Significant and rapid advancements in cancer research have been attributed to Artificial Intelligence (AI). However, AI’s role and impact on the clinical side has been limited. This discrepancy manifests due to the overlooked, yet profound, differences in the clinical and research practices in oncology. Our contribution seeks to scrutinize physicians' engagement with AI by interviewing 7 medical-imaging experts and disentangle its future alignment across the clinical and research workflows, diverging from the existing "one-size-fits-all" paradigm within Human-Centered AI discourses. Our analysis revealed that physicians' trust in AI is less dependent on their general acceptance of AI, but more on their contestable experiences with AI. Contestability, in clinical workflows, underpins the need for personal supervision of AI outcomes and processes, i.e., clinician-in-the-loop. Finally, we discuss tensions in the desired attributes of AI, such as explainability and control, contextualizing them within the divergent intentionality and scope of clinical and research workflows.@en

Background: Radiomics, the field of image-based computational medical biomarker research, has experienced rapid growth over the past decade due to its potential to revolutionize the development of personalized decision support models. However, despite its research momentum and important advances toward methodological standardization, the translation of radiomics prediction models into clinical practice only progresses slowly. The lack of physicians leading the development of radiomics models and insufficient integration of radiomics tools in the clinical workflow contributes to this slow uptake. Methods: We propose a physician-centered vision of radiomics research and derive minimal functional requirements for radiomics research software to support this vision. Free-to-access radiomics tools and frameworks were reviewed to identify best practices and reveal the shortcomings of existing software solutions to optimally support physician-driven radiomics research in a clinical environment. Results: Support for user-friendly development and evaluation of radiomics prediction models via machine learning was found to be missing in most tools. QuantImage v2 (QI2) was designed and implemented to address these shortcomings. QI2 relies on well-established existing tools and open-source libraries to realize and concretely demonstrate the potential of a one-stop tool for physician-driven radiomics research. It provides web-based access to cohort management, feature extraction, and visualization and supports “no-code” development and evaluation of machine learning models against patient-specific outcome data. Conclusions: QI2 fills a gap in the radiomics software landscape by enabling “no-code” radiomics research, including model validation, in a clinical environment. Further information about QI2, a public instance of the system, and its source code is available at https://medgift.github.io/quantimage-v2-info/. Key points As domain experts, physicians play a key role in the development of radiomics models.Existing software solutions do not support physician-driven research optimally.QuantImage v2 implements a physician-centered vision for radiomics research.QuantImage v2 is a web-based, “no-code” radiomics research platform.

@en

We examine the technological aspects of political collaborative practices in one of the first studies of participatory constitution writing in the course of its progression. In particular, we examine how digital collaborative and communicative tools can facilitate (or inhibit) the permeation of boundaries, which manifest through the differences in political ideologies and partisan beliefs. Our study is grounded in interviews with 15 members of the Constituent Assembly in the canton of Valais, Switzerland, and its primary contribution is in constructing a fine-grained contextualized understanding of political collaborations, their evolution, and their relationship with collaborative tools. Our findings demonstrate the centrality of versatile and widely available digital tools (such as WhatsApp and Google Docs) in political work. In addition, elected lawmakers prefer tools that allow them to organize their collaborative and communicative actions based on dynamic social boundaries, and their need for asynchronous work practices. We observed a tendency of simultaneously using multiple digital tools to accomplish specific political objectives, and leveraging them in plenary sessions for strategic advantages. On the one hand, collaborative tools enabled strategic advantages by selective permeation of boundaries across political ideologies. On the other hand, lack of awareness about boundaries between ‘private’ and ‘public’ on social networks were considered as privacy blind spots. By focusing on boundaries of different kinds, our paper elucidates how the introduction of digital technologies into political process transforms the long-established categories, distinctions and divisions that are often taken for granted.@en

Autonomous Passenger Shuttles (APS) are rapidly becoming an urban public transit alternative. Traversing populous com-mercial and residential centers, these shuttles are already operating in several cities. In the absence of a human driver andembedded means of communicating the autonomous shuttle’s intent, the task of seamlessly navigating crosswalks andpedestrian-friendly zones becomes a challenging pursuit for pedestrians.We contribute to the emerging notion of AV–Pedestrian Interaction by examining the context of autonomous passengershuttles (APS) in real-world settings, and by comparingfourdifferent classes of visual signals – namelyinstructional,symbolic,metaphorical, andanthropomorphic– designed to communicate the shuttle’s intentions. Following a participatory methodologyinvolving local residents and public transport service provider, and working within the framework of inflexible road trafficregulations concerning the operation and testing of autonomous vehicles, we conducted a participatory design workshop, aqualitative, and a survey study. The findings revealed differences across these four classes of signals in terms of pedestrians’subjective perceptions. Anthropomorphic signals were identified as the preferred and effective modality in terms of pedestrians’interpretation of the communicated intent and their perceived sense of attention, confidence, and calmness. Additionally,pedestrians’ experiences while judging the intention oftransitionaryvehicular states (starting/slowing) were reported asperplexing and evoked stress. These findings were translated into design and policy implications in collaboration with otherstakeholders, and exemplify a viable way for assimilating human factors research in urban mobility.@en