Darshi Shah
Recent breakthroughs in large language models (LLMs) have generated both interest and concern about their potential adoption asinformation sources or communication tools across different domains. In public health, where stakes are high and impacts extendacross diverse populations, adopting LLMs poses unique challenges that require thorough evaluation. However, structured approachesfor assessing potential risks in public health remain under-explored. To address this gap, we conducted focus groups with publichealth professionals and individuals with lived experience to unpack their concerns, situated across three distinct and critical publichealth issues that demand high-quality information: infectious disease prevention (vaccines), chronic and well-being care (opioiduse disorder), and community health and safety (intimate partner violence). We synthesize participants’ perspectives into a risktaxonomy, identifying and contextualizing the potential harms LLMs may introduce when positioned alongside traditional healthcommunication. This taxonomy highlights four dimensions of risk to individuals, human-centered care, information ecosystem, andtechnology accountability. For each dimension, we unpack specific risks and offer example reflection questions to help practitionersadopt a risk-reflexive approach. By summarizing distinctive LLM characteristics and linking them to identified risks, we discuss theneed to revisit prior mental models of information behaviors and complement evaluations with external validity and domain expertisethrough lived experience and real-world practices. Together, this work contributes a shared vocabulary and reflection tool for peoplein both computing and public health to collaboratively anticipate, evaluate, and mitigate risks in deciding when to employ LLMcapabilities (or not) and how to mitigate harm.
Widespread stigma, both in the offline and online spaces, acts as a barrier to harm reduction efforts in the context of opioid use disorder (OUD). This stigma is prominently directed towards clinically approved medications for addiction treatment (MAT), people with the condition, and the condition itself. Given the potential of artificial intelligence based technologies in promoting health equity, and facilitating empathic conversations, this work examines whether large language models (LLMs) can help abate OUD-related stigma in online communities. To answer this, we conducted a series of pre-registered randomized controlled experiments, where participants read LLM-generated, human-written, or no responses to help seeking OUD-related content in online communities. The experiment was conducted under two setups, i.e., participants read the responses either once (N = 2,141), or repeatedly for 14 days (N = 107). We found that participants reported the least stigmatized attitudes toward MAT after consuming LLM-generated responses under both the setups. This study offers insights into strategies that can foster inclusive online discourse on OUD, e.g., based on our findings LLMs can be used as an education-based intervention to promote positive attitudes and increase people's propensity toward MAT.
This project presents a user-centered design approach to integrating menstrual health support into Hinge Health’s physical therapy app, with a focus on addressing the needs of individuals aged 18–30 experiencing primary dysmenorrhea. Through a combination of literature review, survey data, user interviews, competitive analysis, and iterative prototyping, we identified key pain points and opportunities in the current menstrual health support. Our findings revealed strong user demand for personalized, cycle-aware exercise guidance and trustworthy insights across different phases of the menstrual cycle. In response, we designed and validated a prototype that extends Hinge Health’s pelvic pain program by incorporating menstrual cycle tracking, dynamic exercise recommendations, and intuitive progress visualization. The final design aims to empower users who experience menstrual pain by enhancing body awareness, delivering personalized physical therapy-based pain management, and supporting overall quality of life.