Assessing Completeness of Clinical Histories Accompanying Imaging Orders Using Adapted Open-Source and Closed-Source Large Language Models
David B. Larson, Arogya Koirala, Lina Cheuy, Magdalini Paschali, Dave Van Veen, Hye Sun Na, Matthew Petterson, Zhongnan Fang, Akshay Chaudhari
Abstract
= .31) despite being a smaller model. Using Mistral-7B, 26.2% (12 803 of 48 942) of unannotated clinical histories were found to contain all five elements. Conclusion An easily deployable fine-tuned open-source LLM (Mistral-7B), rivaling GPT-4 Turbo in performance, could effectively extract clinical history elements with substantial agreement with radiologists and produce a benchmark for completeness of a large sample of clinical histories. The model and code will be fully open-sourced. © RSNA, 2025
Topics & Concepts
MedicineCompleteness (order theory)Open sourceClinical historySource modelClinical PracticeArtificial intelligenceMedical physicsProgramming languageSurgeryTheoretical computer scienceComputer scienceMathematical analysisFamily medicineSoftwareMathematicsRadiology practices and educationRadiomics and Machine Learning in Medical ImagingArtificial Intelligence in Healthcare and Education