Existing methods for the communication of follow-up healthcare, medication instructions, and diagnostic information have been reported as ineffective for Limited English Proficiency (LEP) patients, leading to a disproportionate number of adverse events and longer hospital stays for LEP patients compared to English-speaking patients. Instead of relying on traditional translation methods, our service seeks to utilize visual-learning to overcome language and health literacy barriers. Thus, leveraging Large Language Models (LLMs) to automatically generate pictographic translations of medical instructions may have the potential to bridge this gap in communication for LEP patients. To address this need, with the input of physicians, nurses, and pharmacists from Bayview Hospital, we developed a syntax for pictographic representations of medication instructions provided during hospital discharge. Generated images were tested for comprehension accuracy through the use of surveys. Using this syntax, we developed a service involving the translation of verbal medication instructions into pictographs.

Team Members

[foreach 357]

• [if 397 not_equal=””][/if 397][395]

[/foreach 357]

Project Mentors, Sponsors, and Partners

• Tania Maria Caballero, MD, MHS

• Sara Elizabeth Mixter, MD, MPH

• Alice Jenh Hsu, Pharm.D., BCPS AQ-ID

• Sara Maria Munoz-Blanco, MD

• Noah Lu

Course Faculty

[foreach 429]

• [if 433 not_equal=””][/if 433][431]

[/foreach 429]

Project Links

• Project Poster Image

• Project Poster PDF

Additional Project Information