Pharmaceutical companies will leverage machine learning to prevent drug shortages.

2019-10-15

Currently, German pharmaceutical company Merck needs to stockpile drugs to ensure an adequate supply, which means some of the drugs will expire before use. They are planning to use machine learning technology to prevent drug shortages, with Merck stating that their supply and demand forecasting currently has an accuracy of about 85%.


To enhance their forecasting, the company's healthcare division plans to start testing a cloud-based software platform later this year. The platform, manufactured by TraceLink Inc. based in Massachusetts, can analyze real-time data points from various organizations within Merck's supply chain, including pharmacies, hospitals, and wholesale distributors.


TraceLink is currently developing machine learning algorithms for use in the trials, starting with immune oncology drugs aimed at enhancing the body's immune system to fight cancer. Alessandro DeLuca, Head of Merck's Healthcare Division, said, "We hope this product can make a difference in the pharmaceutical field."According to data from the University of Utah, there were approximately 150 to 300 cases of drug shortages in the US per quarter between 2014 and 2019. Commonly scarce drugs due to manufacturing, inadequate supply forecasting, and natural disasters include antibiotics, chemotherapy drugs, and cardiovascular treatments.


Analysts say that more accurate supply and demand forecasting means pharmaceutical companies can save hundreds of millions of dollars each year, as they do not need to produce excess drugs and reduce transportation costs.


According to research and consulting firm Gartner Inc., the average inventory time for pharmaceutical companies is 156 days. For retailers selling consumer goods, it is 78 days. For IT equipment such as printers, servers, and PC components, it is 57 days.


Generally, pharmaceutical companies predict drug demand based on historical data and sales team performance. In recent years, they have had access to more data about drugs in their supply chain due to a US law mandating manufacturers to add serial numbers to drugs.


Drug manufacturers can use TraceLink's software to generate such serial numbers, but the platform can also serve as a central hub for obtaining information about the status of drugs at various stages of the supply chain.TraceLink's network consists of data from over 275,000 organizations worldwide, including hospitals, retail pharmacies, wholesale distributors, and pharmaceutical companies. The system operates with data from over 6 billion serialized drugs. In addition to Merck, TraceLink's clients include Amgen, Sterling Pharmaceuticals, and Sunrise Pharmaceutical Co., Ltd.


To provide customers with more accurate information about supply and demand, TraceLink is developing machine learning algorithms to analyze information within its network without violating data privacy laws.


Stephen Meyer, Senior Director and Supply Chain Analyst specializing in the life sciences industry at Gartner, said, "In the past decade, pharmaceutical companies have faced competition from competitors, generics, and other areas. At the same time, investors are putting pressure on them to increase profits, release cash flow, and provide funding for product development and acquisitions. As a result, many are exploring ways to reduce supply chain costs."


Pepe Rodriguez, Managing Director and Partner at Boston Consulting Group, said, "Better supply and demand forecasting also makes it easier for Merck to expand into regions without reliable supply chain infrastructure, such as parts of Africa and Southeast Asia. The operations and supply chain of pharmaceutical companies."

RECENT AI NEWS

RECENT AI TOOLS