Extracting medications and associated adverse drug events using a natural language processing system combining knowledge base and deep learning

Abstract

Objective: Detecting adverse drug events (ADEs) and medications related information in clinical notes is important for both hospital medical care and medical research. We describe our clinical natural language processing (NLP) system to automatically extract medical concepts and relations related to ADEs and medications from clinical narratives. This work was part of the 2018 National NLP Clinical Challenges Shared Task and Workshop on Adverse Drug Events and Medication Extraction.

Materials and methods: The authors developed a hybrid clinical NLP system that employs a knowledge-based general clinical NLP system for medical concepts extraction, and a task-specific deep learning system for relations identification using attention-based bidirectional long short-term memory networks.

Results: The systems were evaluated as part of the 2018 National NLP Clinical Challenges challenge, and our attention-based bidirectional long short-term memory networks based system obtained an F-measure of 0.9442 for relations identification task, ranking fifth at the challenge, and had <2% difference from the best system. Error analysis was also conducted targeting at figuring out the root causes and possible approaches for improvement.

Conclusions: We demonstrate the generic approaches and the practice of connecting general purposed clinical NLP system to task-specific requirements with deep learning methods. Our results indicate that a well-designed hybrid NLP system is capable of ADE and medication-related information extraction, which can be used in real-world applications to support ADE-related researches and medical decisions.

Keywords: LSTM; UMLS; adverse drug events; attention; clinical natural language processing.

Figure 1.

Architecture of the hybrid system. This system consists of a knowledge-based entity system using Unified Medical Language System (UMLS) and Unstructured Information Management Architecture framework, and a deep learning relation system based on attention-based bidirectional long short-term memory (Att-BiLSTM). ADE: adverse drug event; NER: named entity recognition; WSD: word sense disambiguation.

Figure 2.

The architecture of attention-based bidirectional long short-term memory (BiLSTM)–based relation system.

Figure 3.

Confusion matrix for relations task with the challenge test dataset. ADE: adverse drug event.

Figure 4.

Confusion matrix for concepts task with the challenge test dataset. ADE: adverse drug event.