LGBTQ+ individuals are increasingly turning to chatbots powered by large language models (LLMs) to meet their mental health needs. However, little research has explored whether these chatbots can adequately and safely provide tailored support for this demographic. We interviewed 18 LGBTQ+ and 13 non-LGBTQ+ participants about their experiences with LLM-based chatbots for mental health needs. LGBTQ+ participants relied on these chatbots for mental health support, likely due to an absence of support in real life. Notably, while LLMs offer prompt support, they frequently fall short in grasping the nuances of LGBTQ-specific challenges. Although fine-tuning LLMs to address LGBTQ+ needs can be a step in the right direction, it isn’t the panacea. The deeper issue is entrenched in societal discrimination. Consequently, we call on future researchers and designers to look beyond mere technical refinements and advocate for holistic strategies that confront and counteract the societal biases burdening the LGBTQ+ community.

While previous HCI research has examined chronic care management for children, less is known about supporting families with young children facing serious illnesses. We interviewed 12 families affected by cystic fibrosis (CF) to understand their experiences and explore opportunities to support CF management. We identified three stages of CF management in young children: diagnosis at birth, parental navigation of CF management in the early years, and gradual involvement of children in their CF care. We underscore child development milestones as a key macro-temporal structure in children’s health management, the multifaceted and evolving parental values in crafting a safe place for children, and the balancing acts parents conduct to recreate this safe place as their children grow. We provide design implications to inform the future of child-centered and family-oriented health technologies that can evolve with parents’ and children’s values to assist in creating a safe environment for managing children’s health.

Families managing serious health conditions in children are often burdened not only by the challenge of health management but also by the heavy weight of stigma. To assist these families, various physical and digital support systems have been established to address their emotional and informational needs. We interviewed 32 children and parents living with serious chronic pulmonary illnesses to gain insights into their experiences with both their conditions and support systems. We discovered that, although a wide range of support systems were available, most participants chose to engage selectively with or completely withdraw from them. Using the ecological systems theory, we elucidate the presence of health-related and unintended stigmas associated with support systems across different ecological layers. Our work provides a comprehensive and dynamic perspective on these stigmas, considering technological, interpersonal, institutional, and social factors. By examining how stigma arises in social interactions, we introduce and delve into the concept of "stigma work" and offer design considerations for more empathetic support systems that attend to individuals and groups with stigmatized health conditions, identities, or experiences.

As the number of pre-trained machine learning (ML) models is growing exponentially, data reduction tools are not catching up. Existing data reduction techniques are not specifically designed for pre-trained model (PTM) dataset files. This is largely due to a lack of understanding of the patterns and characteristics of these datasets, especially those relevant to data reduction and compressibility. This paper presents the first, exhaustive analysis to date of PTM datasets on storage compressibility. Our analysis spans different types of data reduction and compression techniques, from hash-based data deduplication, data similarity detection, to dictionary-coding compression. Our analysis explores these techniques at three data granularity levels, from model layers, model chunks, to model parameters. We draw new observations that indicate that modern data reduction tools are not effective when handling PTM datasets. There is a pressing need for new compression methods that take into account PTMs' data characteristics for effective storage reduction. Motivated by our findings, we design Elf, a simple yet effective, error-bounded, lossy floating-point compression method. Elf transforms floating-point parameters in such a way that the common exponent field of the transformed parameters can be completely eliminated to save storage space. We develop Elves, a compression framework that integrates Elf along with several other data reduction methods. Elves uses the most effective method to compress PTMs that exhibit different patterns. Evaluation shows that Elves achieves an overall compression ratio of 1.52×, which is 1.31×, 1.32× and 1.29× higher than a general-purpose compressor (zstd), an error-bounded lossy compressor (SZ3), and the uniform model quantization, respectively, with negligible model accuracy loss.

Data-driven health technologies, such as wearables and medical devices, are increasingly part of children’s daily lives. These technologies help children collect, reflect on, and use their health data. The hope is that they develop healthy habits and skills and prepare themselves to manage their health and wellbeing. However, past research has shown that children, especially those of young age, have limited interactions with these technologies and often struggle to understand their health data. My dissertation research contributes to a comprehensive understanding of how children and their caregivers (i.e., parents and healthcare providers) perceive data-driven health technologies, and use the resulting data to improve children’s health. Drawing on findings from a systematic literature review, content analysis, qualitative interviews, and participatory design workshops, my dissertation research fosters discussion of children’s health data literacy and identifies design opportunities to build children’s health capacity through supporting their health data literacy.

