Drug shortages are a global issue. Between 2014 and 2019, the U.S. had roughly 150 to 300 drug shortages every quarter. Shortages can happen due to issues with manufacturing, supply-and-demand forecasts or natural disasters. Other shortages are simply outside a drugmakers control.

By enabling more precise supply-and-demand forecasts, patients will have access to the drugs they need, exactly when they are needed. It would also allow pharmaceutical companies to save hundreds of millions of dollars annually by reducing wasted drugs and avoiding costs related to expedited shipments. Currently, suppliers tend to stockpile medications to ensure customer supply and as a result, some of this stock expires before they can be used. “Over the past decade, pharmaceutical companies have been facing steep competition from rival brands, generics and biosimilars,” says Stephen Meyer, a senior director and supply-chain analyst at Gartner specialising in the life-sciences industry. Pharmaceutical companies have traditionally predicted demand for drugs based on historical sales yet harnessing this data using machine learning could make predictions far more accurate. German pharmaceuticals company Merck, for example, recently announced plans to use analytics and machine learning to predict and prevent drug shortages. 

 

Whilst Merck believes its supply-and-demand forecasts are 85% accurate today, the company’s health-care division plans to start testing a cloud-based software platform later this year to improve this figure, saving on costs and improving customer service. Legislation is supporting this shift. For example, a 2013 U.S. regulation forced manufacturers to add serial numbers to medications, in part to reduce counterfeit drugs and produce more accurate data all along the supply chain. Now these serial numbers have been added to all stock, Merck worked with TraceLink Inc., the world’s leading life science cloud service provider, to create a platform that can analyse data points from various organisations within Merck’s supply chain in real time – from pharmacies, hospitals to wholesale distributors to improve efficiency. TraceLink’s software generates the mandatory serial numbers and then acts as a central hub for information about the status of drugs at every phase in the supply chain to give clients more accurate information through machine-learning-based algorithms that analyse information in its network without violating data-privacy laws. The first of these machine-learning algorithms were used in the Merck pilot study of the platform into the supply chain of immuno-oncology drugs. 

 

The algorithms give Merck signals about the days of inventory for a specific drug and how long it will take for a drug to get to a particular phase in the supply chain allowing them to better plan resources and logistics. Alessandro DeLuca, chief information officer for Merck’s health-care division said: “The value of this platform is that every single patient will receive the drug that he or she needs at the right moment”, adding that the move could significantly cut drug shortages. Shabbir Dahod, TraceLink’s chief executive added: “As many as 10 entities handle a drug before it gets to a patient, including manufacturers, pharmacies and wholesale distributors. It’s a highly complex supply chain.” Therefore, by including data from more than 275,000 organisations world-wide, including hospitals, retail pharmacies, wholesale distributors and drugmakers, the TraceLink network simplifies the tracking system through its access to more than six billion serial-numbered drugs. Improving the accuracy of drug demand and supply levels, and enabling reliable forecasting, allows life science organisations, such as Merck, to expand into locations that are not able to provide reliable supply-chain infrastructure, such as parts of Africa and Southeast Asia. Improving digital management of supply chains means that “a lot of growth from pharma companies is coming from emerging markets where the logistics are challenging,” said Pepe Rodriguez, managing director and partner at Boston Consulting Group who specialises in operations and supply chains in pharmaceutical companies. 

 

In allowing a safe and legitimate way of managing drug supply chains, the populations of these countries that were previously prevented from receiving life-saving treatment will now be able to access it. Drug shortages are a major challenge for the health sector. While many life science sector companies are considering creating their own manufacturing operation to produce drugs that are in chronic shortage, Merck is championing a new, digital approach that could change the face of drug supply forever. Machine learning is transforming organisations and industries around the world. As well as supply chain predictions, pharmaceutical companies also use it for clinical trial analysis, and to predict peak demand for electricity. Retailers use it to assess buying patterns so they can figure out what sizes to stock and in the financial sector, banks also are using neural networks to detect credit card fraud and to prevent money laundering. This emerging technology is only in its infancy, but its potential in the pharmaceutical supply industry holds no bounds.