Active learning has become an increasingly popular method for screening large amounts of data in systematic reviews and meta-analyses. The active learning process continually improves its predictions on the remaining unlabeled records, with the goal of identifying all relevant records as early as possible. However, determining the optimal point at which to stop the active learning process is a challenge. The cost of additional labeling of records by the reviewer must be balanced against the cost of erroneous exclusions. This paper introduces the SAFE procedure, a practical and conservative set of stopping heuristics that offers a clear guideline for determining when to end the active learning process in screening software like ASReview. The eclectic mix of stopping heuristics helps to minimize the risk of missing relevant papers in the screening process. The proposed stopping heuristic balances the costs of continued screening with the risk of missing relevant records, providing a practical solution for reviewers to make informed decisions on when to stop screening. Although active learning can significantly enhance the quality and efficiency of screening, this method may be more applicable to certain types of datasets and problems. Ultimately, the decision to stop the active learning process depends on careful consideration of the trade-off between the costs of additional record labeling against the potential errors of the current model for the specific dataset and context.
MULTIFILE
Background: Urban slums are characterised by unique challenging living conditions, which increase their inhabitants’ vulnerability to specific health conditions. The identification and prioritization of the key health issues occurring in these settings is essential for the development of programmes that aim to enhance the health of local slum communities effectively. As such, the present study sought to identify and prioritise the key health issues occurring in urban slums, with a focus on the perceptions of health professionals and community workers, in the rapidly growing city of Bangalore, India. Methods: The study followed a two-phased mixed methods design. During Phase I of the study, a total of 60 health conditions belonging to four major categories: - 1) non-communicable diseases; 2) infectious diseases; 3) maternal and women’s reproductive health; and 4) child health - were identified through a systematic literature review and semi-structured interviews conducted with health professionals and other relevant stakeholders with experience working with urban slum communities in Bangalore. In Phase II, the health issues were prioritised based on four criteria through a consensus workshop conducted in Bangalore. Results: The top health issues prioritized during the workshop were: diabetes and hypertension (non-communicable diseases category), dengue fever (infectious diseases category), malnutrition and anaemia (child health, and maternal and women’s reproductive health categories). Diarrhoea was also selected as a top priority in children. These health issues were in line with national and international reports that listed them as top causes of mortality and major contributors to the burden of diseases in India. Conclusions: The results of this study will be used to inform the development of technologies and the design of interventions to improve the health outcomes of local communities. Identification of priority health issues in the slums of other regions of India, and in other low and lower middle-income countries, is recommended.
DOCUMENT
Amsterdam Airport Schiphol has faced capacity constraints, particularly during peak periods. At the security screening checkpoint, this is due to the growing number of passengers and a shortage of security staff. To improve operating performance, there is a need to integrate newer technologies that improve passing times. This research presents a discrete event simulation (DES) model for the inclusion of a shoe scanner at the security screening checkpoint at Amsterdam Airport Schiphol. Simulation is a frequently used method to assess the influence of process changes, which, however, has not been applied for the inclusion of shoe scanners in airport security screenings yet. The simulation model can be used to assess the implementation and potential benefits of an optical shoe scanner, which is expected to lead to significant improvements in passenger throughput and a decrease in the time a passenger spends during the security screening, which could lead to improved passenger satisfaction. By leveraging DES as a tool for analysis, this study provides valuable insights for airport authorities and stakeholders aiming to optimize security screening operations and enhance passenger satisfaction.
DOCUMENT
