Generative AI enables designers to more broadly and rapidly explore design spaces. However, the sheer scale at which designs can be generated makes it difficult to identify which generated concepts deserve further attention. To support this identification process, we explore pupillometry—specifically pupil dilation—as a support signal for design evaluation. We conducted a study with 40 participants who viewed AI-generated bicycle designs while wearing eye tracking glasses to measure pupil dilation and rated designs on perceived surprise, valence, and feasibility.

We present BioSpark, a system for analogical innovation designed to act as a creativity partner in reducing the cognitive effort in finding, mapping, and creatively adapting diverse inspirations. While prior approaches have focused on initial stages of finding inspirations, BioSpark uses LLMs embedded in a familiar, visual, Pinterest-like interface to go beyond inspiration to supporting users in identifying the key solution mechanisms, transferring them to the problem domain, considering tradeoffs, and elaborating on details and characteristics. To accomplish this BioSpark introduces several novel contributions, including a tree-of-life enabled approach for generating relevant and diverse inspirations, as well as AI-powered cards including 'Sparks' for analogical transfer; 'Trade-offs' for considering pros and cons; and 'Q&A' for deeper elaboration. We evaluated BioSpark through workshops with professional designers and a controlled user study, finding that using BioSpark led to a greater number of generated ideas; those ideas being rated higher in creative quality; and more diversity in terms of biological inspirations used than a control condition. Our results suggest new avenues for creativity support tools embedding AI in familiar interaction paradigms for designer workflows.

With recent advancements in the capabilities of Text-to-Image (T2I) AI models, product designers have begun experimenting with them in their work. However, T2I models struggle to interpret abstract language and the current user experience of T2I tools can induce design fixation rather than a more iterative, exploratory process. To address these challenges, we developed Inkspire, a sketch-driven tool that supports designers in prototyping product design concepts with analogical inspirations and a complete sketch-to-design-to-sketch feedback loop. To inform the design of Inkspire, we conducted an exchange session with designers and distilled design goals for improving T2I interactions. In a within-subjects study comparing Inkspire to ControlNet, we found that Inkspire supported designers with more inspiration and exploration of design ideas, and improved aspects of the co-creative process by allowing designers to effectively grasp the current state of the AI to guide it towards novel design intentions.

Prototyping AI user experiences is challenging due in part to probabilistic AI models making it difficult to anticipate, test, and mitigate AI failures before deployment. In this work, we set out to support practitioners with early AI prototyping, with a focus on natural language (NL)-based technologies. Our interviews with 12 NL practitioners from a large technology company revealed that, in addition to challenges prototyping AI, prototyping was often not happening at all or focused only on idealized scenarios due to a lack of tools and tight timelines. These findings informed our design of the AI Playbook, an interactive and low-cost tool we developed to encourage proactive and systematic consideration of AI errors before deployment. Our evaluation of the AI Playbook demonstrates its potential to 1) encourage product teams to prioritize both ideal and failure scenarios, 2) standardize the articulation of AI failures from a user experience perspective, and 3) act as a boundary object between user experience designers, data scientists, and engineers.

Adolescents with chronic conditions must work with family caregivers to manage their illness experiences. To explore how technology can support collaborative documentation of these experiences, we designed and distributed a paper diary probe kit in a two-week field deployment with 12 adolescent-parent dyads (24 participants). Three insights emerged from the study that highlight how technology can support shared illness management: 1) provide scaffolds to recognize physical and emotional experiences in the context of daily activities; 2) help families reconstruct patient experiences; and 3) adapt to individual preferences for capturing, representing and sharing experiences. We discuss opportunities for HCI research that follow from these findings and conclude by reflecting on the benefits and limitations of using diary probes with adolescent patients and their parental caregivers.

Teens with complex chronic illnesses have difficulty understanding and articulating symptoms such as pain and emotional distress. Yet, symptom communication plays a central role in clinical care and illness management. To understand how design can help overcome these challenges, we created a visual library of 72 sketched illustrations, informed by the Observations of Daily Living framework along with insights from 11 clinician interviews. We utilized our library with storyboarding techniques, free-form sketching, and interviews, in co-design sessions with 13 pairs of chronically-ill teens and their parents. We found that teens depicted symptoms as being interwoven with narratives of personal and social identity. Teens and parents were enthusiastic about collaboratively-generated, interactive storyboards as a tracking and communication mechanism, and suggested three ways in which they could aid in communication and coordination with informal and formal caregivers. In this paper, we detail these findings, to guide the design of tools for symptom-tracking and incorporation of patient-generated data into pediatric care.

