Improving Efficiency and Equity of Ambulance Services through Advanced Demand Modelling

近年来，英国对救护车服务的需求急剧上升，预计未来几年的压力将越来越大。不断增长的需求和有限的救护车资源之间的差距是维持高质量服务的主要挑战。2017年，NHS英格兰进行了一项重大的国家改革，称为救护车响应计划（ARP），旨在解决效率和绩效问题。它注意到过度使用立即派遣决定和分配给事件的资源不足。所涉及的关键问题：护理质量；它的成本效益;以及不同地区和不同人口群体之间的平等供应。在这种情况下，从2017年到2018年，国王学院的研究人员与伦敦救护车服务中心（LAS）合作，开展了由anesrc资助的项目DASH，探索大数据如何改善救护车响应的决策。最终报告提出了6项新的数据举措，其中3项与需求预测密切相关。鉴于NHS的压力日益增加，救护车服务必须了解他们所服务的人群的需求，拟议的博士项目旨在以LAS为案例研究，开发一种先进的救护车服务需求预测模型。研究的目的是寻找最相关的社会经济、环境和时空因素，并将这些因素建模为救护车需求的预测因子。博士学位的最后一个组成部分将发展该模型作为需求管理创新的含义，用于未来的测试。

Demand for Ambulance Services in England has risendramatically over recent years, with growing pressureanticipated for future years. The disparity between theincreasing demand and limited ambulance resources makesthe major challenge for maintaining a high-quality service. In2017, NHS England undertook a significant national reformcalled the Ambulance Response Programme (ARP), designedto address efficiency and performance issues. It noted theover-use of immediate dispatch decisions and the insufficientallocation of resources to incidents. Key issues concerned:the quality of care; its cost-effectiveness; and the equality ofprovision across areas and population groups. Given suchsituation, from 2017 to 2018, King's researchers haveworked with the London Ambulance Service (LAS) on anESRC-funded project - DASH, exploring how big data couldimprove decision-making in ambulance response. The finalreport suggested six new data initiatives, out of which, threeare strongly related to demand prediction.In view of the growing pressures of NHS, and the necessity ofambulance services to understand the needs of thepopulations they serve, the proposed PhD project aims todevelop an advanced demand prediction model forambulance services taking LAS as a case study. Theresearch is to find the most correlated socioeconomic,environmental, and spatiotemporal factors and to modelthese factors as predictors of ambulance demand. The finalcomponent of the PhD will develop the implications of themodel as Demand Management innovations, for futuretesting.