RESUMEN
Background and purpose: Mobile stroke units (MSU) have been demonstrated to improve prehospital stroke care in metropolitan and rural regions. Due to geographical, social and structural idiosyncrasies of the German city of Mannheim, concepts of established MSU services are not directly applicable to the Mannheim initiative. The aim of the present analysis was to identify major determinants that need to be considered when initially setting up a local MSU service. Methods: Local stroke statistics from 2015 to 2021 were analyzed and circadian distribution of strokes and local incidence rates were calculated. MSU patient numbers and total program costs were estimated for varying operating modes, daytime coverage models, staffing configurations which included several resource sharing models with the hospital. Additional case-number simulations for expanded catchment areas were performed. Results: Median time of symptom onset of ischemic stroke patients was 1:00 p.m. 54.3% of all stroke patients were admitted during a 10-h time window on weekdays. Assuming that MSU is able to reach 53% of stroke patients, the average expected number of ischemic stroke patients admitted to MSU would be 0.64 in a 10-h shift each day, which could potentially be increased by expanding the MSU catchment area. Total estimated MSU costs amounted to 815,087 per annum. Teleneurological assessment reduced overall costs by 11.7%. Conclusion: This analysis provides a framework of determinants and considerations to be addressed during the design process of a novel MSU program in order to balance stroke care improvements with the sustainable use of scarce resources.
RESUMEN
The automatic, sensor-based assessment of human activities is highly relevant for production and logistics, to optimise the economics and ergonomics of these processes. One challenge for accurate activity recognition in these domains is the context-dependence of activities: Similar movements can correspond to different activities, depending on, e.g., the object handled or the location of the subject. In this paper, we propose to explicitly make use of such context information in an activity recognition model. Our first contribution is a publicly available, semantically annotated motion capturing dataset of subjects performing order picking and packaging activities, where context information is recorded explicitly. The second contribution is an activity recognition model that integrates movement data and context information. We empirically show that by using context information, activity recognition performance increases substantially. Additionally, we analyse which of the pieces of context information is most relevant for activity recognition. The insights provided by this paper can help others to design appropriate sensor set-ups in real warehouses for time management.
