Optimizing Red Blood Cells Consumption Using Markov Decision Process

Khayat Rasoli, Mehran; Yousefi Nejad Attari, Mahdi; Ebadi Torkayesh, Ali; Neishabouri Jami, Ensiyeh

doi:10.22070/jqepo.2020.3210.1062

Optimizing Red Blood Cells Consumption Using Markov Decision Process

Document Type : Research Paper

Authors

mehran khayat rasoli ¹

mahdi yousefi nejad attari ¹

Ali Ebadi Torkayesh ²

ensiyeh neishabouri jami ¹

¹ Department of Industrial Engineering, Bonab branch, Islamic Azad University, Bonab, Iran

² Sabanci University, Faculty of Engineering and Natural Sciences, Istanbul, Turkey

10.22070/jqepo.2020.3210.1062

Abstract

In healthcare systems, one of the important actions is related to perishable products such as red blood cells (RBCs) units that its consumption management in different periods can contribute greatly to the optimality of the system. In this paper, main goal is to enhance the ability of medical community to organize the RBCs units’ consumption in way to deliver the unit order timely with a focus on minimizing total costs of the system. In each medical center such as hospitals or clinics, decision makers consider a one-day period for their policy making about supply and demand of RBCs. Based on the inventory status of the previous day, decisions are made for following day. In this paper, we use Markov decision process (MDP) as a sequential decision-making approach for blood inventory problem considering red blood cells consumption. The proposed MDP model for RBCs consumption management is solved using sequential approximation algorithm. We perform a case study for the proposed model using blood consumption data of Zanjan, Iran. Results for several blood types are discussed accordingly. In terms of total cost of the system, LIFO-LIFO policy is best policy for RBCs consumption among all other policies. In order to analyze the importance of some parameters in the model, a sensitivity analysis is done over shortage cost.

Keywords

Red Blood Cells

Markov Decision Process

Blood Supply Chain

Sequential Approximation Algorithm