Home / Current Issue / Paper 1712621
Demand Forecasting for Community Blood Supply: Time Series and Causal Methods for Optimal Collections and Inventory Safety
Subject area: Science,Engineering and Technology · Area of research: Health Data Science
Abstract
Blood supply is one of the pillars of healthcare delivery, and community-based centers tend to have challenges balancing the quantity of donations with the changing demand in hospitals (Gammon et al., 2020; Li et al., 2023). The fact that blood products are perishable and their demand is unpredictable makes the provision of availability and minimal waste difficult (Abouee-Mehrizi et al., 2019; Zhang et al., 2022). The purpose of conducting the study is to create a hybrid time series-causal forecasting model, which would combine the information about hospital issues, campaign planning, and demographics to optimize collection planning and inventory security. The suggested model is a unified system of ARIMA and Prophet models and exogenous regressors that utilize seasonality, community behavior, and population dynamics (Ding et al., 2023; Motamedi et al., 2024). Model validation concentrates on service-level performance like stock-out days and wastage rates and makes sure that the statistics as well as the operations are relevant. Results show that hybrid models have better performance compared to the conventional time series models in terms of minimizing forecasting error and efficiency in drive scheduling. In addition to having predictive performance, the study also adds an open-source and nonprofit-accessible forecasting workbook to achieve transparency and replicability in managing blood within communities (Bouzarjomehri et al., 2025; Chen, 2025). This framework promotes the involvement of data-based planning in the logistics of public health and assists in upholding ethical and sustainable management of resources.
References
[1] Abouee‐Mehrizi, H., Baron, O., Berman, O. and Chen, D. (2019). Managing Perishable Inventory Systems with Multiple Priority Classes. Production and Operations Management, 28(9), pp.2305–2322. doi:https://doi.org/10.1111/poms.13058.
[2] Ahmed, T., Hasan, M.M., Huan, X. and Saxton, G.D. (2025). Climate Risk and Donations to Nonprofit Organizations. Journal of Business Ethics, [online] pp.1–22. doi:https://doi.org/10.1007/s10551-025-06158-8.
[3] Aror, E. and Mupa, M.N., 2025. Family Law and the Best Interests of the Child Standard Developing: Incorporating the Mental Health, Cultural History and the Voice of the Child in Custody Determinations.
[4] Bhattacharjee, B. (2025). The Role of Nonprofits in the U.S. Economy. [online] 2025(10). Available at: https://www.researchgate.net/publication/396244766_The_Role_of_Nonprofits_in_the_US_Economy.
[5] Bouzarjomehri, H., Maleki, M., Masoudi‐Asl, I. and Ranjbar, M. (2025). Enhancing Transparency: Core Principles for a Developing Health System. World Medical & Health Policy. doi:https://doi.org/10.1002/wmh3.70029.
[6] Bundala, F.A., Kamala, B.A., Moshiro, R., Guga, G., Munishi, C., Ismail, H.R., Mdoe, P.F., Ersdal, H., Rettedal, S. and Salim, N. (2025). Availability and functioning of neonatal care units and neonatal mortality across five regions in Tanzania: a baseline cross-sectional study in 127 CEmONC health facilities. BMJ Global Health, [online] 10(5), pp.e018758–e018758. doi:https://doi.org/10.1136/bmjgh-2024-018758.
[7] Chen, X. (2025). Funding the Future: How Size, Revenue, and Community Shape Retirement Benefits in Nonprofits. Merits, [online] 5(4), p.20. doi:https://doi.org/10.3390/merits5040020.
[8] Chideme, C. and Chikobvu, D. (2024). Application of Time-Series Analysis and Expert Judgment in Modeling and Forecasting Blood Donation Trends in Zimbabwe. MDM Policy & Practice, 9(1). doi:https://doi.org/10.1177/23814683231222483.
[9] Dauphinet, M., Henriques, R. and Monteiro, P.T. (2024). Context-Aware Deep Forecasting: Principles for the Nation-Wide Management of Blood Products. Lecture notes in computer science, pp.359–372. doi:https://doi.org/10.1007/978-3-031-73503-5_29.
[10] Ding, X., Zhang, X., Li, X. and Du, J. (2023). A hybrid neural network based model for blood donation forecasting. Journal of Biomedical Informatics, 146, pp.104488–104488. doi:https://doi.org/10.1016/j.jbi.2023.104488.
[11] Duong, L.N.K., Wood, L.C. and Wang, W.Y.C. (2018). A review and reflection on inventory management of perishable products in a single-echelon model. International Journal of Operational Research, 31(3), p.313. doi:https://doi.org/10.1504/ijor.2018.089734.
[12] Ebinger, F. and Omondi, B. (2020). Leveraging Digital Approaches for Transparency in Sustainable Supply Chains: A Conceptual Paper. Sustainability, [online] 12(15), p.6129. Available at: https://www.mdpi.com/2071-1050/12/15/6129.
[13] Fortsch, S.M. and Liao, Q. (2019). Decreasing operational costs of non-profit community-based blood centres. International Journal of Business and Systems Research, 13(4), p.419. doi:https://doi.org/10.1504/ijbsr.2019.102522.
