应12BET的邀请，英国雷丁大学李微子教授于2024年8月26日上午10点在中关村校区主楼429会议室做了题为《Developing and deploying Al in National Health Services (NHS) in the UK: what are the realities?》的学术报告。报告会由颜志军老师主持，学院众多师生参加了本次报告会。
李教授的报告主要聚焦于英国国家卫生服务中的人工智能开发和应用。尽管人工智能已经取得了实质性进展，但人工智能在医疗保健环境中的实际可用性和广泛集成仍然面临着重大挑战。因此，李教授针对如何构建人工智能解决方案、利用医疗保健数据有效地满足一线医疗保健专业人员的需求开展了研究工作。
李教授通过两个具体的人工智能研究案例向大家介绍了最新研究成果。首先，李教授以风湿病患者为例，指出由于英国患者就医流程的复杂性和低效性，社区医生难以准确判断患者的风湿病类型并将其正确转诊到对应的医院科室，导致许多风湿病患者的病情恶化，造成严重的社会健康问题。基于此，李教授基于社区医院的就诊病历、过往就诊信息和血液化验记录等多维度数据，采用深度学习方法对患者的风湿患病类型进行智能判断，从而帮助社区医生提高了风湿病患者的识别能力。同时，李教授从人工智能的可解释性出发，研究了英国患者诊疗过程中常常出现的就诊爽约问题，提出了基于深度学习的就诊爽约预测算法，并建立了基于人工智能目标检测的电话回访机制，有效降低了英国社区医院转诊后出现的居高不下的就诊爽约率。
同时，李教授也分析了人工智能和医疗健康领域的未来研究方向，认为可以从大语言模型的角度出发，结合气候、经济、全球疾病负担等多样化的数据开展医疗健康领域的研究。
报告结束后，与会师生与李教授展开了积极的讨论与交流。报告反响热烈，得到了师生们的一致好评。
汇报人简介：
Weizi (Vicky) Li is a Professor of Informatics and Digital Health, at Henley Business School, University of Reading. She is a Fellow of Charted Institute of IT(British Computer Society). She is an interdisciplinary researcher focusing onusing informatics, data science, machine learning, and digital information systems to solve real-world healthcare challenges.
She has been Principal Investigators (PI) on large projects funded by the National Institute for Health and Care Research (NIHR), UK Research and Innovation (UKRI), NHS and industries working on data-driven decision support systems that use real-world data from multiple sources including Electronic Patient Records in acute, community hospital and primary care settings, to develop novel technologies (including AI-based methods) to support clinical and operationaldecision makingsin patient pathways.
She is currently Director of Future Blood Testing for Inclusive Monitoring andPersonalised Analytics NetworkPlus founded by UKRI Engineering and PhysicalScience Research Council (EPSRC); PI of UKRI EPSRC Technology mission fund inAIfor Health proiect: Advancing machine learningto achieve real-worldearly detection and personalized disease outcome predictionofinflammatory arthritis; PI of NIHR Invention for Innovation Product Development Award: Machinelearning-enabled decision support system to improve early detection and referralofrheumatic and musculoskeletal diseases.
Her work has been successfully implemented in NHS and has received the Research Engagement and lmpact award in 2020 and 2022 and shortlisted for national Health Service Journal (HSJ) patient safety award.
