Towards more patient friendly clinical notes through language models and ontologies

Abstract

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.

Figure 1:

A flow diagram of the simplification algorithm.

Figure 2:

Grid search results for α values between 0 and 1 with a step of 0.05. Additional tests with step 0.01 were conducted for values between 0.90 and 1. The best performing α values for each model are 0.70 for the ngram, 0.90 for GPT-1, and 0.60 for GPT-2.