Tina Yi Jin Hsieh

A medically grounded LLM agent–based tool to detect patient safety events in medical records

Large language models (LLMs) have shown incredible promise in medicine. While LLMs may be particularly useful in areas requiring extensive review of clinical records, their use remains limited due to their tendency to hallucinate and fabricate information. Hallucination issues, a...

Remote Recruitment to Diversify Infant Research Participation: Lessons From the Infant Vaccine Biepository

AIM: To determine whether remote recruitment, electronic consent and at-home blood collection enabled enrollment of a geographically and socioeconomically diverse infant cohort in the United States (US). METHODS: We describe the demographics of 256 infants included in this analys...