[14] Gammon, R.R., Rosenbaum, L., Cooke, R., Friedman, M., Rockwood, L., Nichols, T. and Vossoughi, S. (2020). Maintaining adequate donations and a sustainable blood supply: Lessons learned. Transfusion, 61(1), pp.294–302. doi:https://doi.org/10.1111/trf.16145.
[15] Giriteka, T., Bulakali, D.P. and Wendler, C.B. (2023). Essential human and material resources for emergency care in the district hospitals of Burundi. ResearchGate. [online] doi:https://doi.org/10.1016//j.afjem.2023.09.005.
[16] Gmakouba, W., Azianu, K., Gangak, L., Kombate, G., Bini, M. and Bantakpa, S. (2025). Availability of Health Services and Preparedness for Basic Emergency Obstetric and Newborn Care in Togo. World Journal of Public Health, 10(2), pp.106–119. doi:https://doi.org/10.11648/j.wjph.20251002.14.
[17] Grieger, M., Brunner, J.O., Heller, A.R. and Bartenschlager, C.C. (2025). Scarce, scarcer, scarcest: performance-flexible AI-based planning of elective surgeries for efficient and effective intensive care capacity management. OR Spectrum. doi:https://doi.org/10.1007/s00291-025-00830-1.
[18] Gunzo, L.T., Mupa, M.N., Nemure, T., Muchenje, J.D. and Ndlovu, N.T., 2025a. Forecasting Feeder-Level Outages with Hybrid Time-Series/ML Models: Accuracy, Explainability, and Maintenance Prioritization. management (Soumbara, 2025; Ezugwu, 2025), 35, p.10.
[19] Gunzo, L.T., Nemure, T., Mupa, M.N. and Muchenje, J.D., 2025b. Deepfake-Resistant Telehealth: Multi-Factor Voice-Face-Contextive Verification Under Real-Time Constraints.
[20] Hlahla, V., Mupa, M.N. and Danda, C., 2025. Donor-funded project financial management: Lessons from global development initiatives for US community-based programs. World Journal of Advanced Research and Reviews,[online], 27(2), pp.1812-1821.
[21] Kalu-Mba, N.N.A.N.N.A., Mupa, M.N. and Tafirenyika, S., 2025. Artificial Intelligence as a Catalyst for Innovation in the Public Sector: Opportunities, Risks, and Policy Imperatives.
[22] Kashaka, N.D. (2025). Exploring the Role of Nonprofits in Community Development. Research Invention Journal of Research In Education, [online] 5(1), pp.1–7. doi:https://doi.org/10.59298/rijre/2025/5117.
[23] Keppler, S.M. (2025). Rethinking Frontline Nonprofit Operations: The Role of Aggregator Organizations. Springer series in supply chain management, pp.73–97. doi:https://doi.org/10.1007/978-3-031-74994-0_5.
[24] Khan, M., Lee, H. and Bae, J. (2019). The Role of Transparency in Humanitarian Logistics. Sustainability, 11(7), p.2078. doi:https://doi.org/10.3390/su11072078.
[25] Kharel, R., Thapa, G.B., Voor, T., Pant, S.R., Adhikari, S.K., Bist, B.S., Relan, P., Lin, T., Lubetkin, D., Deluca, G., Shilpakar, O., Shrestha, S.K., Pokharel, Y.R., Paudel, S., Thapa, A.S., Shakya, Y.M., Karki, A.R., Dhakal, N. and Aluisio, A.R. (2023). Emergency unit assessment of seven tertiary hospitals in Nepal using the WHO tool: a cross-sectional study. [online] 16(1). doi:https://doi.org/10.1186/s12245-023-00484-2.
[26] Leong, X.Y., Jajo, N., Peiris, S. and Khadra, M. (2023). Forecasting Elective Surgery Demand Using ARIMA-Machine Learning Hybrid Model. European Journal of Artificial Intelligence and Machine Learning, 2(3), pp.1–7. doi:https://doi.org/10.24018/ejai.2023.2.3.19.
[27] Li, N., Pham, T., Cheng, C., McElfresh, D.C., Metcalf, R.A., Russell, W.A., Birch, R., Yurkovich, J.T., Montemayor-Garcia, C., Lane, W.J., Tobian, A.A.R., Roubinian, N., Seheult, J. and Goel, R. (2023). Blood Demand Forecasting and Supply Management: An Analytical Assessment of Key Studies Utilizing Novel Computational Techniques. Transfusion Medicine Reviews, [online] p.150768. doi:https://doi.org/10.1016/j.tmrv.2023.150768.
[28] Matenga, H.R., Mupa, M.N. and Musemwa, B.M., 2025. Artificial Intelligence-Driven Mechatronic System for Energy Efficiency in US Manufacturing Industries [online]
[29] Matthew, B. (2025). Adopting AIPowered Demand Sensing to Navigate Seasonal Demand Volatility. [online] Logistics & Supply Chain Review. Available at: https://www.researchgate.net/publication/393888619_Adopting_AI-Powered_Demand_Sensing_to_Navigate_Seasonal_Demand_Volatility [Accessed 27 Oct. 2025].
