Decision support tools for next-generation vaccines and advanced therapy medicinal products: present and future

Sarkis, Miriam; Bernardi, Andrea; Shah, Nilay; Papathanasiou, Maria M.

doi:10.1016/j.coche.2021.100689

Cited by 11 publications

(8 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of methods for efficient production scheduling of batch processes is an area of significant interest within the domain of process systems engineering and operations research [1,2]. There are three main drivers for research within online production scheduling: a) identifying modelling approaches that integrate with the practicalities of online scheduling, b) considering plant uncertainties, and c) handling nonlinearities [3].…”

Section: Online Production Scheduling: Optimization and Simulationmentioning

confidence: 99%

Distributional Reinforcement Learning for Scheduling of Chemical Production Processes

Mowbray¹,

Zhang²,

Chanona³

2022

Preprint

View full text Add to dashboard Cite

Reinforcement Learning (RL) has recently received significant attention from the process systems engineering and control communities. Recent works have investigated the application of RL to identify optimal scheduling decision in the presence of uncertainty. In this work, we present a RL methodology tailored to efficiently address production scheduling problems in the presence of uncertainty. We consider commonly imposed restrictions on these problems such as precedence and disjunctive constraints which are not naturally considered by RL in other contexts. Additionally, this work naturally enables the optimization of risk-sensitive formulations such as the conditional value-at-risk (CVaR), which are essential in realistic scheduling processes. The proposed strategy is investigated thoroughly in a parallel batch production environment, and benchmarked against mixed integer linear programming (MILP) strategies. We show that the policy identified by our approach is able to account for plant uncertainties in online decision-making, with expected performance comparable to existing MILP methods. Additionally, the framework gains the benefits of optimizing for risk-sensitive measures, and identifies online decisions orders of magnitude faster than the most efficient optimization approaches. This promises to mitigate practical issues and ease in handling realizations of process uncertainty in the paradigm of online production scheduling.

show abstract

Section: Online Production Scheduling: Optimization and Simulationmentioning

confidence: 99%

Distributional Reinforcement Learning for Scheduling of Chemical Production Processes

Mowbray¹,

Zhang²,

Chanona³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Sarkis et al (2021) explore mathematical models that can be used as tools to account for the unprecedented demand shock in nanomedicine manufacturing, due to both novel vaccine platforms (e.g., vector-based and RNA-based for SARS-CoV-2 vaccines) and Advanced Therapy Medicinal Products (ATMPs) manufacturing success [ 19 • ]. The authors find that different vaccine platforms and other emerging nanomedicines will face bottlenecks at varying stages of the value chain, concluding in the wide spread need for decision-support tools that inform operational planning and strategies in order to account for this uncertainty [ 19 • ]. The authors describe Mixed Integer Linear Programming (MILP) as a method for planning supply chain network structures that meet multiple objectives, including being patient-centric and cost-efficient, but do not ultimately discuss the network structures and resilience [ 19 • ].…”

Section: Review: Nano Supply Chains and Resiliencementioning

confidence: 99%

“…The authors find that different vaccine platforms and other emerging nanomedicines will face bottlenecks at varying stages of the value chain, concluding in the wide spread need for decision-support tools that inform operational planning and strategies in order to account for this uncertainty [ 19 • ]. The authors describe Mixed Integer Linear Programming (MILP) as a method for planning supply chain network structures that meet multiple objectives, including being patient-centric and cost-efficient, but do not ultimately discuss the network structures and resilience [ 19 • ].…”

Section: Review: Nano Supply Chains and Resiliencementioning

confidence: 99%

“…Perhaps due to the governance issues and wide application capabilities of nanotechnology, many of the publications on nano supply chain resilience enumerate a variety of disruptions to the interconnected global supply chains, including policy changes, economic stresses, natural disasters [ 18 ], computer security [ 21 ], political stressors [ 16 ], uncertainty in demand and supply [ 19 • ] targeted reverse engineering attack [ 22 ], and future pandemics [ 15 • ]. Despite acknowledgement of the chaos these disruptions cause on supply chains and the need to drive forward supply chain resilience, only two of these publications draw on efficiency-driven or lean supply chains as the foil for resilience [ 15 • , 16 ].…”

Section: Review: Nano Supply Chains and Resiliencementioning

confidence: 99%

“…Common areas to consider in creating a wholistic framework applicable to the rapid pace of nanotechnology development and to the ensuing regulatory requirements include knowledge sharing and transparency in nanotechnology research and development [ 28 • ], stakeholder awareness and participation [ 29 ], acknowledgement of the pacing problem [ 30 ], implementation of sustainability impact assessments [ 31 ], and bioavailability [ 32 ]. Some systems, such as Quality by Design (QbD) [ 19 • ] and the OECD’s Safe(r) Innovation Approach for implementing safety-by-design [ 33 ] in nanotechnology applications have been outlined but have yet to be implemented. Other advanced decision-making frameworks such as multi-criteria decision analysis (MCDA) have proven useful for safely and effectively researching and developing emerging technologies in nanomedicine [ 34 ].…”

Section: Moving Forward: Operationalizing Resiliencementioning

confidence: 99%

See 2 more Smart Citations