We study inventory control policies for pharmaceutical supply chains, addressing challenges such as perishability, yield uncertainty, and non-stationary demand, combined with batching constraints, lead times, and lost sales. Collaborating with Bristol-Myers Squibb (BMS), we develop a realistic case study incorporating these factors and benchmark three policies--order-up-to (OUT), projected inventory level (PIL), and deep reinforcement learning (DRL) using the proximal policy optimization (PPO) algorithm--against a BMS baseline based on human expertise. We derive and validate bounds-based procedures for optimizing OUT and PIL policy parameters and propose a methodology for estimating projected inventory levels, which are also integrated into the DRL policy with demand forecasts to improve decision-making under non-stationarity. Compared to a human-driven policy, which avoids lost sales through higher holding costs, all three implemented policies achieve lower average costs but exhibit greater cost variability. While PIL demonstrates robust and consistent performance, OUT struggles under high lost sales costs, and PPO excels in complex and variable scenarios but requires significant computational effort. The findings suggest that while DRL shows potential, it does not outperform classical policies in all numerical experiments, highlighting 1) the need to integrate diverse policies to manage pharmaceutical challenges effectively, based on the current state-of-the-art, and 2) that practical problems in this domain seem to lack a single policy class that yields universally acceptable performance.

Any overreliance on foreign inputs in drug supply chains could leave the U.S. open to dire shortages in the event of conflict or natural catastrophe. The White House has flagged the potential disruption of the pharmaceutical supply chain as a national-security issue, saying these drugs are essential to the health and prosperity of the country. "The ever-changing threat environment, both natural and man-made, gives rise to numerous unforeseen challenges, such as to the pharmaceutical supply chain," said Jennifer Foley, a deputy director in DHS's science and technology directorate. Quantifind Inc., a company that normally does risk screening for financial institutions, will do the work, looking into supply chains for the Cross-Border Threat Screening and Supply Chain Defense Center of Excellence, a government-backed research center connected with Texas A&M University. Our Morning Risk Report features insights and news on governance, risk and compliance.

New technologies like 5G and edge computing are making healthcare more connected, secure, and efficient. When healthcare practitioners must make life-or-death decisions, the quality of information at their disposal is critical. Having more specific data -- and being able to access it in real time -- leads to more informed decisions. The Internet of Medical Things (IoMT) makes this possible through an infrastructure of connected medical devices, software applications, and health systems powered by 5G wireless technology and edge computing, which enables connected devices to process data closer to where it is created. Global healthcare funding to private companies reached a new quarterly record of $18.1B in Q2'20. Get the report to learn more.

Artificial intelligence (AI) will transform the pharmaceutical cold chain -- not in the distant, hypothetical future, but in the next few years. As the president of a company that has been actively involved in the creation of an application that will utilize machine learning to generate predictive data on environmental hazards in the biopharmaceutical cold chain cycle, I've seen firsthand the promise of this technology. When coupled with machine learning and predictive analytics, the AI transformation goes much deeper than smarter search functions. It holds the potential to address some of the biggest challenges in pharmaceutical cold chain management. By aggregating and analyzing data from multiple sources -- a drug order and weather data along a delivery route, for example -- AI-based systems can provide complete visibility with predictive data throughout the cold chain.

Safety stock is among the most critical elements in the pharmaceutical supply chain. Yet safety stock has also proven very difficult to manage and optimize, even as it locks down working capital and drives up inventory costs. Pharmaceutical companies typically maintain high levels of safety stock to achieve better service levels that maximize revenue of high-margin products and drive customer satisfaction. Also called buffer stock, it provides a safety net against variability such as unanticipated delays in raw materials or transportation, or unusually high demand. Stockouts that result from inadequate safety stock could be highly damaging to the business, with millions in lost revenue and potential brand damage if vital medicines are unavailable.