Groeneveld S W M, van Os-Medendorp H, van Gemert-Pijnen J E W C, Verdaasdonk R M, van Houwelingen T, Dekkers T, den Ouden M E M
Research Group Technology, Health & Care, School of Social Work, Saxion University of Applied Sciences, P.O. box 70.000, 7500 KB Enschede, Netherlands; Research Group Smart Health, School of Health, Saxion University of Applied Sciences, P.O. box 70.000, 7500 KB Enschede, Netherlands; TechMed Center, Health Technology Implementation, University of Twente, P.O. box 217, 7500 AE Enschede, Netherlands.
Faculty Health, Sports, and Social Work, Inholland University of Applied Sciences, P.O. box 75068, 1070 AB Amsterdam, Netherlands; Spaarne Gasthuis Academy, P.O. box 417, 2000 AK Haarlem, Netherlands.
Nurse Educ Today. 2025 Jun;149:106659. doi: 10.1016/j.nedt.2025.106659. Epub 2025 Mar 1.
As more and more older adults prefer to stay in their homes as they age, there's a need for technology to support this. A relevant technology is Artificial Intelligence (AI)-driven lifestyle monitoring, utilizing data from sensors placed in the home. This technology is not intended to replace nurses but to serve as a support tool. Understanding the specific competencies that nurses require to effectively use it is crucial. The aim of this study is to identify the essential competencies nurses require to work with AI-driven lifestyle monitoring in long-term care.
A three round modified Delphi study was conducted, consisting of two online questionnaires and one focus group. A group of 48 experts participated in the study: nurses, innovators, developers, researchers, managers and educators. In the first two rounds experts assessed clarity and relevance on a proposed list of competencies, with the opportunity to provide suggestions for adjustments or inclusion of new competencies. In the third round the items without consensus were bespoken in a focus group.
After the first round consensus was reached on relevance and clarity on n = 46 (72 %) of the competencies, after the second round on n = 54 (83 %) of the competencies. After the third round a final list of 10 competency domains and 61 sub-competencies was finalized. The 10 competency domains are: Fundamentals of AI, Participation in AI design, Patient-centered needs assessment, Personalisation of AI to patients' situation, Data reporting, Interpretation of AI output, Integration of AI output into clinical practice, Communication about AI use, Implementation of AI and Evaluation of AI use. These competencies span from basic understanding of AI-driven lifestyle monitoring, to being able to integrate it in daily work, being able to evaluate it and communicate its use to other stakeholders, including patients and informal caregivers.
Our study introduces a novel framework highlighting the (sub)competencies, required for nurses to work with AI-driven lifestyle monitoring in long-term care. These findings provide a foundation for developing initial educational programs and lifelong learning activities for nurses in this evolving field. Moreover, the importance that experts attach to AI competencies calls for a broader discussion about a potential shift in nursing responsibilities and tasks as healthcare becomes increasingly technologically advanced and data-driven, possibly leading to new roles within nursing.
随着越来越多的老年人希望在年老时居家养老，需要技术来提供支持。一项相关技术是人工智能（AI）驱动的生活方式监测，它利用安置在家庭中的传感器收集的数据。这项技术并非旨在取代护士，而是作为一种辅助工具。了解护士有效使用该技术所需的特定能力至关重要。本研究的目的是确定护士在长期护理中运用人工智能驱动的生活方式监测所需的基本能力。
开展了一项三轮的改良德尔菲研究，包括两份在线问卷和一次焦点小组讨论。48名专家参与了该研究，包括护士、创新者、开发者、研究人员、管理人员和教育工作者。在前两轮中，专家们对一份拟议的能力清单的清晰度和相关性进行评估，并有机会就调整或纳入新能力提出建议。在第三轮中，对未达成共识的项目在焦点小组中进行讨论。
第一轮后，就46项（72%）能力的相关性和清晰度达成了共识，第二轮后就54项（83%）能力达成了共识。第三轮后，最终确定了一份包含10个能力领域和61项子能力的清单。这10个能力领域分别是：人工智能基础、参与人工智能设计、以患者为中心的需求评估、根据患者情况对人工智能进行个性化设置、数据报告、解读人工智能输出结果、将人工智能输出结果整合到临床实践中、关于人工智能使用的沟通、人工智能的实施以及对人工智能使用的评估。这些能力涵盖了从对人工智能驱动的生活方式监测的基本理解，到能够将其融入日常工作、进行评估并与包括患者和非正式护理人员在内的其他利益相关者交流其使用情况。
我们的研究引入了一个新颖的框架，突出了护士在长期护理中运用人工智能驱动的生活方式监测所需的（子）能力。这些发现为在这个不断发展的领域为护士制定初始教育计划和终身学习活动奠定了基础。此外，专家们对人工智能能力的重视引发了关于随着医疗保健技术日益先进和数据驱动，护理职责和任务可能发生潜在转变的更广泛讨论，这可能会在护理领域产生新的角色。