Patient-generated health data (PGHD) is crucial for healthcare providers' decision making, as it complements clinical data by providing a more holistic view of patients' daily conditions. We interviewed 20 healthcare providers in asthma care to envision future technologies to support their PGHD use. We found that healthcare providers want future artificial intelligence (AI) systems to enhance their ability to treat patients by analyzing PGHD for profiling risk and predicting deterioration. Despite the potential benefits of AI, providers perceived various challenges of AI use with PGHD, including AI-driven data inequity, added burden, lack of trust toward AI, and fear of being replaced by AI. Clinicians wished for a future of co-dependent human-AI collaboration, where AI will help them to improve their clinical practice. In turn, healthcare providers can improve AI systems by making AI outputs more trustworthy and humane. Through the lens of data feminism, we discuss the importance of considering context and aligning the complex human infrastructure before designing or deploying PGHD-based AI systems in clinical settings. We highlight the opportunity to design for human-AI enrichment, where humans and AI not only partner with each other for improved performance, but also enrich each other to enhance each other's work overtime.

Children are increasingly using wearables with physical activity tracking features. Although research has designed and evaluated novel features for supporting parent-child collaboration with these wearables, less is known about how families naturally adopt and use these technologies in their everyday life. We conducted interviews with 17 families who have naturally adopted child-owned wearables to understand how they use wearables individually and collaboratively. Parents are primarily motivated to use child-owned wearables for children's long-term health and wellbeing, whereas children mostly seek out entertainment and feeling accomplished through reaching goals. Children are often unable to interpret or contextualize the measures that wearables record, while parents do not regularly track these measures and focus on deviations from their children's routines. We discuss opportunities for making naturally-occurring family moments educational to positively contribute to children's conceptual understanding of health, such as developing age-appropriate trackable metrics for shared goal-setting and data reflection.

OBJECTIVE: Qualitative methods are particularly well-suited to studying the complexities and contingencies that emerge in the development, preparation, and implementation of technological interventions in real-world clinical practice, and much remains to be done to use these methods to their full advantage. We aimed to analyze how qualitative methods have been used in health informatics research, focusing on objectives, populations studied, data collection, analysis methods, and fields of analytical origin. METHODS: We conducted a scoping review of original, qualitative empirical research in JAMIA from its inception in 1994 to 2019. We queried PubMed to identify relevant articles, ultimately including and extracting data from 158 articles. RESULTS: The proportion of qualitative studies increased over time, constituting 4.2% of articles published in JAMIA overall. Studies overwhelmingly used interviews, observations, grounded theory, and thematic analysis. These articles used qualitative methods to analyze health informatics systems before, after, and separate from deployment. Providers have typically been the main focus of studies, but there has been an upward trend of articles focusing on healthcare consumers. DISCUSSION: While there has been a rich tradition of qualitative inquiry in JAMIA, its scope has been limited when compared with the range of qualitative methods used in other technology-oriented fields, such as human-computer interaction, computer-supported cooperative work, and science and technology studies. CONCLUSION: We recommend increased public funding for and adoption of a broader variety of qualitative methods by scholars, practitioners, and policy makers and an expansion of the variety of participants studied. This should lead to systems that are more responsive to practical needs, improving usability, safety, and outcomes.

Spreadsheet systems are by far the most popular platform for data exploration on the planet, supporting millions of rows of data. However, exploring spreadsheets that are this large via operations such as scrolling or issuing formulae can be overwhelming and error-prone. Users easily lose context and suffer from cognitive and mechanical burdens while issuing formulae on data spanning multiple screens. To address these challenges, we introduce dynamic hierarchical overviews that are embedded alongside spreadsheets. Users can employ this overview to explore the data at various granularities, zooming in and out of the spreadsheet. They can issue formulae over data subsets without cumbersome scrolling or range selection, enabling users to gain a high or low-level perspective of the spreadsheet. An implementation of our dynamic hierarchical overview, NOAH, integrated within DataSpread, preserves spreadsheet semantics and look and feel, while introducing such enhancements. Our user studies demonstrate that NOAH makes it more intuitive, easier, and faster to navigate spreadsheet data compared to traditional spreadsheets like Microsoft Excel and spreadsheet plug-ins like Pivot Table, for a variety of exploration tasks; participants made fewer mistakes in NOAH while being faster in completing the tasks.