Structured prediction models for RNN based sequence labeling in clinical text

TL;DR

This paper explores advanced structured prediction models combining CRFs and RNNs to improve medical entity recognition in clinical texts, addressing domain-specific challenges for more accurate extraction.

Contribution

It introduces extensions to LSTM-CRF models with pairwise potentials and proposes an approximate skip-chain CRF inference method tailored for clinical text analysis.

Findings

Enhanced phrase detection accuracy for medical entities

Effective modeling of pairwise potentials in RNN-CRF frameworks

Improved structured prediction performance in clinical NLP

Abstract

Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies for structured prediction in order to improve the exact phrase detection of various medical entities.