Multilingual Evaluation of a Large Language Model-Based Primary Care Chatbot

Pre-visit planning has the potential to reduce EHR documentation burden while improving workflow efficiency, care quality, and patient–provider engagement. Large language model (LLM) chatbots show promise for supporting this task, but while their English-centric development suggests a potential for disparity, the extent to which these concerns translate into performance degradation in multilingual clinical settings remains unclear. In this mixed-methods study, we systematically evaluate the multilingual capabilities of PCP-Bot, an English-developed LLM-based (GPT-4o) clinical chatbot that collects patient concerns and generates structured, physician-ready summaries (∼200 words) under structured output constraints. We enrolled 31 bilingual individuals (11 Mandarin, 10 Spanish, 10 Hindi) to role-play as patients to evaluate the PCP-Bot, interacting with it across five synthetic clinical cases in both English and a second language. Participants completed a structured survey comprising baseline language proficiency screening, standardized interactions with PCP-Bot in each language, and post-interaction evaluations. Case order was randomized, with each scenario completed first in English and subsequently in the participant’s second language. All summaries were generated in English, regardless of the interaction language. Our results show that Hindi achieved usability and conversation quality parity with English across all measured dimensions. Mandarin achieved usability parity but showed a significant conversation quality gap relative to English. Spanish demonstrated significant deficits in both conversation quality and summary quality. Trust and workload remained consistent across languages. Qualitatively, participants found PCP-Bot natural, smooth, and accurate overall, but noted repetition, transcription errors, missed follow-ups, and more frequent usability issues in non-English interactions. Overall, our findings demonstrate that LLM translation capabilities can enable effective deployment beyond English following appropriate performance validation.