University of Twente Student Theses
Optimizing the deployment of automated external defibrillators by a data-driven algorithmic approach
Nazarian, Arthur (2018) Optimizing the deployment of automated external defibrillators by a data-driven algorithmic approach.
This is the latest version of this item.
PDF
40MB |
Abstract: | Treating out-of-hospital cardiac arrests (OHCAs) is extremely challenging due to their unpredictability and urgency of intervention. However, the usage of public automated external defibrillators (AEDs) generally improves survival outcomes. With this research, we contribute to existing literature by proposing a comprehensive and efficient prescriptive optimization method that guides the deployment of AEDs that ultimately could improve survival rates. Our methodology accounts for the uncertainty of future cardiac arrest locations and incorporates the creation of candidate locations for AED placement. The latter enables controlling the granularity of possible AED locations and affects the solution quality. The proposed heuristic optimization methods comprise an efficient and effective Greedy heuristic and a more complex hybrid algorithm that is based on a combination of the Greedy Randomized Adaptive Search Procedure and Simulated Annealing with several extensions. We employ the proposed methodology to 43 municipalities in the Netherlands using real data from an established cardiac arrest registry. By relocating existing AEDs, we show that the average proportion of instances where an AED can be retrieved within the first critical 6 minutes can be improved from 47.2% to 68.5%. Using the more realistic decaying coverage function, the coverage of future cardiac arrests improves by 73.5%. |
Item Type: | Essay (Master) |
Clients: | Academisch Medisch Centrum, Amsterdam, Netherlands |
Faculty: | BMS: Behavioural, Management and Social Sciences |
Subject: | 30 exact sciences in general, 31 mathematics, 44 medicine, 50 technical science in general, 54 computer science |
Programme: | Industrial Engineering and Management MSc (60029) |
Link to this item: | https://purl.utwente.nl/essays/74410 |
Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Repository Staff Only: item control page