Artificial intelligence (AI) supported clinical decision support (CDS) technologies can parse vast quantities of patient data into meaningful insights for healthcare providers. Much work is underway to determine the technical feasibility and the accuracy of AI-driven insights. Much less is known about what insights are considered useful and actionable by healthcare providers, their trust in the insights, and clinical workflow integration challenges. Our research team used a conceptual prototype based on AI-generated treatment insights for type 2 diabetes medications to elicit feedback from 41 U.S.-based clinicians, including primary care and internal medicine physicians, endocrinologists, nurse practitioners, physician assistants, and pharmacists. We contribute to the human-computer interaction (HCI) community by describing decision optimization and design objective tensions between population-level and personalized insights, and patterns of use and trust of AI systems. We also contribute a set of 6 design principles for AI-supported CDS.

A growing body of research has examined whether and how an individual can leverage online social networks to receive social support for health behavior change. This prior research largely focuses on attributes of the post content and the experiences and concerns of people posting. Less is known about moderators and mediators that influence whether and how one's social network will respond to a request for support. Using a factorial survey experiment, we find evidence that attitudes toward specific types of health behaviors greatly increase likelihood of response to a post, and that targeting close-tie relationships may increase effectiveness of social media based behavior change interventions, particularly related to smoking cessation.

In this paper, we present disruption of household routines as a method to study home technology usage.Using three case studies as guidance, we show how disrupting household practices-either through changing the technology, task or division of labor-can provide valuable insight into current and future technology usage, and can guide the design of future technologies.Based on our case studies, we outline best practices and challenges with respect to the pragmatics of disruptive research methods. RESEARCH HIGHLIGHTS• We present disruption as a method for studying technology use in homes.• Grounded in three case studies, we provide best practices for using this method.• We address pragmatic and ethical challenges of using disruption as a method.

This paper presents the results of an ongoing study into the potential role of mobile or wireless health applications for targeting the prevention of excessive gestational weight gain in pregnant lower-income American women. Informed by a qualitative study of pregnant women's experiences, we develop a set of design requirements for designing mobile health (mHealth) interventions related to healthy pregnancies. We identify a disconnection between physical activity and food tracking application design paradigms, and the reality of pregnant women's lives and capacities. We introduce the concept of an individualized pregnancy ecology, which provides an alternative paradigm for design of health and wellness management tools for lower-income pregnant women.

Many people struggle with their weight and are turning to online communities for social and informational support. The aim of this study is to understand the issues commonly discussed in online weight loss communities. Through observation and content analysis of threads in one specific weight loss community, we identified 17 distinct categories discussed by the participants. We detail four categories specifically: Personal Experience, Consumption Choices, Dieting Strategy, and Exercise. Our analysis describes some key user roles and states that often relate to different phases of a person's weight loss journey. We identify a set of transient states, which are not proper roles but are significant in an online community where individuals are attempting to change their own behaviors. We close with design suggestions for encouraging and maintaining participant engagement in an online health community

Prior research describes how households coordinate to resolve technology complexity in residential settings. In this paper, we examine how social roles and routines of use can potentially hinder the development of technological literacy. Through this short paper, we aim to open a discussion about ways to increase technological literacy of the public.

Adolescents represent nearly one-fifth of the planet's population, yet the interaction design literature offers little guidance on the unique needs, opportunities, and challenges of designing for this age group. In this paper, we provide guidance on interaction design with adolescents, grounded in methodological and behavioral sciences literature. We clarify what adolescence is and what the needs of adolescents are with respect to their cognitive, emotional, social, and physical changes. We present and discuss common pitfalls that can occur in research and design projects involving adolescent populations. We single out of video data gathering methods as a particularly apropos approach to understanding teen populations and offer up an overview our own approach to videography, called 'mobile video collage'. We conclude with a call to the field of interaction design and children to better understand the unique position, needs and values of adolescents.

Technology-based interventions for promoting health behavior-change frequently leverage multiplayer game mechanics such as group-based competitions. However, health interventions successful for groups writ large may not always translate to successful behavior change at the individual level. In this paper, we explore the tension between group and individual success, based on an empirical study on a long-term real-world deployment of a pervasive health game for youth. We report five distinctive player types along the dimensions of motivation, behavior, and influence on others. Based on the findings, we provide design suggestions to help game designers integrate group-based mechanisms that maximize intervention effectiveness.

