SEGMENTATION OF MEDICAL BIOMARKER PROFILES AND ACTIVITY LEVELS OF BLOOD DONORS AT UDD PMI SURABAYA CITY USING K-MEANS CLUSTERING AND PCA
Keywords:
blood donor segmentation, k-means clustering, medical biomarkers, principal component analysis, retention analyticsAbstract
Maintaining a stable and safe blood supply requires comprehensive insight into both the physiological characteristics and donation retention patterns of active blood donors. At the Blood Transfusion Unit of the Indonesian Red Cross in Surabaya City, donation records have primarily been summarized through basic demographic counts without integrating clinical screening indicators and repeat donation behavior into unified donor profiles. This study aims to segment active blood donors based on medical screening biomarkers and donation frequency to support targeted donor retention strategies. Using observational transaction records collected from January to October 2026, clinical data cleaning and donor-level aggregation transformed 136,031 initial records into 134,980 validated donation transactions representing 78,074 unique donors. Seven standardized variables comprising average age, donation frequency, hemoglobin level, systolic blood pressure, diastolic blood pressure, pulse rate, and body weight were clustered using the k-means algorithm, validated via silhouette evaluation and the non-parametric Kruskal-Wallis test, and projected using principal component analysis. Four distinct donor segments emerged with an optimal silhouette score of 0.2036 and statistically significant differences across all indicators: young adults with lighter body weight representing 47.31 percent of donors with low donation frequency, mature routine donors representing 19.39 percent with the highest average frequency of 3.54 donations within ten months, middle-aged donors with higher blood pressure and body weight representing 32.54 percent, and a minor elevated-pulse group representing 0.77 percent. These findings provide an empirical foundation for automated post-donation reminders aligned with the mandatory sixty-one-day medical recovery interval.
References
Andini, T. D., & Farokhah, L. (2022). Peningkatan ketersediaan darah sesuai segmentasi umur menggunakan K-Means clustering. Jurnal Manajemen Informatika (JAMIKA), 12(2), 126-136. https://doi.org/10.34010/jamika.v12i2.7897
Arifin, S., Manurung, M. M., Jonathan, S., & Alifah, M. (2026). A review of Kruskal-Wallis test applications in scientific research. Journal of Applied Finance & Risk Management, 4(2), 42-55. https://e-journal.president.ac.id/index.php/JAFRM/article/download/6301/2413
Armayanti, D., & Astuti, Y. (2023). Gambaran penangguhan pendonor di Unit Donor Darah PMI Kota Yogyakarta tahun 2022. Jurnal Sehat Mandiri, 18(2), 11-23. https://doi.org/10.33761/jsm.v18i2.1015
Ben Elmir, W., Hemmak, A., & Senouci, B. (2023). Smart platform for data blood bank management: Forecasting demand in blood supply chain using machine learning. Information, 14(1), Article 31. https://doi.org/10.3390/info14010031
Ezugwu, A. E., Ikotun, A. M., Oyelade, O. O., Abualigah, L., Agushaka, J. O., Eke, C. I., & Akinyelu, A. A. (2022). A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Engineering Applications of Artificial Intelligence, 110, Article 104743. https://doi.org/10.1016/j.engappai.2022.104743
Gewers, F. L., Ferreira, G. R., Arruda, H. F. D., Silva, F. N., Comin, C. H., Amancio, D. R., & Costa, L. D. F. (2021). Principal component analysis: A natural approach to data exploration. ACM Computing Surveys, 54(4), Article 70. https://doi.org/10.1145/3447755
Greenacre, M., Groenen, P. J. F., Hastie, T., D'Enza, A. I., Markos, A., & Tuzhilina, E. (2022). Principal component analysis. Nature Reviews Methods Primers, 2, Article 100. https://doi.org/10.1038/s43586-022-00184-w
Ikotun, A. M., Ezugwu, A. E., Abualigah, L., Abuhaija, B., & Heming, J. (2023). K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Information Sciences, 622, 178-210. https://doi.org/10.1016/j.ins.2022.11.139
Ningsih, A. W., Novriyenni, & Khair, H. (2025). Pengelompokkan pendonor darah berdasarkan golongan darah di PMI Kabupaten Langkat menggunakan metode clustering K-Means. Fusion: Journal of Research in Engineering, Technology and Applied Sciences, 2(1), 40-48. https://doi.org/10.66341/fusion.v2i1.261
Okoye, K., & Hosseini, S. (2024). Mann-Whitney U test and Kruskal-Wallis H test statistics in R. In R programming: Statistical data analysis in research (pp. 225-246). Springer Nature Singapore. https://doi.org/10.1007/978-981-97-3385-9_11
Pratiwi, D., & Prasetyo, A. B. (2026). Klasterisasi donor darah reaktif IMLTD di PMI DKI Jakarta dengan K-Means. Indonesian Journal of Multidisciplinary on Social and Technology, 4(3), 2085-2098. https://doi.org/10.69693/ijmst.v4i3.12496
Ramadhan, M. R. (2023). Clustering pasien yang layak donor darah dengan algoritma K-Means studi kasus PMI Kota Medan. Jurnal Sains dan Teknologi Informasi, 2(3), 74-79. https://doi.org/10.47065/jussi.v2i3.4596
Shutaywi, M., & Kachouie, N. N. (2021). Silhouette analysis for performance evaluation in machine learning with applications to clustering. Entropy, 23(6), Article 759. https://doi.org/10.3390/e23060759
Twumasi, C., & Twumasi, J. (2022). Machine learning algorithms for forecasting and backcasting blood demand data with missing values and outliers: A study of Tema General Hospital of Ghana. International Journal of Forecasting, 38(3), 1258-1277. https://doi.org/10.1016/j.ijforecast.2021.10.008
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Khairunisa Olive Ektha, Nada Amalia Choiro, Kartika Maulida Hindrayani, Aviolla Terza Damaliana (Author)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

