Towards more patient friendly clinical notes through language models and ontologies
This addresses the challenge for patients who struggle to understand complex medical notes, though it is incremental as it builds on existing text simplification techniques.
The paper tackles the problem of making clinical notes more accessible to patients by automatically simplifying medical text, using a method based on language models and ontologies that surpasses the state of the art in generating simpler sentences while preserving grammar and meaning.
Clinical notes are an efficient way to record patient information but are notoriously hard to decipher for non-experts. Automatically simplifying medical text can empower patients with valuable information about their health, while saving clinicians time. We present a novel approach to automated simplification of medical text based on word frequencies and language modelling, grounded on medical ontologies enriched with layman terms. We release a new dataset of pairs of publicly available medical sentences and a version of them simplified by clinicians. Also, we define a novel text simplification metric and evaluation framework, which we use to conduct a large-scale human evaluation of our method against the state of the art. Our method based on a language model trained on medical forum data generates simpler sentences while preserving both grammar and the original meaning, surpassing the current state of the art.