Blood platelet inventory management: Incorporating data-driven demand forecasts.

Clicks: 146
ID: 281860
2025
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #21 of 25 articles by views in health care management science

Most read Least read

Bar heights use a square-root scale.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Platelet products are vital in the blood transfusion system since they are used for treating serious diseases such as cancer. They are expensive products (C$504 per unit) with a short shelf life of five to seven days. Since platelet demand is uncertain and highly variable, platelet inventory management is a challenging task. In this work, we propose a data-driven inventory management model for platelet products that incorporates demand forecasts in the inventory management process. The proposed model uses forecast-dependent target inventory levels to determine an ordering policy that has a goal of minimizing both the shortage and wastage. The data used in this study is a large clinical dataset of daily platelet transfusions for a centralized blood distribution centre for four hospitals in Hamilton, Ontario, spanning from 2016 to 2018. Experimental results show that our proposed policy performs well in minimizing shortages and wastages and that larger forecast errors can be tolerated as the system scales (for example as a result of demand aggregation and inventory pooling). We also perform sensitivity analysis to provide a more in-depth study of the proposed model. In particular, we suggest that by incorporating demand forecasts in the inventory management model, ordering less frequently than daily is feasible.
Reference Key
motamedi2025blood Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Motamedi, Maryam; Dawson, Jessica; Li, Na; Down, Douglas
Journal health care management science
Year 2025
DOI
10.1007/s10729-025-09706-w
URL
Keywords
inventory management operations research operations management health service forecasting base stock data-driven optimization platelet inventory management

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.