Clinical Relationships Extraction Techniques from Patient Narratives

TL;DR

This paper presents a system that extracts clinical relationships from patient narratives using domain-specific grammars and supervised machine learning, aiming to support clinical research and healthcare informatics.

Contribution

It combines rule-based and machine learning approaches for relationship extraction from clinical texts, with an analysis of various features and algorithms.

Findings

Supervised ML approaches effectively extract clinical relationships.

Feature selection impacts extraction accuracy.

Different algorithms and corpus sizes influence performance.

Abstract

The Clinical E-Science Framework (CLEF) project was used to extract important information from medical texts by building a system for the purpose of clinical research, evidence-based healthcare and genotype-meets-phenotype informatics. The system is divided into two parts, one part concerns with the identification of relationships between clinically important entities in the text. The full parses and domain-specific grammars had been used to apply many approaches to extract the relationship. In the second part of the system, statistical machine learning (ML) approaches are applied to extract relationship. A corpus of oncology narratives that hand annotated with clinical relationships can be used to train and test a system that has been designed and implemented by supervised machine learning (ML) approaches. Many features can be extracted from these texts that are used to build a model by the classifier. Multiple supervised machine learning algorithms can be applied for relationship extraction. Effects of adding the features, changing the size of the corpus, and changing the type of the algorithm on relationship extraction are examined. Keywords: Text mining; information extraction; NLP; entities; and relations.