Technology-based health behavior change interventions involving passive on-body sensing and feedback interfaces show promise for increasing participation in physical activity. However, the majority of prior studies are small-scale interventions that heavily rely on research teams for programmatic support. In larger-scale deployments, participants may have to take over setup and maintenance tasks. In this paper, we examine the "hidden work" involved with the large-scale deployment of a behavior change application in American schools. We offer insight into the coordination required to maintain such deployments, and identify unique challenges that arise when schoolchildren are the target of a behavior change intervention. Our findings highlight the behind-the-scenes coordination and management work required of adult facilitators in order to support pervasive health interventions for children in school environments. We offer advice to researchers and project managers attempting integration of technology-based health behavior change applications for children.

Why do user experience problems with home computing persist, despite several decades worth of academic study and countless technological innovations to overcome these issues? This paper presents the results of a multi-week trial investigating technical support practices in North American homes using a combination of breaching experiments and custom software. What this study uncovered was not a one-size-fits-all solution to technical problems in residential settings, but instead a rich description of the articulation work required to acquire devices, maintain and configure them over time, and seek help when problems occur. Based on this study, I argue that many of the user experience problems experienced with home computing and electronics are due to issues related to individual agency rather than technical or user interface characteristics of any given technology combination. Additionally, I make a case for the use of breaching experiments to study phenomenon related to technologies infrastructures that are difficult to capture via other traditionally used methods.

Active video games (AVG) have become widespread as more physical interfaces are introduced in video games. Lab based studies have indicated that AVGs can increase the amount and intensity of physical activity compared to non-active games and TV, however, the long-term effectiveness of AVGs has yet been established. In fact, most of the existing studies show a reduction of interest and participation over time. This paper presents our findings from a long-term, multi-site deployment of a pervasive health game, the American Horsepower Challenge (AHPC). Similar to previous studies, our findings also show reduced effectiveness of the game, but on a much larger scale. Moreover, we analyze reasons for this and report what kind of game related online and offline activities happened during the deployment. We argue that a shift of evaluation metrics and design goals is required to make real-world sustainable behavior changes. Based on empirical data, we propose three goals for AVGs---sustainability, adaptability and sociability. Behavior-changing games can learn how to achieve these goals from existing game genres, such as alternate reality games, location-based games, family games, and multiplayer online games etc.

With rising concerns about obesity and sedentary lifestyles in youth, there has been an increasing interest in understanding how pervasive and ubiquitous computing technologies can catalyze positive health behaviors in children and teens. School-based interventions seem like a natural choice, and ubiquitous computing technologies hold much promise for these interventions. Yet the literature contains little guidance for how to approach school-based ubicomp deployments. Grounded in our analysis of a large-scale US school-based intervention for promoting youth physical activity, we present an approach to the design and evaluation of school-based ubicomp that treats the school as a social institution. We show how the school regulates students' daily lives, drawing from work in the sociology of schools to create a framing for planning, executing and analyzing school-based ubicomp deployments. These insights will assist other researchers and designers engaging in deployments of ubiquitous computing systems in settings with established institutional structures.

In this paper, we present an entry for the 2011 MobileHCI design competition. Our aim is to define the "essence" of mobile communication and connectivity, and illustrate it via a design example called Spaces Without Faces, an application to locate quiet study spaces on a university campus. We argue that the essence of mobile communication and connectivity, no matter the form factor of the phone, comes not from the ability to make text and voice calls, but rather to use the phone as a device for obtaining information about resources in nearby physical environments.

HCI endeavors to create human-centered computer systems, but underlying technological infrastructures often stymie these efforts. We outline three specific classes of user experience difficulties caused by underlying technical infrastructures, which we term constrained possibilities, unmediated interaction, and interjected abstractions. We explore how prior approaches in HCI have addressed these issues, and discuss new approaches that will be required for future progress. We argue that the HCI community must become more deeply involved with the creation of technical infrastructures. Doing so, however, requires a substantial expansion to the methodological toolbox of HCI.

Conflict and disruption are a part of everyday life, yet research in the home largely examines consensus and rituals. In this paper, we use Holmes and Rahe's categorization of major life events in order to investigate disruption within the home. We examine posts contributed to an online technology support board and show how life disruptions fundamentally impact technology practices and routines. We conclude that examining technology in the context of life disruption is a worthwhile area for further work.

The Value Sensitive Design (VSD) methodology provides a comprehensive framework for advancing a value-centered research and design agenda. Although VSD provides helpful ways of thinking about and designing value-centered computational systems, we argue that the specific mechanics of VSD create thorny tensions with respect to value sensitivity. In particular, we examine limitations due to value classifications, inadequate guidance on empirical tools for design, and the ways in which the design process is ordered. In this paper, we propose ways of maturing the VSD methodology to overcome these limitations and present three empirical case studies that illustrate a family of methods to effectively engage local expressions of values. The findings from our case studies provide evidence of how we can mature the VSD methodology to mitigate the pitfalls of classification and engender a commitment to reflect on and respond to local contexts of design.

