Ethical AI for Crisis Response: A Dynamic Policy Orchestrator for Prescriptive Resilience in Pharmaceutical Supply Chains

Jamal Musbah; Ibrahim Badi

doi:10.31181/sor202786

Authors

Jamal Musbah 1) School of Engineering and Applied Sciences, Libyan Academy, Misrata, Libya; 2) College of Technical Sciences, Bani Walid, Libya Author https://orcid.org/0009-0006-4914-4744
Ibrahim Badi School of Engineering and Applied Sciences, Libyan Academy, Misrata, Libya Author https://orcid.org/0000-0002-1193-1578

DOI:

https://doi.org/10.31181/sor202786

Keywords:

Adaptive Supply Chain, Machine Learning, Pharmaceutical Logistics, Risk Management, Humanitarian Operations, Ethical AI

Abstract

Pharmaceutical supply chains in volatile regions must balance cost efficiency with continuity of life-saving supplies under changing demand, fuel, and security conditions. This study develops a hybrid AI-driven Policy Orchestrator that adapts target inventory days, rationing limits, and delivery radius to the observed operating context. A simulation-based framework generated 1,000 Latin Hypercube Sampling (LHS) contexts, each evaluated under three candidate regimes, yielding 3,000 context–policy records and 1,000 optimal labels. A multi-output Random Forest model learned the mapping from context to policy parameters, achieving R² values of 0.93, 0.82, and 0.77 for target inventory days, rationing, and delivery radius, respectively. The orchestrator was evaluated over a 90-day steady-state horizon and three separate 20-day shock episodes. In steady state, mean total cost increased by 12.3%, while routing distance and stockout penalty decreased descriptively by 6.9% and 15.0%, respectively; neither reduction was statistically significant. During the Security Crisis, mean modeled danger-node traversals decreased from 40.75 to zero per replication, accompanied by a mean increase of 13,618.5 USD in stockout penalties per replication. During the Fuel Price Surge, the delivery radius contracted from 20.0 to 14.2 km. The findings support context-aware, safety-constrained decision support while highlighting key trade-offs and the need for field validation.

Downloads

Download data is not yet available.

References

Kovács, G., & Falagara Sigala, I. (2021). Lessons learned from humanitarian logistics to manage supply chain disruptions. Journal of Supply Chain Management, 57(1), 41–49. https://doi.org/10.1111/jscm.12253

Ivanov, D. (2020). Predicting the impacts of epidemic outbreaks on global supply chains: A simulation-based analysis on the coronavirus outbreak (COVID-19/SARS-CoV-2) case. Transportation Research Part E: Logistics and Transportation Review, 136, 101922. https://doi.org/10.1016/j.tre.2020.101922

Chopra, S., & Meindl, P. (2019). Supply chain management: Strategy, planning & operation. In Das Summa Summarum des Management: Die 25 wichtigsten Werke für Strategie, Führung und Veränderung (pp. 265–275). Springer. https://doi.org/10.1007/978-3-8349-9320-5_22

Zhu, G., Chou, M. C., & Tsai, C. W. (2020). Lessons learned from the COVID-19 pandemic exposing the shortcomings of current supply chain operations: A long-term prescriptive offering. Sustainability, 12(14), 5858. https://doi.org/10.3390/su12145858

Milewski, D. (2022). Managerial and economical aspects of the just-in-time system "lean management in the time of pandemic". Sustainability, 14(3), 1204. https://doi.org/10.3390/su14031204

Tomasini, R., & Van Wassenhove, L. (2009). Humanitarian logistics. Palgrave Macmillan. https://doi.org/10.1057/9780230233485

Jabbarzadeh, A., Fahimnia, B., & Seuring, S. (2014). Dynamic supply chain network design for the supply of blood in disasters: A robust model with real world application. Transportation Research Part E: Logistics and Transportation Review, 70, 225–244. https://doi.org/10.1016/j.tre.2014.06.003

Musbah, J., & Badi, I. (2026). Strategic selection of resilient pharmaceutical replenishment policies: A human-in-the-loop (HITL) Z-number SWOT-VIKOR framework. Science, Engineering and Technology, 6(S1), 38–55. https://doi.org/10.54327/set2026/v6.iS1.350

