Transforming Clinical Trials Supply Chain Management with Sustainability
Randomized clinical studies are notoriously unpredictable, with constant changes in patient recruitment, randomization, retention, and dosing impacting medicine supply. These fluctuations often lead to significant medicine waste, historically as high as 70% across biopharmaceutical companies. Reducing this waste is crucial for several reasons:
- Environmental Sustainability: Minimizing the quantity of medicines packaged, transported, and stored helps reduce our environmental footprint.
- Ethical Responsibility: Reducing the use of high-value, low-volume medicines as comparators or rescue medications allows these resources to be redirected to other clinical studies.
- Cost Efficiency: Lowering the cost of supplying medicines to clinical studies enables reinvestment in the development of new, potentially lifesaving treatments.
Traditional supply chain tools used for designing, planning, and managing clinical studies lack predictive capabilities and rely heavily on users’ experience. Advanced Analytics, Optimization, and Machine Learning (AAOML) tools offer a transformative approach to predicting key parameters and reducing medicine waste.
Implementation and Action
Our team at MOAT Digital Life Science has successfully implemented a commercially available AAOML modelling tool to significantly cut down medicine waste. Through collaborative project management and resource augmentation, with subject matter experts at the top of their field in clinical trials supply chain, we initially focused on study design across eleven high-cost programs. By working closely with each clinical project team, we identified key study design parameters (e.g., country selection, visit window) that could impact medicine waste and cost. Using the AAOML tool, we conducted mathematical simulations to optimize these parameters, resulting in the most efficient and cost-effective study designs.
Historically, patient retention, particularly in oncology, has been inaccurately assessed, leading to increased waste. Data Science and AI advancements have enhanced the accuracy of AAOML simulations, developing a reliable retention forecasting tool.
Outcomes and Benefits
The project has demonstrated substantial benefits, underscoring the value of AAOML in clinical design:
- Waste Reduction: We have achieved a dramatic reduction in planned clinical supply design waste targets, from over 50% historically to approximately 20%. This reduction has decreased shipments, lessened the demand for competitor comparator and rescue medicines, and generated significant savings in trial budgets and cost avoidance.
- Capability Building: The use of AAOML tools has fostered new capabilities within our Supply Chain Management organization. Collaborating with product vendors has led to industry-leading, benchmarked study designs and optimized workflows. Additionally, the creation of consistent business processes and training programs has empowered our supply chain team to influence study design more effectively than ever before.
Key Success Factors
Three critical behaviours have driven the success:
- Scientific Leadership: Implementing AAOML in clinical supply chain design required a cultural shift and capability enhancement. The team effectively educated and demonstrated the benefits to initially sceptical stakeholders, using scientific evidence and success stories to prove the tool’s value.
- Study Collaboration: Traditionally, supply chain design followed scientific and operational study design. By integrating AAOML, we have made supply chain design an inherent part of the overall study design process. This collaborative approach has optimized study parameters, reducing waste and costs.
- Technical Collaboration: Our Data Sciences and AI teams worked closely with Supply Chain and product vendors to enhance the key inputs for the AAOML modelling tool.
- MOAT’s Project Management, Resource Augmentation & Change Management, allowing BAU activities to be achieved with minimal impact to the business and upskilling of the team for a successful implementation.
Conclusion
Historically, medicine waste has been a significant issue in the biopharmaceutical industry. By leveraging AAOML tools, we have minimized waste, reduced our environmental impact, and enhanced ethical responsibility. This innovative approach has not only generated substantial cost savings but also built new capabilities for future supply chain management, ensuring optimal study designs moving forward.