TY - JOUR
T1 - Forecasting sustainability of healthcare supply chains using deep learning and network data envelopment analysis
AU - Azadi, Majid
AU - Yousefi, Saeed
AU - Saen, Reza Farzipoor
AU - Shabanpour, Hadi
AU - Jabeen, Fauzia
PY - 2023/1
Y1 - 2023/1
N2 - The main objective of this study is to propose a network data envelopment analysis (NDEA) model and a deep learning approach for forecasting the sustainability of healthcare supply chains (HSCs). Technological advances manifested in approaches such as deep learning, artificial intelligence (AI), and Blockchain are of substantial importance throughout HSCs and are understood as competitive advantages. Furthermore, applying advanced performance evaluation techniques, including DEA in HSCs for enhancing performance has attracted momentous attention over the last two decades. To make use of these approaches, a network DEA (NDEA) model and a deep learning approach are developed to predict the sustainability of HSCs. The developed model in this paper can determine the optimal value of bounded connections. Using the DEA capabilities, the threshold of each of these bounded connections is obtained to maximize the efficiency of decision making units (DMUs). It also identifies the role of the dual-role connections for each DMU. The results show that HSCs that use the least facilities and have the most desirable output, as well as the least undesirable output, are in the top ranks.
AB - The main objective of this study is to propose a network data envelopment analysis (NDEA) model and a deep learning approach for forecasting the sustainability of healthcare supply chains (HSCs). Technological advances manifested in approaches such as deep learning, artificial intelligence (AI), and Blockchain are of substantial importance throughout HSCs and are understood as competitive advantages. Furthermore, applying advanced performance evaluation techniques, including DEA in HSCs for enhancing performance has attracted momentous attention over the last two decades. To make use of these approaches, a network DEA (NDEA) model and a deep learning approach are developed to predict the sustainability of HSCs. The developed model in this paper can determine the optimal value of bounded connections. Using the DEA capabilities, the threshold of each of these bounded connections is obtained to maximize the efficiency of decision making units (DMUs). It also identifies the role of the dual-role connections for each DMU. The results show that HSCs that use the least facilities and have the most desirable output, as well as the least undesirable output, are in the top ranks.
KW - Deep learning
KW - Forecasting
KW - Network data envelopment analysis (NDEA)
KW - Performance measurement
KW - Sustainable healthcare supply chain
UR - http://www.scopus.com/inward/record.url?scp=85140320702&partnerID=8YFLogxK
UR - https://www.sciencedirect.com/science/article/pii/S0148296322008220?via%3Dihub
U2 - 10.1016/j.jbusres.2022.113357
DO - 10.1016/j.jbusres.2022.113357
M3 - Article
AN - SCOPUS:85140320702
SN - 0148-2963
VL - 154
JO - Journal of Business Research
JF - Journal of Business Research
M1 - 113357
ER -