PMID- 33647938
OWN - NLM
STAT- MEDLINE
DCOM- 20211124
LR  - 20220228
IS  - 1527-974X (Electronic)
IS  - 1067-5027 (Print)
IS  - 1067-5027 (Linking)
VI  - 28
IP  - 7
DP  - 2021 Jul 14
TI  - Extracting postmarketing adverse events from safety reports in the vaccine 
      adverse event reporting system (VAERS) using deep learning.
PG  - 1393-1400
LID - 10.1093/jamia/ocab014 [doi]
AB  - OBJECTIVE: Automated analysis of vaccine postmarketing surveillance narrative 
      reports is important to understand the progression of rare but severe vaccine 
      adverse events (AEs). This study implemented and evaluated state-of-the-art deep 
      learning algorithms for named entity recognition to extract nervous system 
      disorder-related events from vaccine safety reports. MATERIALS AND METHODS: We 
      collected Guillain-Barre syndrome (GBS) related influenza vaccine safety reports 
      from the Vaccine Adverse Event Reporting System (VAERS) from 1990 to 2016. VAERS 
      reports were selected and manually annotated with major entities related to 
      nervous system disorders, including, investigation, nervous_AE, other_AE, 
      procedure, social_circumstance, and temporal_expression. A variety of 
      conventional machine learning and deep learning algorithms were then evaluated 
      for the extraction of the above entities. We further pretrained domain-specific 
      BERT (Bidirectional Encoder Representations from Transformers) using VAERS 
      reports (VAERS BERT) and compared its performance with existing models. RESULTS 
      AND CONCLUSIONS: Ninety-one VAERS reports were annotated, resulting in 2512 
      entities. The corpus was made publicly available to promote community efforts on 
      vaccine AEs identification. Deep learning-based methods (eg, bi-long short-term 
      memory and BERT models) outperformed conventional machine learning-based methods 
      (ie, conditional random fields with extensive features). The BioBERT large model 
      achieved the highest exact match F-1 scores on nervous_AE, procedure, 
      social_circumstance, and temporal_expression; while VAERS BERT large models 
      achieved the highest exact match F-1 scores on investigation and other_AE. An 
      ensemble of these 2 models achieved the highest exact match microaveraged F-1 
      score at 0.6802 and the second highest lenient match microaveraged F-1 score at 
      0.8078 among peer models.
CI  - (c) The Author(s) 2021. Published by Oxford University Press on behalf of the 
      American Medical Informatics Association. All rights reserved. For permissions, 
      please email: journals.permissions@oup.com.
FAU - Du, Jingcheng
AU  - Du J
AUID- ORCID: 0000-0002-0322-4566
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Xiang, Yang
AU  - Xiang Y
AUID- ORCID: 0000-0003-1395-6805
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Sankaranarayanapillai, Madhuri
AU  - Sankaranarayanapillai M
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Zhang, Meng
AU  - Zhang M
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Wang, Jingqi
AU  - Wang J
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Si, Yuqi
AU  - Si Y
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Pham, Huy Anh
AU  - Pham HA
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Xu, Hua
AU  - Xu H
AUID- ORCID: 0000-0002-5274-4672
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
FAU - Chen, Yong
AU  - Chen Y
AD  - Perelman School of Medicine, University of Pennsylvania, Philadelphia, 
      Pennsylvania, USA.
FAU - Tao, Cui
AU  - Tao C
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston, Houston, Texas, USA.
LA  - eng
GR  - R01 LM011829/LM/NLM NIH HHS/United States
GR  - R01 AI130460/AI/NIAID NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PL  - England
TA  - J Am Med Inform Assoc
JT  - Journal of the American Medical Informatics Association : JAMIA
JID - 9430800
RN  - 0 (Influenza Vaccines)
SB  - IM
MH  - Adverse Drug Reaction Reporting Systems
MH  - Computer Systems
MH  - *Deep Learning
MH  - *Guillain-Barre Syndrome
MH  - Humans
MH  - *Influenza Vaccines/adverse effects
MH  - United States
PMC - PMC8279785
OTO - NOTNLM
OT  - VAERS
OT  - deep learning
OT  - named entity recognition
OT  - vaccine adverse events
EDAT- 2021/03/02 06:00
MHDA- 2021/11/25 06:00
PMCR- 2022/02/27
CRDT- 2021/03/01 20:21
PHST- 2020/08/26 00:00 [received]
PHST- 2021/01/14 00:00 [revised]
PHST- 2021/01/20 00:00 [accepted]
PHST- 2021/03/02 06:00 [pubmed]
PHST- 2021/11/25 06:00 [medline]
PHST- 2021/03/01 20:21 [entrez]
PHST- 2022/02/27 00:00 [pmc-release]
AID - 6153955 [pii]
AID - ocab014 [pii]
AID - 10.1093/jamia/ocab014 [doi]
PST - ppublish
SO  - J Am Med Inform Assoc. 2021 Jul 14;28(7):1393-1400. doi: 10.1093/jamia/ocab014.