[30] Mkalaf, K.A., Rami, H. and Gibson, P. (2023). Application of Overall Equipment Effectiveness for Optimizing Ventilator Reliability in Intensive Care Units and Emergency Departments. Journal of techniques, 5(2), pp.187–196. doi:https://doi.org/10.51173/jt.v5i2.1419.
[31] Motamedi, M., Dawson, J., Li, N., Li, N., Li, N., Down, D.G., Heddle, N.M. and Heddle, N.M. (2024). Demand forecasting for platelet usage: From univariate time series to multivariable models. PloS one, 19(4), pp.e0297391–e0297391. doi:https://doi.org/10.1371/journal.pone.0297391.
[32] Muchenje, J.D., Mupa, M.N., Mupa, M.W.M., Nayo, D. and Homwe, T., 2025a. Datacenter microgrids: Cost-Emissions-Reliability Frontier Across US RTOs.
[33] Muchenje, J.D., Mupa, M.N., Nayo, D. and Homwe, T., 2025b. Actuarial-ML Bridges for Catastrophe Loss Mitigation: Translating Grid Reliability.
[34] Niakan, P.B., Keramatpour, M., Afshar-Nadjafi, B. and Komijan, A.R. (2024). An Integrated Supply Chain Model for Predicting Demand and Supply and Optimizing Blood Distribution. Logistics, 8(4), p.134. doi:https://doi.org/10.3390/logistics8040134.
[35] Privett, N. (2011). Operations Management in Community-Based Nonprofit Organizations. International series in management science/operations research, pp.67–95. doi:https://doi.org/10.1007/978-1-4614-0806-2_3.
[36] Rehman, D.T. (2025). Artificial Intelligence in Public Health: A Community-Centered Approach to Medical Innovation. Journal of Social Sciences and Community Support , [online] 2(1), pp.12–22. Available at: https://www.researchcorridor.org/index.php/jsscs/article/view/479 [Accessed 27 Oct. 2025].
[37] Sena, E.V., Syed, Z. and Mupa, M.N., 2024. Effects of Digital Health Records on the Quality of patients' Health and Health Care Organizations.
[38] Sena, E.V., Syed, Z.A. and Mupa, M.N., 2024. The Impact of Integrating Mental health Services into Primary Care on Health Care Outcomes.
[39] Shokouhifar, M. and Ranjbarimesan, M. (2022). Multivariate time-series blood donation/demand forecasting for resilient supply chain management during COVID-19 pandemic. Cleaner Logistics and Supply Chain, p.100078. doi:https://doi.org/10.1016/j.clscn.2022.100078.
[40] Yashkin, D. (2020). Forecasting the inventory levels of an industrial enterprise in conditions of demand volatility. Marketing and Digital Technologies, 4(4), pp.82–92. doi:https://doi.org/10.15276/mdt.4.4.2020.6.
[41] Zare, H. and Anderson, G. (2025). The Significance of Definitions in Determining the Level of Community Benefits for Nonprofit Hospitals. The Milbank Quarterly, 103(3), pp.809–830. doi:https://doi.org/10.1111/1468-0009.70041.
[42] Zhang, C., Ayer, T., White, C.C., Bodeker, J.N. and Roback, J.D. (2022). Inventory Sharing for Perishable Products: Application to Platelet Inventory Management in Hospital Blood Banks. Operations Research. doi:https://doi.org/10.1287/opre.2022.2410.
How to cite this paper
@article{1712621,
author = {Zainab Mugenyi, Munashe Naphtali Mupa, Kwame Ofori Boakye, Nicholas Donkor, Farisai Melody Nare},
title = {Demand Forecasting for Community Blood Supply: Time Series and Causal Methods for Optimal Collections and Inventory Safety},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {590-600},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712621.pdf},
abstract = {Blood supply is one of the pillars of healthcare delivery, and community-based centers tend to have challenges balancing the quantity of donations with the changing demand in hospitals (Gammon et al., 2020; Li et al., 2023). The fact that blood products are perishable and their demand is unpredictable makes the provision of availability and minimal waste difficult (Abouee-Mehrizi et al., 2019; Zhang et al., 2022). The purpose of conducting the study is to create a hybrid time series-causal forecasting model, which would combine the information about hospital issues, campaign planning, and demographics to optimize collection planning and inventory security. The suggested model is a unified system of ARIMA and Prophet models and exogenous regressors that utilize seasonality, community behavior, and population dynamics (Ding et al., 2023; Motamedi et al., 2024). Model validation concentrates on service-level performance like stock-out days and wastage rates and makes sure that the statistics as well as the operations are relevant. Results show that hybrid models have better performance compared to the conventional time series models in terms of minimizing forecasting error and efficiency in drive scheduling. In addition to having predictive performance, the study also adds an open-source and nonprofit-accessible forecasting workbook to achieve transparency and replicability in managing blood within communities (Bouzarjomehri et al., 2025; Chen, 2025). This framework promotes the involvement of data-based planning in the logistics of public health and assists in upholding ethical and sustainable management of resources.},
month = {December},
}