Can AI Be the Cure for Drug Shortages?
A promising path forward exists by integrating AI-based tools into healthcare systems.
AI in healthcare

Drug shortages are becoming a pervasive global issue.  In the United States alone, there were 309 active drug shortages at the end of the second quarter of 2023 — the most in nearly a decade and close to the all-time high of 320 shortages, according to a report by the American Society of Health-System Pharmacists. Causes of these shortages are varied and complex, ranging from manufacturing and quality issues to unexpected demand surges, posing significant risks to public health. However, the responsible use of evolving technology, especially Artificial Intelligence (AI), can be a valuable asset in addressing the drug shortage crisis. The National Artificial Intelligence Act of 2020 defines AI as “a machine-based system that can, for a given set of human-defined objectives, make predictions, recommendations or decisions influencing real or virtual environments. Here are a few ways in which healthcare systems can utilize AI-driven approaches to mitigate the impact of drug shortages.

AI-Driven Forecasting and Inventory Management: One of the most significant ways AI can combat drug shortages lies in its ability to forecast shortages before they occur. Conventional methods of demand forecasting rely on manual analysis and decision making and often fall short in capturing dynamic factors influencing supply and demand. In contrast, AI algorithms swiftly analyze diverse data sources such as historical shortage data, production capacity, regulatory trends, and market dynamics, achieving high accuracy in predicting potential shortages. By capitalizing on these predictions, healthcare systems can take proactive measures to mitigate shortages, such as increasing production capacity or securing alternative suppliers. Furthermore, AI-powered epidemiological models can forecast changes in disease prevalence and treatment demand, enabling healthcare systems to anticipate shifts in medication requirements and adjust procurement strategies accordingly.

Supply Chain Optimization: Pharmaceutical supply chains are complex and are notoriously susceptible to disruptions. However, AI’s data analysis prowess holds promise in optimizing the pharmaceutical supply network. Through predictive analytics and machine learning algorithms, AI can identify vulnerabilities in the supply chain, anticipate disruptions, and recommend strategic interventions to minimize risks, preventing shortages from happening in the first place.

Production Optimization/Quality Control: Manufacturing quality issues and production inefficiencies are major reasons for drug shortages. AI can enhance production processes within pharmaceutical manufacturing facilities, minimizing drug shortages. By analyzing production data in real-time, AI can identify inefficiencies, optimize manufacturing workflows, and reduce waste. Furthermore, AI-driven quality control systems can enhance the reliability and safety of pharmaceutical products by detecting defects, anomalies, or deviations from specifications in real-time, minimizing the likelihood of production delays due to regulatory compliance issues.

Alternative Therapies/Enhanced Clinical Decision Support: AI can support clinical decision-making in managing drug shortages. Though still in its early stages, AI-driven clinical decision support systems (CDSS) can analyze patient data, treatment guidelines, and drug availability information to recommend alternative therapies or dosing regimens when preferred medications are unavailable. By integrating clinical expertise with real-time data analytics, AI-driven CDSS can empower healthcare providers to navigate complex treatment scenarios and optimize patient outcomes amidst drug shortages.

Overall, AI presents a promising path forward in addressing the persistent issue of drug shortages. By integrating AI-based tools, healthcare systems can not only predict and prevent shortages but also optimize supply chains, streamline production, and support informed clinical decision-making. While challenges remain, responsible implementation can ensure that AI’s potential in tackling drug shortages is fully realized, achieving better patient outcomes and improving the global public health. 


Abu Zwaida, Tarek, Chuan Pham, and Yvan Beauregard. "Optimization of inventory management to prevent drug shortages in the hospital supply chain." Applied Sciences 11.6 (2021): 2726.

Pall, Raman, et al. "Predicting drug shortages using pharmacy data and machine learning." Health Care Management Science (2023): 1-17.

Pal, Subharun. "Advancements in AI-Enhanced Just-In-Time Inventory: Elevating Demand Forecasting Accuracy." International Journal for Research in Applied Science & Engineering Technology 11 (2023): 282-289.

Richey Jr, Robert Glenn, et al. "Artificial intelligence in logistics and supply chain management: A primer and roadmap for research." Journal of Business Logistics 44.4 (2023): 532-549.

Shoushtari, Farzaneh, Ehsan Ghafourian, and Mohammadamin Talebi. "Improving Performance of Supply Chain by Applying Artificial Intelligence." International journal of industrial engineering and operational research 3.1 (2021): 14-23.

Tarumi, Shinji et al. “Leveraging Artificial Intelligence to Improve Chronic Disease Care: Methods and Application to Pharmacotherapy Decision Support for Type-2 Diabetes Mellitus.” Methods of information in medicine vol. 60,S 01 (2021): e32-e43. doi:10.1055/s-0041-1728757

U.S. Food and Drug Administration. "Frequently Asked Questions about Drug Shortages." FDA, of Form