A Neural Topic-Attention Model for Medical Term Abbreviation Disambiguation

TL;DR

This paper introduces a neural topic-attention model for disambiguating medical abbreviations in clinical notes, leveraging few-shot learning and improved sentence representations to handle scarce and noisy data effectively.

Contribution

It presents a novel neural topic-attention approach combined with dataset correction and balanced evaluation for medical abbreviation disambiguation with limited labeled data.

Findings

Enhanced sentence representations improve disambiguation accuracy.

Topic information significantly boosts performance on small, unbalanced datasets.

Model outperforms baseline methods in experimental evaluations.

Abstract

Automated analysis of clinical notes is attracting increasing attention. However, there has not been much work on medical term abbreviation disambiguation. Such abbreviations are abundant, and highly ambiguous, in clinical documents. One of the main obstacles is the lack of large scale, balance labeled data sets. To address the issue, we propose a few-shot learning approach to take advantage of limited labeled data. Specifically, a neural topic-attention model is applied to learn improved contextualized sentence representations for medical term abbreviation disambiguation. Another vital issue is that the existing scarce annotations are noisy and missing. We re-examine and correct an existing dataset for training and collect a test set to evaluate the models fairly especially for rare senses. We train our model on the training set which contains 30 abbreviation terms as categories (on average, 479 samples and 3.24 classes in each term) selected from a public abbreviation disambiguation dataset, and then test on a manually-created balanced dataset (each class in each term has 15 samples). We show that enhancing the sentence representation with topic information improves the performance on small-scale unbalanced training datasets by a large margin, compared to a number of baseline models.