Prior research suggests that people may ask their family and friends for computer help. But what influences whether and how a "helper" will provide help? To answer this question, we conducted a qualitative investigation of people who participated in computer support activities with family and friends in the past year. We describe how factors including maintenance of one's personal identity as a computer expert and accountability to one's social network determine who receives help and the quality of help provided. We also discuss the complex, fractured relationship between the numerous stakeholders involved in the upkeep of home computing infrastructures. Based on our findings, we provide implications for the design of systems to support informal help-giving in residential settings.

Householders are increasingly adopting home networking as a solution to the demands created by the presence of multiple computers, devices, and the desire to access the Internet. However, current network solutions are derived from the world of work (and initially the military) and provide poor support for the needs of the home. We present the key findings to emerge from empirical studies of home networks in the UK and US. The studies reveal two key kinds of work that effective home networking relies upon: one, the technical work of setting up and maintaining the home network, and the other, the collaborative and socially organized work of the home which the network is embedded in and supports. The two are thoroughly intertwined and rely upon one another for their realization, yet neither is adequately supported by current networking technologies and applications. Explication of the “work to make the home network work” opens up the design space for the continued integration of the home network in domestic life and elaboration of future support. Key issues for development include the development of networking facilities that do not require advanced networking knowledge, that are flexible and support the local social order of the home and the evolution of its routines, and which ultimately make the home network visible and accountable to household members.

As computing migrates from the workplace to the home, householders must tackle problems of home network maintenance. Often they lack the technical knowledge or motivation to complete these tasks, making the user experience of home network maintenance frustrating. In response to these difficulties, many householders rely on handwritten reminders or interactive networking tools that are ill-suited for the home environment. In this paper, we seek to understand how to design better home network management tools through a study of sketches created by 40 people in 18 households. In our study, we obtained information about householders' knowledge, practices and needs with respect to home networking. Based on our results, we present guidelines for transforming the user experience of home network management.

How can designers of ubiquitous computing technologies ensure that they understand the non-functional needs, values, and expectations of end-users? In this paper, we use a qualitative method from public policy to elicit reflective feedback from end-users about technologies that they may not yet have used nor fully comprehend. Our study uncovers information about end-user perceptions of RFID, including a range of "folk theories" held by the public about this technology, and their associations of it with certain social groups and values. We argue that these perceptions can limit technological adoption, and conclude with a discussion of challenges for the design and deployment of ubiquitous computing systems.

For much of the industrialized world, network connectivity in the home is commonplace. Despite the large number of networked homes, even the most technically savvy people can have difficulties with home network installation and maintenance. We contend that these problems will not disappear over time as the networking industry matures, but rather are due to structural usability flaws inherent in the design of existing network infrastructure, devices, and protocols. The HCI community can offer a unique perspective to overcoming the challenges associated with home networking. This paper discusses why home networking is difficult, based on analysis of historical, social, and technical factors. It explores how the designs of existing home networking technologies have implications for usability, and examines a range of models for addressing these usability challenges. The paper concludes with a discussion of how these models may impact future research efforts in both HCI and networking.

End-users are often perceived as the weakest link in information security. Because of this perception, a growing body of research and commercial activity is focused on automated approaches to security. With these approaches, security decisions are removed from the hands of the users, and are placed instead in systems themselves, or in remote services or organizations that establish policies that are automatically enforced. We contend that although security automation is potentially beneficial in theory, in practice it is not a panacea for end-user information security. A number of technical and social factors mitigate against the acceptance and efficacy of automated end-user security solutions in many cases. In this paper, we present a discussion of the inherent limitations of automating security for end-users. We then discuss a set of design guidelines for choosing whether to automate end-user security systems. We conclude with a set of research directions focused on increasing the acceptance and efficacy of security solutions for end-users.

As computer networking has moved out of managed environments and into the home, householders - whether they want to or not - have had to tackle problems of home network maintenance. Unlike in enterprise environments, however, householders often do not plan or manage for network growth. In this paper, the author presents the results of a preliminary study examining householders' conceptual models of their home networks. He then examines characteristics of home networking technology leading to difficulties in setup and maintenance tasks. The author concludes by proposing future research focused on visual tools that empower all householders to understand and maintain their home networks.