Abstract: AI tools in radiology are revolutionising the diagnosis, evaluation, and management of patients. However, there is a major gap between the large number of developed AI tools and those translated into daily clinical practice, which can be primarily attributed to limited usefulness and trust in current AI tools. Instead of technically driven development, little effort has been put into value-based development to ensure AI tools will have a clinically relevant impact on patient care. An iterative comprehensive value evaluation process covering the complete AI tool lifecycle should be part of radiology AI development. For value assessment of health technologies, health technology assessment (HTA) is an extensively used and comprehensive method. While most aspects of value covered by HTA apply to radiology AI, additional aspects, including transparency, explainability, and robustness, are unique to radiology AI and crucial in its value assessment. Additionally, value assessment should already be included early in the design stage to determine the potential impact and subsequent requirements of the AI tool. Such early assessment should be systematic, transparent, and practical to ensure all stakeholders and value aspects are considered. Hence, early value-based development by incorporating early HTA will lead to more valuable AI tools and thus facilitate translation to clinical practice. Clinical relevance statement: This paper advocates for the use of early value-based assessments. These assessments promote a comprehensive evaluation on how an AI tool in development can provide value in clinical practice and thus help improve the quality of these tools and the clinical process they support. Key Points: Value in radiology AI should be perceived as a comprehensive term including health technology assessment domains and AI-specific domains. Incorporation of an early health technology assessment for radiology AI during development will lead to more valuable radiology AI tools. Comprehensive and transparent value assessment of radiology AI tools is essential for their widespread adoption.
The purpose of this study was to explore the experiences and impact of peer-to-peer shadowing as a technique to develop nurse middle managers’ clinical leadership practices. A qualitative descriptive study was conducted to gain insight into the experiences of nurse middle managers using semi-structured interviews. Data were analysed into codes using constant comparison and similar codes were grouped under sub-themes and then into four broader themes. Peer-to-peer shadowing facilitates collective reflection-in-action and enhances an “investigate stance” while acting. Nurse middle managers begin to curb the caring disposition that unreflectively urges them to act, to answer the call for help in the here and now, focus on ad hoc “doings”, and make quick judgements. Seeing a shadowee act produces, via a process of social comparison, a behavioural repertoire of postponing reactions and refraining from judging. Balancing the act of stepping in and doing something or just observing as well as giving or withholding feedback are important practices that are difficult to develop.
Background: 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 longterm care. Methods: 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. Findings: 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 AIdriven 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. Conclusion: 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.
LINK
Middels een RAAK-impuls aanvraag wordt beoogd de vertraging van het RAAK-mkb project Praktische Predictie t.g.v. corona in te halen. In het project Praktische Predictie wordt een prototype app ontwikkeld waarmee fysiotherapeuten in een vroeg stadium het chronisch worden van lage rugpijn kunnen voorspellen. Om chronische rugpijn te voorkomen is het belangrijk om in een vroeg stadium de kans hierop in te schatten door psychosociale en mogelijk andere risicofactoren op chronische pijnklachten te herkennen en hierop te interveniëren. Fysiotherapeuten zijn met deze vraag naar het lectoraat Werkzame factoren in Fysiotherapie en Paramedisch Handelen van de Hogeschool van Arnhem en Nijmegen gegaan en dit heeft aanleiding gegeven een onderzoek op te zetten waarin een dergelijke methodiek ontwikkeld wordt. De voorgestelde methodiek betreft een Clinical Decision Support Tool waarmee een geïndividualiseerde kans op chronische rugpijn kan worden bepaald gekoppeld aan een behandeladvies conform de lage rugpijn richtlijn. Hiervoor is eerst geïnventariseerd welke methoden fysiotherapeuten reeds gebruiken en welke in de literatuur worden genoemd. Op basis hiervan is een keuze gemaakt ten aanzien van data die digitaal verzameld worden in minimaal 16 fysiotherapiepraktijken waarbij patiënten gedurende 12 weken gevolgd worden. Met de verzamelde data worden met machine learning algoritmes ontwikkeld voor het berekenen van de kans op chroniciteit. De algoritmes worden ingebouwd in de Clinical Decision Support Tool: een gebruiksvriendelijke prototype app. Bij het ontwikkelen van de tool worden eindgebruikers (fysiotherapeuten en patiënten) intensief betrokken. Op deze manier wordt gegarandeerd dat de tool aansluit bij de wensen en behoeften van de doelgroep. De tool berekent de kans op chroniciteit en geeft een behandeladvies. Daarnaast kan de tool gebruikt worden om patiënten te informeren en te betrekken bij de besluitvorming. Vanwege de coronacrisis is er een aanzienlijke vertraging in de patiënten-instroom (doel n= 300) ontstaan die we met ondersteuning van een RAAK-impuls subsidie willen inlopen.
The main objective is to write a scientific paper in a peer-reviewed Open Access journal on the results of our feasibility study on increasing physical activity in home dwelling adults with chronic stroke. We feel this is important as this article aims to close a gap in the existing literature on behavioral interventions in physical therapy practice. Though our main target audience are other researchers, we feel clinical practice and current education on patients with stroke will benefit as well.
Alcohol use disorder (AUD) is a major problem. In the USA alone there are 15 million people with an AUD and more than 950,000 Dutch people drink excessively. Worldwide, 3-8% of all deaths and 5% of all illnesses and injuries are attributable to AUD. Care faces challenges. For example, more than half of AUD patients relapse within a year of treatment. A solution for this is the use of Cue-Exposure-Therapy (CET). Clients are exposed to triggers through objects, people and environments that arouse craving. Virtual Reality (VRET) is used to experience these triggers in a realistic, safe, and personalized way. In this way, coping skills are trained to counteract alcohol cravings. The effectiveness of VRET has been (clinically) proven. However, the advent of AR technologies raises the question of exploring possibilities of Augmented-Reality-Exposure-Therapy (ARET). ARET enjoys the same benefits as VRET (such as a realistic safe experience). But because AR integrates virtual components into the real environment, with the body visible, it presumably evokes a different type of experience. This may increase the ecological validity of CET in treatment. In addition, ARET is cheaper to develop (fewer virtual elements) and clients/clinics have easier access to AR (via smartphone/tablet). In addition, new AR glasses are being developed, which solve disadvantages such as a smartphone screen that is too small. Despite the demand from practitioners, ARET has never been developed and researched around addiction. In this project, the first ARET prototype is developed around AUD in the treatment of alcohol addiction. The prototype is being developed based on Volumetric-Captured-Digital-Humans and made accessible for AR glasses, tablets and smartphones. The prototype will be based on RECOVRY, a VRET around AUD developed by the consortium. A prototype test among (ex)AUD clients will provide insight into needs and points for improvement from patient and care provider and into the effect of ARET compared to VRET.