Christopher, M., & Peck, H. (2004). Building the resilient supply chain. International Journal of Logistics Management, 15(2), 1–14. https://doi.org/10.1108/09574090410700275

Snyder, L. V. (2006). Facility location under uncertainty: A review. IIE Transactions, 38(7), 547–564. https://doi.org/10.1080/07408170500216480

Ivanov, D., & Dolgui, A. (2020). Viability of intertwined supply networks: Extending the supply chain resilience angles towards survivability. A position paper motivated by COVID-19 outbreak. International Journal of Production Research, 58(10), 2904–2915. https://doi.org/10.1080/00207543.2020.1750727

Ivanov, D., & Dolgui, A. (2021). A digital supply chain twin for managing the disruption risks and resilience in the era of Industry 4.0. Production Planning & Control, 32(9), 775–788. https://doi.org/10.1080/09537287.2020.1768450

Musbah, J., Badi, I., & Pamucar, D. (2026). Dynamic replenishment policies for vendor-managed inventory under stochastic demand: A simulation-based comparative study. Acta Technica Jaurinensis, 19(3), 195–205. https://doi.org/10.14513/actatechjaur.00960

Lepenioti, K., Bousdekis, A., Apostolou, D., & Mentzas, G. (2020). Prescriptive analytics: Literature review and research challenges. International Journal of Information Management, 50, 57–70. https://doi.org/10.1016/j.ijinfomgt.2019.04.003

Guan, Q., Cao, H., Jia, L., Yan, D., & Chen, B. (2025). Synergetic attention-driven transformer: A deep reinforcement learning approach for vehicle routing problems. Expert Systems with Applications, 274, 126961. https://doi.org/10.1016/j.eswa.2025.126961

Oroojlooyjadid, A., Nazari, M., Snyder, L. V., & Takáč, M. (2022). A deep Q-network for the beer game: Deep reinforcement learning for inventory optimization. Manufacturing & Service Operations Management, 24(1), 285–304. https://doi.org/10.1287/msom.2020.0939

Musbah, J., Badi, I., & Bouraima, M. B. (2025). Optimizing time-based heuristics for resilient VMI replenishment: A simulation-optimization approach. Journal of Industrial Intelligence, 3(2). https://doi.org/10.56578/jii030204

Thejasree, P., Manikandan, N., Vimal, K. E. K., Sivakumar, K., & Krishnamachary, P. C. (2024). Applications of machine learning in supply chain management—A review. In K. E. K. Vimal, S. Rajak, V. Kumar, R. S. Mor, & A. Assayed (Eds.), Industry 4.0 Technologies: Sustainable Manufacturing Supply Chains: Volume 1—Theory, Challenges, and Opportunity (pp. 73–82). Springer. https://doi.org/10.1007/978-981-99-4819-2_6

Govindan, K., Mina, H., & Alavi, B. (2020). A decision support system for demand management in healthcare supply chains considering the epidemic outbreaks: A case study of coronavirus disease 2019 (COVID-19). Transportation Research Part E: Logistics and Transportation Review, 138, 101967. https://doi.org/10.1016/j.tre.2020.101967

Holguín-Veras, J., Pérez, N., Jaller, M., Van Wassenhove, L. N., & Aros-Vera, F. (2013). On the appropriate objective function for post-disaster humanitarian logistics models. Journal of Operations Management, 31(5), 262–280. https://doi.org/10.1016/j.jom.2013.06.002

Friday, D., Savage, D. A., Melnyk, S. A., Harrison, N., Ryan, S., & Wechtler, H. (2021). A collaborative approach to maintaining optimal inventory and mitigating stockout risks during a pandemic: Capabilities for enabling health-care supply chain resilience. Journal of Humanitarian Logistics and Supply Chain Management, 11(2), 248–271. https://doi.org/10.1108/JHLSCM-07-2020-0061

Musbah, J., & Badi, I. (2026). LLM-assisted virtual expert weight elicitation in pharmaceutical supply chains: A Z-number multi-agent framework. Intelligent Systems Research and Applications Journal, 2, 27–39. https://doi.org/10.59543/mmhqdg22