improving Service Access using Virtual Exposure (iSAVE)

对接受治疗的焦虑可能从短暂的担忧和负面情绪，到长期的特定恐惧症，对患者来说是一种令人虚弱的经历。避免治疗或诊断程序，如扫描，可能会对患者的护理途径和临床结果产生负面影响，而避免焦虑引发的经历被认为会在恶性循环中加剧问题。目前患者解决这一问题的方案(如治疗和镇静)往往昂贵、耗时且难以获得。iSAVE是一个使用虚拟暴露来改善服务获取的项目。它将提供虚拟现实暴露治疗工具，帮助那些对接受医疗治疗感到焦虑的患者。VR工具使用了创新的眼睛跟踪硬件和软件，嵌入到VR头戴式耳机中，可以监控患者在VR中的焦虑程度；这是现有曝光工具所不具备的功能。机器学习被用来根据患者的眼球运动来衡量他们的焦虑水平，人工智能使虚拟工具能够智能地调整患者接受的暴露水平。这使得暴露体验对个人来说是个性化的，因此是非常有效的。iSAVE将进行更多的行业研究，使这种工具准备好上市，并供需要它的患者使用。该项目将；(1)改进和实施机器学习方法，这是该工具的一个新功能，并在焦虑的患者中测试这些方法；(2)进一步开发用户界面和体验，使患者和最终用户(从业者和护理提供者)可以访问该工具；(3)建立未来需要进行哪些临床试验，以减少实施到患者护理路径中的不确定性，包括分析进入NHS的交付组件，以及监管批准的要求。我们的目标是为精神健康生态系统做好iSave准备。进入护理提供者的手中，以降低成本和节省时间，并进入患者的手中，以减少他们的焦虑，改善他们所接受的护理。

Anxiety about receiving medical treatments can range from momentary worry and negative feelings, to longer term specified phobias and is a debilitating experience for a patient. Avoiding treatments or diagnostic procedures such as scans can negatively impact the care pathway and clinical outcomes for the patient, and avoidance of anxiety inducing experiences is known to exacerbate the problem in a vicious cycle. Current solutions to this problem for patients (e.g. therapy and sedation) are often expensive, time consuming and hard to access.iSAVE is a project which will improve Service Access using Virtual Exposure. It will deliver Virtual Reality exposure therapy tools to help patients who are anxious about receiving health care treatments. The VR tool uses innovative eye tracking hardware and software, embedded into the VR headset, which monitors the anxiety levels of the patients while they are in VR; something which has not been a feature of existing exposure tools. Machine Learning is used to index the patient's anxiety levels from their eye movements, Artificial Intelligence enables the virtual tool to intelligently adapt the level of exposure the patient receives. This makes the exposure experience personalised to the individual, and therefore highly effective.iSAVE will undertake additional industrial research that will make this tool ready for market, and accessible by the patients that need it. The project will; (1) improve and implement the machine learning approaches that are a novel feature of the tool, and test these with anxious patients; (2) further develop the user interface and experience to make the tool accessible to patients and end-users (practitioners and care providers); (3) establish what future clinical trials would be needed to reduce the uncertainty of implementation into the patient care pathway, including an analysis of delivery components into the NHS, and the requirements for regulatory approval.Our objective is to get iSAVE ready for the mental health ecosystem. Into the hands of care providers to reduce costs and save time, and into the hands of patients, to reduce their anxiety and improve the care they recieve.