Can AI Help Predict Drug Shortages?

In 2021, while working as a pharmacist intern on call in the accident and emergency unit of a federal teaching hospital in southeastern Nigeria, I encountered a drug shortage that has stayed with me. A patient with severe preeclampsia needed magnesium sulfate, but the hospital did not have it in stock, and nearby pharmacies were closed. Despite the team’s efforts, we could not provide the medication. As a result, the patient died.

That experience left me with a question I still think about: Could we have identified the supply gap before the patient needed the drug?

Drug shortages look different in the United States. Pharmacy shelves may not be visibly empty, but pharmacy teams absorb disruptions through therapeutic substitutions, compounding, delayed procedures, emergency purchasing, and hours spent contacting wholesalers.

The problem remains substantial. The American Society of Health-System Pharmacists (ASHP) reported 227 active drug shortages at the end of the second quarter of 2026, up for the third consecutive quarter but below the record of 323 in the first quarter of 2024.¹ A 2025 Vizient survey reported that US hospitals spent approximately 20 million hours managing drug shortages in 2023, equivalent to nearly $900 million in annual labor costs.² These figures capture only part of the burden. Shortages can also complicate treatment decisions, disrupt medication selection, and delay care.

Testing What Public Data Can Tell Us

As a pharmacist and MBA candidate studying health care, operations, and business analytics, I examined whether publicly available information could help distinguish drugs associated with shortages from those not listed as being in shortage.

I assembled a dataset covering approximately 3,000 prescription drugs using US FDA drug listings and recall records, alongside shortage information from FDA and ASHP sources. For each drug, I recorded characteristics including dosage form, injectable or oral status, the number of approved products, brand or generic status, controlled-substance status, and how recently a new product had entered the market.

Then, I compared models designed to distinguish drugs appearing on shortage lists from those that did not. A fuller technical report is in preparation.

The initial findings suggested that these characteristics contained some useful information about shortage-list status. However, the signal was modest, and the analysis does not establish whether the models can reliably identify drugs that will enter shortage in the future. Identifying characteristics associated with listed shortages is not the same as forecasting when a new shortage will begin.

Some of the strongest risk signals were familiar to pharmacy professionals. Sterile injectables, controlled substances, and long-established drugs with multiple approved products featured prominently among higher-risk drugs. A relatively simple scoring rule based on these characteristics captured much of the signal identified by more complex models.

In this initial analysis, adding machine learning did not appear to deliver a substantial improvement over a simpler approach. Recall history, which I had expected to be informative, also contributed little.

These findings raise an important question about artificial intelligence (AI): Does a more sophisticated model necessarily produce a better operational decision? In some cases, identifying useful signals and presenting them clearly may matter more than algorithmic complexity.

The Missing Piece is Hospital-Level Data

Two lessons emerge from this work. First, public data can help identify where shortage risk may be concentrated, but it offers a limited view of how a supply disruption will affect an individual hospital. That depends on factors such as medication utilization, on-hand inventory, supplier lead times, purchasing concentration, and the availability of clinically appropriate alternatives.

A medication associated with national shortage risk may not pose an immediate problem for a hospital with sufficient inventory and alternative suppliers. Conversely, a drug with limited warning signals could become urgent for a hospital with high utilization and little stock on hand.

Second, hospitals may be able to make better use of data they already possess. Imagine a weekly dashboard identifying the 10 medications that deserve closer attention. It could combine public shortage-risk indicators with internal consumption patterns, inventory levels, supplier delivery performance, and purchasing concentration. Pharmacy teams could use it to review stock levels, contact suppliers, evaluate alternatives, and prioritize contingency planning.

Such a tool would not eliminate shortages or replace pharmacists' judgment. Its value would lie in helping teams decide where to investigate before a supply problem becomes a clinical emergency.

Three Steps Toward More Useful Shortage Intelligence:

1. Enable responsible data sharing. Deidentified, appropriately governed purchasing, utilization, inventory, and supplier-performance data could help researchers test whether public risk indicators produce useful hospital-level warnings.
2. Integrate shortage risk into routine pharmacy management. Pilot projects should measure whether such tools improve warning time or reduce emergency purchasing, not merely whether their classifications appear accurate.
3. Be transparent about limitations. Developers should distinguish between identifying drugs associated with shortages and forecasting future ones, and report how models were validated and where they perform poorly. A confident forecast that fails when a medication is needed is not a substitute for a resilient supply chain.

I cannot say whether anyone could have foreseen the supply gap that night in 2021. I do believe that better use of data could help more hospitals recognize vulnerabilities earlier and prepare more effectively. AI may have a role in that effort, but it is not the starting point. The starting point is better information, connected to the decisions pharmacy teams make every day.

REFERENCES

1. American Society of Health-System Pharmacists. Drug Shortages Statistics. National Drug Shortages: January 2001 to June 2026. Accessed October 11, 2026. https://www.ashp.org/drug-shortages/shortage-resources/drug-shortages-statistics

2. New Vizient survey finds drug shortages cost hospitals nearly $900M annually in labor expenses. News release. Vizient, Inc. June 17, 2025. Accessed October 11, 2026. https://www.vizient.com/newsroom/news-releases/new-vizient-survey-finds-drug-shortages-cost-hospitals-nearly-900m-annually-in-labor-expenses