Evaluating an Assistive Robot for the Detection of Urinary Tract Infections

Urinary Tract Infections (UTIs) are highly prevalent and, if left untreated, can lead to serious health complications. While urine testing is an effective diagnostic tool, it is often conducted late in the infection’s progression. As part of a broader project exploring technology-driven approaches to early UTI detection, we introduce an assistive robot prototype designed to facilitate daily interactions with users. This robot gathers a range of information that may serve as potential earlyindicators of UTIs, through a three-tiered interaction framework, increasing in intensity from light conversational topics to structured clinical questionnaires. To assess the feasibility and effectiveness of this approach, we conduct a user study in a psueudo-home environment involving 15 individuals with a history of UTIs, spanning 55 interactive sessions. Findings reveal promising levels of engagement and acceptance and insight on our LLM-driven interaction as a feasible approach.We provide key next steps for improvement towards our long-term study in-situ, highlighting the need for a more robust conversational strategy and promoting agency through user-initiated interactions.