors can affect timely blood availability. This paper presents a comparative analysis of four supervised machine learning algorithms, namely Logistic Regression, Decision Tree, Random Forest, and K-Nearest Neighbors (KNN), for predicting blood donor availability. Donor demographic, health, location, and donation history attributes are considered as predictive features. The dataset is preprocessed by selecting relevant attributes and converting categorical values into numerical representations before model training. The four algorithms are trained and evaluated under the same experimental conditions using Accuracy, Precision, Recall, and F1-Score. The comparative results indicate that Random Forest achieves the best overall performance among the evaluated algorithms. The trained machine learning approach is integrated with location and blood group-based donor search to identify and prioritize potentially available donors matching the required criteria. The proposed approach provides a data-driven mechanism for improving donor identification and supporting efficient blood donor selection during emergency healthcare situations.

Keywords

Blood Donor Availability, Machine Learning, Donor Prediction, Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors, Comparative Analysis, Classification.

Full Text:

Download Paper PDF

References

[1] A. Sivasankaran, E. Williams, M. Albrecht, G. E. Switzer, V. S. Cherkassky, and M. Maiers, “Machine Learning Approach to Predicting Stem Cell Donor Availability,” Biology of Blood and Marrow Transplantation, vol. 24, no. 12, pp. 2425–2432, 2018. DOI: 10.1016/j.bbmt.2018.07.035.

[2] Y. Li, A. Masiliune, D. Winstone, L. Gasieniec, P. Wong, H. Lin, R. Pawson, G. Parkes, and A. Hadley, “Predicting the Availability of Hematopoietic Stem Cell Donors Using Machine Learning,” Biology of Blood and Marrow Transplantation, vol. 26, no. 8, pp. 1406–1413, 2020. DOI: 10.1016/j.bbmt.2020.03.026.

[3] H. Y. Wu, Z. G. Li, X. K. Sun, W. M. Bai, A. D. Wang, Y. C. Ma, R. H. Diao, E. Y. Fan, F. Zhao, Y. Q. Liu, et al., “Predicting Willingness to Donate Blood Based on Machine Learning: Two Blood Donor Recruitments During COVID-19 Outbreaks,” Scientific Reports, vol. 12, p. 19165, 2022. DOI: 10.1038/s41598-022-21215-2.

[4] H. Shih and S. Rajendran, “Comparison of Time Series Methods and Machine Learning Algorithms for Forecasting Taiwan Blood Services Foundation’s Blood Supply,” Journal of Healthcare Engineering, vol. 2019, Article ID 6123745, pp. 1–6, 2019. DOI: 10.1155/2019/6123745.

[5] X. Ding, X. Zhang, X. Li, and J. Du, “A Hybrid Neural Network Based Model for Blood Donation Forecasting,” Journal of Biomedical Informatics, vol. 146, p. 104488, 2023. DOI: 10.1016/j.jbi.2023.104488.

Share your valuable work from Social Media Buttons