Collaborative intelligence for intensive care units,Critical Care

当前位置： X-MOL 学术 › Crit. Care › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Collaborative intelligence for intensive care units
Critical Care ( IF 8.8 ) Pub Date : 2021-12-14 , DOI: 10.1186/s13054-021-03852-7
Kay Choong See _{1,

2}

Affiliation

The intensive care unit (ICU) is a rich and complex data environment, well-suited for artificial intelligence (AI) and machine learning techniques. Numerous AI applications are being developed for the management of critically ill patients [1], both before and during the COVID-19 pandemic [2]. However, it remains unclear how intensive care clinicians can benefit from AI. Learning from the business literature, the concept of collaborative intelligence can help to clarify how humans can synergize with AI [3]. For the ICU, three domains can be identified where AI can augment the human clinician, and vice versa (Table 1).

Table 1 Collaborative intelligence for intensive care units

Full size table

The first domain is related to accountability and risk mitigation, where AI amplifies human cognition while humans sustain AI [3]. The speed and consistency of digital systems allow AI to help humans perform continuous and rapid multi-channel monitoring, data harvesting, organization and analysis. Such abilities are particularly useful in the ICU, where critically ill patients quickly amass large quantities of clinical data, and clinicians are at risk of monitoring fatigue. Furthermore, AI-driven decisions can help corroborate human decisions. In return, humans can provide real-world stress testing of AI systems, including simulated adversarial attacks, which are intentional contamination of data aimed at causing AI malfunction. Additionally, humans can audit AI algorithms for accuracy and bias, enhancing confidence and trust in AI.

The second domain is related to sense-making, where AI interacts with humans in intelligible ways (i.e., explainable AI [4]) while humans help explain AI [3]. Rather than merely providing an output that substantiates human answers, AI can produce lists of salient features and probabilities for various diagnoses, predictions and actions, helping humans prioritize and justify decisions. To avoid the “black-box” effect, human clinicians can augment AI outputs by helping interpret these to lay-persons.

The third and final domain is performance augmentation, where AI embodies human skills while humans train AI [3]. Real-time AI-powered ultrasound systems to guide novices in image acquisition and interpretation are commercially available, e.g., Caption AI (Caption Health, Brisbane, CA). At the cognitive level, just like how human players train using computer chess engines, human clinicians can learn from AI-generated decisions and data summaries. Graph data science methods using multivariate time series can reveal novel visual relationships among patient characteristics, treatments and clinical evolution [5]. In turn, AI methods like reinforcement learning depend on real-life data and decision-making. Ultimately, implementation and scaling of AI solutions require human support for digital resources.

Not applicable.

AI:: Artificial intelligence
ICU:: Intensive care unit

1.
Gutierrez G. Artificial intelligence in the intensive care unit. Crit Care. 2020;24(1):101.
Article Google Scholar
2.
Chen J, See KC. Artificial intelligence for COVID-19: rapid review. J Med Internet Res. 2020;22(10):e21476.
Article Google Scholar
3.
Wilson HJ, Daugherty PR. Collaborative intelligence: humans and AI are joining forces. Harv Bus Rev. 2018;96(4):114–23.
Google Scholar
4.
Amann J, Blasimme A, Vayena E, Frey D, Madai VI, Precise QC. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak. 2020;20(1):310.
Article Google Scholar
5.
Martinez-Aguero S, Marques AG, Mora-Jimenez I, Alvarez-Rodriguez J, Soguero-Ruiz C. Data and network analytics for COVID-19 ICU patients: a case study for a Spanish Hospital. IEEE J Biomed Health Inform. 2021;25(2):4340–53.
Article Google Scholar

Download references

No funding was required for this study.

Affiliations

Division of Respiratory and Critical Care Medicine, Department of Medicine, National University Hospital, University Medicine Cluster, National University Health System, 1E Kent Ridge Road, NUHS Tower Block Level 10, Singapore, 119228, Singapore
Kay Choong See
Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
Kay Choong See

Authors

Kay Choong SeeView author publications
You can also search for this author in PubMed Google Scholar

Contributions

KCS contributed to study concept, design and drafting of manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Kay Choong See.

