Radiological reports typically summarize the content and interpretation of imaging studies in unstructured form that precludes quantitative analysis. This limits the monitoring of radiological services to throughput undifferentiated by content, impeding specific, targeted operational optimization. Here we present Neuradicon, a natural language processing (NLP) framework for quantitative analysis of neuroradiological reports. Our framework is a hybrid of rule-based and artificial intelligence models to represent neurological reports in succinct, quantitative form optimally suited to operational guidance. We demonstrate the application of Neuradicon to operational phenotyping of a corpus of 336,569 reports, and report excellent generalizability across time and two independent healthcare institutions.
@article{arxiv.2107.10021,
title = {Neuradicon: operational representation learning of neuroimaging reports},
author = {Henry Watkins and Robert Gray and Adam Julius and Yee-Haur Mah and Walter H. L. Pinaya and Paul Wright and Ashwani Jha and Holger Engleitner and Jorge Cardoso and Sebastien Ourselin and Geraint Rees and Rolf Jaeger and Parashkev Nachev},
journal= {arXiv preprint arXiv:2107.10021},
year = {2025}
}