Vision-language models for radiology report drafting

Two companion research papers from Mosaic Clinical Technologies and Cognita evaluate our investigational vision-language models (VLMs) for CT and X-ray report drafting. A retrospective study of 237,905 exams across 50 conditions found additional expert-confirmed findings for every condition tested, averaging approximately 40% enhanced detection. Radiologists using the models in investigational clinical use saw efficiency gains of more than 27% on CT and 31% on X-ray.