As the U.S. healthcare system faces near-unprecedented shortages of hundreds of medicines and cancer treatments, pharmaceutical manufacturers are facing increasing pressure to maximize productivity and reliability of supply.
Every pharmaceutical product begins with a series of supply chain inputs that are assembled at the manufacturing plant and then released to market. Applying Internet of Things (IoT) technology, data analytics, and artificial intelligence (AI) in combination with lean manufacturing techniques to these processes can help manufacturers improve their operations and make better use of existing raw materials.
These solutions also help pharmaceutical companies and other medical device manufacturers continuously optimize their supply chain management and manufacturing processes to achieve long-term efficiency and quality improvements.
Factory data for smarter supply chain forecasting
Accurately forecasting supply chain needs is a classic challenge for manufacturers, especially in the pharmaceutical industry. Market conditions, emerging diseases, new treatments, and seasonal demand differences all complicate forecasting how much of a particular product to produce and what inputs are required. For example, if demand for a routine medication is constant, predicting supply chain needs is easy. But for new drugs or seasonal vaccines, sourcing the right amounts of raw materials can be more difficult.
Accurate historical data and real-time demand inputs facilitate more accurate forecasting, especially when demand for a particular product fluctuates greatly. Touchless Forecasting uses advanced analytics based on this data to identify clearer predictive signals. This data is collected from a combination of historical records, installed ERP and historian systems, and IoT sensors with associated analytical tools. This data provides real-time information on product execution, quality defects, and trends in numerous parameters that are essential for accurate forecasting.
Making this data available for analysis and prediction is not always easy. But building something called a “data fabric” can help. A data fabric makes integrated data from ERP and other sources available in a clean, easy-to-use platform that can be used for analysis and prediction. More accurate forecasts lead to more accurate supply chain planning and prevent shortages due to forecast errors. Better forecasts also lead to better resource allocation within the smart factory after raw materials arrive.
Making factories smarter with IoT-generated data
The foundation of a smart factory is IoT sensors that track equipment functionality, employee locations, and other key aspects of the production process. IoT sensor data can inform several smart practices, including the ability to track factory functioning in real time. Managers can monitor activity on the factory floor and, rather than reacting when they see or hear something unusual, they can monitor the data and integrate it into their daily sessions to resolve issues faster.
For example, if data shows that equipment is starting to fail, managers can immediately call for service and begin setting up another production line to minimize interruptions.
Over time, as IoT systems collect more data, they can perform historical analysis to identify long-term trends, such as maintenance intervals for specific equipment. These insights enable proactive predictive maintenance (PdM) that avoids unplanned downtime due to equipment failure and reduces the costs associated with unnecessary interval-based maintenance. Maintenance can be scheduled between production runs to minimize disruptions. PdM also helps manufacturers optimize yields by reducing the number and size of batches lost due to unplanned downtime, an important consideration for products that use raw materials that are hard to obtain.
Another way to leverage historical factory data is to create a digital twin that simulates the operations of a specific piece of equipment, a production line, or an entire factory. Digital twins allow manufacturing engineers and planners to find new ways to try and optimize different elements of the production process without interrupting actual production or risking hard-to-obtain inputs.
Improving product quality for patients and healthcare providers
Internal and external data can also help pharmaceutical manufacturers improve product quality and enhance patient and healthcare provider experience. This can improve quality of life for patients relying on new drugs or experimental treatment plans by eliminating costly cycles of research and rework and reducing the chances that defects will go undetected. For example, patients receiving a new cancer treatment that has received special FDA approval may have little (or no) data about potential side effects. If a patient reports a side effect, that data can be quickly analyzed and matched against smart factory data to identify areas where the product can be improved to reduce side effects in the future.
Higher quality products also make healthcare workers’ jobs easier. For example, healthcare workers administering injectable biological cancer treatments need to be sanitized, gowned, and gloved before administering the drug to a patient. At that point, if the product’s packaging is difficult to open, it can create “fit, feel, and finish” issues, frustrating healthcare workers and wasting time. Product feedback data can help manufacturers make quick adjustments to eliminate packaging issues and make it easier to use.
Start your smart supply chain and manufacturing journey
Laying the foundation for smart factories and supply chain technology requires three steps.
The first step is to understand the current state of the factory and imagine what it would look like with real-time and historical data to support the analysis. This step is important because most supply chains and factory floors evolved long before today’s smart technologies, and integrating the two requires conscious brainstorming. A thorough “as is” and “to be” also allows manufacturers to document baseline performance and set reasonable goals for improvement.
Armed with a vision of what is possible in terms of optimization and forecasting, the second step is to identify use cases and priorities to achieve pre-determined goals, which might include increasing on-time and complete delivery rates, optimizing batch yields, improving supply chain forecast accuracy, etc.
Once the use case has been identified, the third preparatory step is to identify the resources required for that use case. At this stage, you audit your IT/OT (operational technology) environment to determine the number and type of IoT devices, data growth, improved access and analytics through a data fabric, or a combination of these resources required for the use case. This is also the stage where you start to develop the business case in terms of investment, financial and non-financial benefits, and return on investment.
Once goals are developed and use cases are identified, alignment with talent at different levels of the organization is critical. Leaders must be able to communicate a unified and aligned vision of the goals, and employees must understand the impact on their roles and responsibilities. Involving talent early on will accelerate adoption of new tools and processes, leading to talent success.
Investing in and implementing smart sourcing and manufacturing solutions will not quickly and completely solve today’s drug and medical device shortages, but it can help manufacturers bring more product to market and reduce the risk of future shortages, while also reducing costs and improving product quality.
Sheetal Chawla is head of life sciences and regional head for Northeast at Capgemini Americas, while Brian Eden is vice president of global life sciences at Capgemini Group.