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

KCS has received honoraria and travel support from Medtronic and GE Healthcare.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and Permissions

Cite this article

See, K.C. Collaborative intelligence for intensive care units. Crit Care 25, 426 (2021). https://doi.org/10.1186/s13054-021-03852-7

Download citation

Received: 29 November 2021
Accepted: 30 November 2021
Published: 14 December 2021
DOI: https://doi.org/10.1186/s13054-021-03852-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

中文翻译：

重症监护室的协作智能

重症监护病房 (ICU) 是一个丰富而复杂的数据环境，非常适合人工智能 (AI) 和机器学习技术。在 COVID-19 大流行之前和期间，正在开发大量 AI 应用程序来管理重症患者 [1] [2]。然而，目前尚不清楚重症监护临床医生如何从人工智能中受益。从商业文献中学习，协作智能的概念有助于阐明人类如何与人工智能协同工作 [3]。对于 ICU，可以确定 AI 可以增强人类临床医生的三个领域，反之亦然（表 1）。

表 1 重症监护室的协作智能

全尺寸表

第一个领域与问责制和风险缓解有关，其中人工智能放大人类认知，而人类维持人工智能 [3]。数字系统的速度和一致性使人工智能能够帮助人类执行持续快速的多通道监控、数据收集、组织和分析。这种能力在重症监护室特别有用，重症患者迅速积累大量临床数据，临床医生面临监测疲劳的风险。此外，人工智能驱动的决策可以帮助证实人类的决策。作为回报，人类可以对 AI 系统进行真实世界的压力测试，包括模拟对抗性攻击，这是对旨在导致 AI 故障的数据的故意污染。此外，人类可以审核 AI 算法的准确性和偏差，从而增强对 AI 的信心和信任。

第二个领域与意义建构有关，其中人工智能以可理解的方式与人类交互（即可解释的人工智能 [4]），而人类则帮助解释人工智能 [3]。AI 不仅可以提供证实人类答案的输出，还可以为各种诊断、预测和行动生成显着特征和概率列表，帮助人类优先考虑和证明决策的合理性。为了避免“黑匣子”效应，人类临床医生可以通过帮助向非专业人士解释这些结果来增加 AI 输出。

第三个也是最后一个领域是性能增强，其中人工智能体现了人类技能，而人类训练人工智能 [3]。用于指导新手进行图像采集和解释的实时人工智能超声系统已上市，例如 Caption AI (Caption Health, Brisbane, CA)。在认知层面，就像人类玩家如何使用计算机国际象棋引擎进行训练一样，人类临床医生可以从 AI 生成的决策和数据摘要中学习。使用多元时间序列的图形数据科学方法可以揭示患者特征、治疗和临床演变之间的新视觉关系 [5]。反过来，强化学习等人工智能方法依赖于现实生活中的数据和决策。最终，人工智能解决方案的实施和扩展需要人类对数字资源的支持。

不适用。

人工智能：: 人工智能
重症监护室：: 重症监护室

1.
Gutierrez G. 重症监护病房中的人工智能。暴击护理。2020；24(1):101。
文章谷歌学术
2.
陈杰，见 KC。COVID-19 的人工智能：快速审查。J Med Internet Res。2020;22(10):e21476。
文章谷歌学术
3.
威尔逊 HJ，多尔蒂公关。协作智能：人类和人工智能正在联手。Harv Bus Rev. 2018；96(4):114-23。
谷歌学术
4.
Amann J、Blasimme A、Vayena E、Frey D、Madai VI、Precise QC。医疗保健中人工智能的可解释性：多学科视角。BMC Med 通知 Decis Mak。2020；20(1):310。
文章谷歌学术
5.
Martinez-Aguero S、Marques AG、Mora-Jimenez I、Alvarez-Rodriguez J、Soguero-Ruiz C. COVID-19 ICU 患者的数据和网络分析：西班牙医院的案例研究。IEEE J Biomed 健康信息。2021;25(2):4340-53。
文章谷歌学术

下载参考资料

这项研究不需要资金。

隶属关系

新加坡国立大学医院 1E Kent Ridge Road, NUHS Tower Block Level 10, Singapore, 119228, National University Health System, National University Hospital, University Medicine Cluster, National University Health System, 1E Kent Ridge Road, 新加坡
凯仲见
新加坡国立大学杨潞龄医学院医学系，新加坡，新加坡
凯仲见

作者

Kay Choong查看作者的出版物
您也可以在PubMed Google Scholar中搜索该作者

贡献

KCS 为手稿的研究概念、设计和起草做出了贡献。所有作者阅读并认可的终稿。

通讯作者

与 Kay Choong See 的通信。

伦理批准和同意参与

不适用。

同意发表

不适用。

利益争夺

KCS 已收到 Medtronic 和 GE Healthcare 的酬金和旅行支持。

出版商注

Springer Nature 对出版地图和机构附属机构的管辖权主张保持中立。

开放存取本文根据知识共享署名 4.0 国际许可进行许可，该许可允许以任何媒介或格式使用、共享、改编、分发和复制，只要您对原作者和来源给予适当的信任，并提供链接到知识共享许可，并说明是否进行了更改。本文中的图像或其他第三方材料包含在文章的知识共享许可中，除非在材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的允许或超出允许的用途，您将需要直接从版权所有者那里获得许可。要查看此许可证的副本，请访问 http://creativecommons.org/licenses/by/4.0/。

转载和许可