Human-AI Collaboration in Healthcare: AI-Enabled Adaptive Learning Systems

人类-人工智能协作(HAIC)描述了人类和人工智能(AI)系统协同工作的系统，以产生优于独立解决方案的结果。今天，人工智能系统开始部署在医疗保健系统中，以实现工作流程优化，并获得潜在的经济和生产力好处。他们已经被证明在一些临床环境中侵蚀甚至超过了训练有素的专家的表现([1])。然而，这些好处并非没有缺点。具体到医疗保健领域，深度学习模型等人工智能容易产生偏见，易于泛化，并可能产生无法解释的预测([2])。当然，人类也不是没有弱点。一项研究估计，放射科医生的医疗差错被列为第三大死亡原因，年发生率高达9.5%([3])。出错率的原因是集中度高、工作量大、周转快等因素，这些因素导致了放射科医生的疲劳。HAIC寻求缓解人类和人工智能的个人弱点，同时利用它们各自的优势，最终开发出一个增强的系统。HAIC涵盖了广泛的主题，包括分布外泛化、基于延迟的系统、可解释的人工智能、视听计算机视觉和多模式人工智能模型。在这个DPhil项目中，我们的初始目标是开发大型多通道语言模型，用于创建支持人工智能的自适应学习系统。例如，超声师面临着一项要求苛刻的职业，即在有时间限制的紧张情况下保持高诊断精度，这需要高水平的技能。将专家知识和专业知识转移给新学员是一个巨大的挑战。通过HAIC开发人工智能系统，向新手学员传达特定任务的专家知识，同时适应他们随着时间的推移不断变化的专业水平，可以简化这一耗时和成本密集型的过程。该项目属于EPSRC的人机交互研究领域，将与OxSTaR(牛津模拟、教学和研究)团队合作进行。HAIC在医疗保健领域是一个相对较新的领域；因此，有许多新的问题需要解决。尽管各种类型的人工智能自适应学习系统已经有了一些初步的发展，但这些系统主要在教育领域实现。参考文献[1]Babak Ehteshami Bejnordi，Mitko Veta，Paul Johannes Van Diest，Bram Van Ginneken，NicoKarsSemeijer，Geert Litjens，Jeroen AWM Van Der Laak，Meyke Hermsen，Quirine F Manson，Maschenka Balkenholl等。深度学习算法检测乳腺癌女性淋巴转移的诊断评估。JAMA，318(22)：2199-2210,2017.[2]Milena A.Gianfrancesco，Suzanne Tamang，Jioos Yazdany，和Gabriela SchMajuk。使用电子健康记录数据的机器学习算法中的潜在偏差。《美国医学会内科杂志》178(11)：1544-1547，11 2018[3]Martin A Makary和Michael Daniel。医疗错误--美国第三大死因。《英国医学杂志》，353,2016。[4]斯蒂芬·韦特、斯里尼瓦斯·科拉、让·朱迪、艾伦·莱加斯托、斯蒂芬·L·马克尼克、苏珊娜·马丁内斯·康德、伊丽莎白·A·克鲁宾斯基和黛博拉·L·里德。疲惫的阅览室：放射学的影响。《美国放射学会杂志》，14(2)：191-197,2017。

Human-AI collaboration (HAIC) describes systems whereby humans and artificial intelligence (AI) systems work in tandem to produce outcomes superior to independent solutions. Today, AI systems are beginning to be deployed in healthcare systems, for workflow optimisation, and potential economical and productivity benefits. They have been shown to encroach or even outperform the performance of trained experts in some clinical settings ([1]). However, these benefits do not come without drawbacks. Specific to the healthcare domain, AI such as deep learning models are susceptible to bias, can be prone to poor generalisation, and can produce uninterpretable predictions ([2]). Humans are, of course, also not without weaknesses. A study approximated that medical errors from radiologists rank as the third most significant cause of death, with an annual occurrence rate of up to 9.5% ([3]). The error rate can be attributed to several factors, such as high concentration, large workload and quick turnover, which contributes to fatigue of the radiologists ([4]). HAIC seeks to mitigate the individual weaknesses of humans and AI while leveraging their respective strengths, ultimately developing an enhanced system. HAIC encompasses a wide range of topics, including out-of-distribution generalisation, deferral-based systems, explainable AI, audio-visual computer vision, and multimodal AI models. In this DPhil project, our initial goal is to develop large multimodal language models for creating AI-enabled adaptive learning systems. For instance, sonographers face the demanding profession of maintaining high diagnostic precision in stressful situations with time constraints, which requires a high level of skill. Transferring expert knowledge and expertise to new trainees presents a significant challenge.Streamlining this time- and cost-intensive process can be achieved through HAIC by developing AI systems that convey task-specific expert knowledge to novice trainees while adapting to their evolving expertise levels over time. This project falls under the EPSRC's research area of human-computer interaction and will be carried out in collaboration with the OxSTaR (Oxford Simulation, Teaching, and Research) team. HAIC is a relatively new field in healthcare; therefore, there are many novel problems to address.Although there have been some preliminary developments in various types of AI-enabled adaptive learning systems, these have primarily been implemented in the education domain. There are no publications of similar work in the healthcare domain.References[1] Babak Ehteshami Bejnordi, Mitko Veta, Paul Johannes Van Diest, Bram Van Ginneken, NicoKarssemeijer, Geert Litjens, Jeroen AWM Van Der Laak, Meyke Hermsen, Quirine F Manson,Maschenka Balkenhol, et al. Diagnostic assessment of deep learning algorithms for detection oflymph node metastases in women with breast cancer. Jama, 318(22):2199-2210, 2017.[2] Milena A. Gianfrancesco, Suzanne Tamang, Jinoos Yazdany, and Gabriela Schmajuk. PotentialBiases in Machine Learning Algorithms Using Electronic Health Record Data. JAMA InternalMedicine, 178(11):1544-1547, 11 2018.[3] Martin A Makary and Michael Daniel. Medical error-the third leading cause of death in the us.Bmj, 353, 2016.[4] Stephen Waite, Srinivas Kolla, Jean Jeudy, Alan Legasto, Stephen L Macknik, Susana Martinez-Conde, Elizabeth A Krupinski, and Deborah L Reede. Tired in the reading room: the influence offatigue in radiology. Journal of the American College of Radiology, 14(2):191-197, 2017.