Objective: Parents routinely access young children's medical records, but medical societies strongly recommend confidential care during adolescence, and most medical centers restrict parental records access during the teen years. We sought to assess public opinion about adolescent medical privacy. Materials and Methods: The Cornell National Social Survey (CNSS) is an annual nationwide public opinion survey. We added questions about a) whether parents should be able to see their 16-year-old child's medical record, and b) whether teens would avoid discussing sensitive issues (sex, alcohol) with doctors if parents could see the record. Hypothesizing that highlighting the rationale for adolescent privacy would change opinions, we conducted an experiment by randomizing question order. Results: Most respondents (83.0%) believed that an adolescent would be less likely to discuss sensitive issues with doctors with parental medical record access; responses did not differ by question order (P = .29). Most also believed that parents should have access to teens' records, but support for parental access fell from 77% to 69% among those asked the teen withholding question first (P = .01). Conclusions: Although medical societies recommend confidential care for adolescents, public opinion is largely in favor of parental access. A brief "nudge," asking whether parental access might harm adolescent-doctor communication, increased acceptance of adolescent confidentiality, and could be part of a strategy to prepare parents for electronic patient portal policies that medical centers impose at the beginning of adolescence.

Objective: Medical privacy policies, which are clear-cut for adults and young children, become ambiguous during adolescence. Yet medical organizations must establish unambiguous rules about patient and parental access to electronic patient portals. We conducted a national interview study to characterize the diversity in adolescent portal policies across a range of institutions and determine the factors influencing decisions about these policies. Methods: Within a sampling framework that ensured diversity of geography and medical organization type, we used purposive and snowball sampling to identify key informants. Semi-structured interviews were conducted and analyzed with inductive thematic analysis, followed by a member check. Results: We interviewed informants from 25 medical organizations. Policies established different degrees of adolescent access (from none to partial to complete), access ages (from 10 to 18 years), degrees of parental access, and types of information considered sensitive. Federal and state law did not dominate policy decisions. Other factors in the decision process were: technology capabilities; differing patient population needs; resources; community expectations; balance between information access and privacy; balance between promoting autonomy and promoting family shared decision-making; and tension between teen privacy and parental preferences. Some informants believed that clearer standards would simplify policy-making; others worried that standards could restrict high-quality polices. Conclusions: In the absence of universally accepted standards, medical organizations typically undergo an arduous decision-making process to develop teen portal policies, weighing legal, economic, social, clinical, and technological factors. As a result, portal access policies are highly inconsistent across the United States and within individual states.

Diagnostic radiology reports are increasingly being made available to patients and their family members. However, these reports are not typically comprehensible to lay recipients, impeding effective communication about report findings. In this paper, we present three studies informing the design of a prototype to foster patient-clinician communication about radiology report content. First, analysis of questions posted in online health forums helped us identify patients' information needs. Findings from an elicitation study with seven radiologists provided necessary domain knowledge to guide prototype design. Finally, a clinical field study with 14 pediatric patients, their parents and clinicians, revealed positive responses of each stakeholder when using the prototype to interact with and discuss the patient's current CT or MRI report and allowed us to distill three use cases: co-located communication, preparing for the consultation, and reviewing radiology data. We draw on our findings to discuss design considerations for supporting each of these use cases.

Adolescents with complex chronic illnesses, such as cancer and blood disorders, must partner with family and clinical caregivers to navigate risky procedures with life-altering implications, burdensome symptoms and lifelong treatments. Yet, there has been little investigation into how technology can support these partnerships. We conducted 38 in-depth interviews (15 with teenage adolescents with chronic forms of cancer and blood disorders, 15 with their parents, and eight with clinical caregivers) along with nine non-participant observations of clinical consultations to better understand common challenges and needs that could be supported through design. Participants faced challenges primarily concerning: 1) teens' limited participation in their care, 2) communicating emotionally-sensitive information, and 3) managing physical and emotional responses. We draw on these findings to propose design goals for sociotechnical systems to support teens in partnering in their care, highlighting the need for design to support gradually evolving partnerships in care.