Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Acquisition of a Lexicon for Family History Information through BERT-assisted Sublanguage Analysis
Liwei Wang;
Huan He;
Andrew Wen;
Sungrim Moon;
Sunyang Fu;
Keven J Peterson;
Xuguang Ai;
Sijia Liu;
Ramakanth Kavuluru;
Hongfang Liu
ABSTRACT
Background:
A patient’s family history (FH) information significantly influences downstream clinical care. Despite this importance, there is no standardized way to capture FH information in electronic health records (EHR) and a substantial portion of FH information is frequently embedded in clinical notes. This renders FH information difficult to use in downstream data analytics or clinical decision support applications. To address this issue, a natural language processing (NLP) system capable of extracting and normalizing FH information can be used.
Objective:
In this study, we aimed to construct an FH lexical resource for information extraction and normalization.
Methods:
we exploited a transformer-based method to construct an FH lexical resource leveraging a corpus consisting of clinical notes generated as part of primary care. The usability of the lexicon was demonstrated through the development of an expert-based baseline FH system. We also experimented with a deep-learning-based module for FH information extraction. Previous FH challenge datasets were used for evaluation.
Results:
The resulting lexicon contains 33,603 lexicon entries normalized to 6,408 concept unique identifiers (CUIs) of the Unified Medical Language System (UMLS) and 15,126 codes of the Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT), with an average number of 5.4 variants per concept. The performance evaluation demonstrates that the combination of the baseline FH system with a state-of-the-art deep learning-based FH module can improve the recall of FH information using the BioCreative/N2C2 family history challenge dataset.
Conclusions:
The resulting lexicon and baseline FH system are freely available through the Open Health Natural Language Processing (OHNLP) GitHub. Clinical Trial: NA
Citation
Please cite as:
Wang L, He H, Wen A, Moon S, Fu S, Peterson KJ, Ai X, Liu S, Kavuluru R, Liu H
Acquisition of a Lexicon for Family History Information: Bidirectional Encoder Representations From Transformers–Assisted Sublanguage Analysis