Annotating and detecting phenotypic information for chronic obstructive pulmonary disease

Ju, Meizhi and Short, Andrea and Thompson, Paul and Bakerly, Nawar Diar and Gkoutos, Georgios and Tsaprouni, Loukia and Ananiadou, Sophia (2019) Annotating and detecting phenotypic information for chronic obstructive pulmonary disease. JAMIA Open. ISSN 2574-2531

[img] Text (Published Paper)
5480553 - Published Version

Download (389kB)


Chronic obstructive pulmonary disease (COPD) phenotypes cover a range of lung abnormalities. To allow text mining methods to identify pertinent and potentially complex information about these phenotypes from textual data, we have developed a novel annotated corpus, which we use to train a neural network-based named entity recognizer to detect fine-grained COPD phenotypic information.

Materials and methods
Since COPD phenotype descriptions often mention other concepts within them (proteins, treatments, etc.), our corpus annotations include both outermost phenotype descriptions and concepts nested within them. Our neural layered bidirectional long short-term memory conditional random field (BiLSTM-CRF) network firstly recognizes nested mentions, which are fed into subsequent BiLSTM-CRF layers, to help to recognize enclosing phenotype mentions.

Our corpus of 30 full papers (available at: is annotated by experts with 27 030 phenotype-related concept mentions, most of which are automatically linked to UMLS Metathesaurus concepts. When trained using the corpus, our BiLSTM-CRF network outperforms other popular approaches in recognizing detailed phenotypic information.

Information extracted by our method can facilitate efficient location and exploration of detailed information about phenotypes, for example, those specifically concerning reactions to treatments.

The importance of our corpus for developing methods to extract fine-grained information about COPD phenotypes is demonstrated through its successful use to train a layered BiLSTM-CRF network to extract phenotypic information at various levels of granularity. The minimal human intervention needed for training should permit ready adaption to extracting phenotypic information about other diseases.

Item Type: Article
Identification Number:
26 April 2019Published
19 March 2019Accepted
Subjects: CAH01 - medicine and dentistry > CAH01-01 - medicine and dentistry > CAH01-01-01 - medical sciences (non-specific)
CAH09 - mathematical sciences > CAH09-01 - mathematical sciences > CAH09-01-02 - operational research
CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions: Faculty of Health, Education and Life Sciences > School of Health Sciences
Depositing User: Loukia Tsaprouni
Date Deposited: 15 May 2019 08:50
Last Modified: 12 Jan 2022 12:53

Actions (login required)

View Item View Item


In this section...