PeruMedQA: Benchmarking Large Language Models (LLMs) on Peruvian Medical Exams -- Dataset Construction and Evaluation
This addresses the need for medical AI applications in Spanish-speaking Latin American countries like Peru, though it is incremental as it applies existing methods to new data.
The researchers tackled the problem of evaluating large language models (LLMs) on Peruvian medical exams by constructing the PeruMedQA dataset with 8,380 questions and fine-tuning models, finding that medgemma-27b-text-it achieved over 90% accuracy in some cases and a fine-tuned medgemma-4b-it rivaled a 70-billion-parameter model.
BACKGROUND: Medical large language models (LLMS) have demonstrated remarkable performance in answering medical examinations. However, the extent to which this high performance is transferable to medical questions in Spanish and from a Latin American country remains unexplored. This knowledge is crucial as LLM-based medical applications gain traction in Latin America. AIMS: to build a dataset of questions from medical examinations taken by Peruvian physicians pursuing specialty training; to fine-tune a LLM on this dataset; to evaluate and compare the performance in terms of accuracy between vanilla LLMs and the fine-tuned LLM. METHODS: We curated PeruMedQA, a multiple-choice question-answering (MCQA) datasets containing 8,380 questions spanning 12 medical domains (2018-2025). We selected eight medical LLMs including medgemma-4b-it and medgemma-27b-text-it, and developed zero-shot task-specific prompts to answer the questions appropriately. We employed parameter-efficient fine tuning (PEFT)and low-rant adaptation (LoRA) to fine-tune medgemma-4b-it utilizing all questions except those from 2025 (test set). RESULTS: medgemma-27b-text-it outperformed all other models, achieving a proportion of correct answers exceeding 90% in several instances. LLMs with <10 billion parameters exhibited <60% of correct answers, while some exams yielded results <50%. The fine-tuned version of medgemma-4b-it emerged victorious agains all LLMs with <10 billion parameters and rivaled a LLM with 70 billion parameters across various examinations. CONCLUSIONS: For medical AI application and research that require knowledge bases from Spanish-speaking countries and those exhibiting similar epidemiological profiles to Peru's, interested parties should utilize medgemma-27b-text-it or a fine-tuned version of medgemma-4b-it.