Exploring Blood Donor's Status Through Clustering: A Method to Improve the Quality of Services in Blood Transfusion Centers

Urgent need for blood and lack of an alternative for it necessitates the presence of a model to assist doctors in providing the proper services for the donors and also the right management of blood transfusion centers. The present study is aimed at determining blood donors’ status.
Cross-sectional survey was applied in the present study through census. The population included the data extracted from blood transfusion center of Birjand from Khordad to Shahrivar 1392 which was provided as an Excel file by the direct visit of the researcher from the blood transfusion organization. In the present study, first, two-step clustering and then C50, C&R TREE, CHAID, and QUEST algorithms were executed to obtain the best ratio among different fields. Analysis was performed using Clementine12.0 software.
The obtained accuracy for executing C50, C&R Tree, CHAID, and QUEST equals 0.9998, 0.9960, 0.9930, and 0.8913, respectively. The results of indices including sensitivity, Specificity, accuracy, precision, FM, GM, FPR, FNR, and ER for C50 are indicators of better performance of this algorithm compared to the other ones. Important variables in modeling are blood pressure label, blood donation status and temperature.
The proposed model helps us in predicting faster and more precise status of blood donation and also the proper management of the blood transfusion centers and it canbe and effive step for efficient usage of blood donation and decreasing the blood maintenance costs.