Improving asthma care through personalised risk assessment and support from a conversational agent

英国有超过540万人患有哮喘，尽管NHS每年在哮喘治疗上花费10亿GB，但全国的死亡率是欧洲最高的。这一统计数据的原因之一是，许多哮喘患者往往严重低估了风险。这导致了对早期护理的忽视，控制不力，最终导致住院。因此，通过改变哮喘患者的相关行为来提高准确的风险评估和减少风险，可以挽救生命并显著降低医疗成本。我们的多部门和国际团队将致力于通过研究一种新型的低成本、可扩展的个性化风险评估，并结合后续的自动化支持来降低风险，以解决这一早期护理缺口。该技术将利用人工智能根据语音特征和自我报告的数据计算个性化的哮喘风险分数。然后，它将提供关于可以采取的降低风险的行动的个性化建议，随后将提供定制的对话指导，以支持健康变化的过程。我们设想，我们的工作最终将导致一个安全和参与性的系统，在该系统中，患者能够在回答一系列问题后看到他们目前哮喘发作的风险，类似于临床病历记录，并记录他们的声音。然后，他们就如何降低风险从自动化培训师那里获得持续的定制支持。他们取得的任何进展都将明显降低他们的风险(例如，将其描述为“加强他们的盾牌”)，以使他们的哮喘控制状态更加切实和具有激励作用。这项技术将通过联合设计方法和定期反馈，在哮喘患者和临床医生的直接参与下合作开发，以确保风险评估、反馈和指导在临床上是合理的，并以一种支持自主、清晰、有用和吸引患者的方式提供。类似的风险评估方法已经被证明在改善心血管和精神健康方面成功，但这将是首次将个性化风险评估应用于哮喘，并与对话代理的支持相结合。风险计算和反馈将涉及三种新方法：1)数据驱动的哮喘风险模型，利用常规收集的未识别的电子健康记录数据，这些数据将用于确定哪些因素最准确地预测哮喘恶化。2)机器学习技术，用于根据声音特征(例如，喘息、呼吸频率、咳嗽)检测哮喘风险。3)自然语言处理技术，用于开发支持自主的对话代理，以支持健康行为的改变。该项目将以伦敦帝国理工学院为基础，来自英国、美国和澳大利亚的组织的临床医生和研究人员。该项目还将与YourMD Ltd合作进行，这将促进在他们的商业应用程序中运行一项试点研究，该应用程序将为概念验证测试提供足够的数据。这将允许算法使用来自更多参与者的对话和语音数据，并将加快未来项目阶段的翻译。

Over 5.4 million people have asthma in the UK, and despite £1Billion a year in NHS spending on asthma treatment, the national mortality rate is the highest in Europe. One of the reasons for this statistic, is that risk is often dramatically underestimated by many with asthma. This leads to neglect of early care, poor control, and eventually, hospitalisation. Therefore, improving accurate risk assessment and reduction via relevant behaviour change among people with asthma could save lives and dramatically reduce health care costs. Our multi-sector and international team will aim to address this early-care gap by investigating a new type of low-cost, and scalable personalised risk assessment, combined with follow-up automated support for risk reduction. The technology will leverage artificial intelligence to calculate a personalised asthma risk score based on voice features and self-reported data. It will then provide personalised advice on actions that can be taken to lower risk followed by customised conversational guidance to support the process of healthy change.We envision our work will ultimately lead to a safe and engaging system where the patients are able to see their current risk of an asthma attack after answering a series of questions, akin to clinical history taking, and record their voice. They then get ongoing customised support from an automated coach on how to reduce that risk. Any progress they make will visibly lower their risk (presented, for example, as "Strengthening their shield"), in order to make their state of asthma control more tangible and motivating. The technology will be developed collaboratively with direct involvement from people with asthma and clinicians through co-design methods and regular feedback in order to ensure risk assessment, feedback and guidance are clinically sound, and delivered in a way that is autonomy-supportive, clear, useful, and engaging to patients.Similar risk assessment approaches have already proven successful for improving cardiovascular and mental health, but this will be the first time personalised risk assessment is applied to asthma and integrated with support from a conversational agent. The risk calculation and feedback will involve three novel approaches:1) A data-driven model of asthma risk drawing on routinely collected de-identified Electronic Health Record data which will be used to identify which factors most accurately predict asthma exacerbation.2) Machine learning techniques for detecting asthma risk from voice features (eg, wheezing, breath rate, coughing). 3) Natural Language Processing techniques for developing an autonomy-supportive conversational agent to support health behaviour change.The project will be based at Imperial College London with clinicians and researchers from organisations in the UK, the US, and Australia. The project will also be undertaken in partnership with YourMD Ltd which will facilitate running a pilot study within their commercial app which will provide access to sufficient data for proof-of-concept testing. This will allow the algorithms to use dialogue and voice data from a larger number of participants, and will also accelerate translation for future project phases.