Literature DB >> 31730700

Using convolutional neural networks to identify patient safety incident reports by type and severity.

Ying Wang1, Enrico Coiera1, Farah Magrabi1.   

Abstract

OBJECTIVE: To evaluate the feasibility of a convolutional neural network (CNN) with word embedding to identify the type and severity of patient safety incident reports.
MATERIALS AND METHODS: A CNN with word embedding was applied to identify 10 incident types and 4 severity levels. Model training and validation used data sets (n_type = 2860, n_severity = 1160) collected from a statewide incident reporting system. Generalizability was evaluated using an independent hospital-level reporting system. CNN architectures were examined by varying layer size and hyperparameters. Performance was evaluated by F score, precision, recall, and compared to binary support vector machine (SVM) ensembles on 3 testing data sets (type/severity: n_benchmark = 286/116, n_original = 444/4837, n_independent = 6000/5950).
RESULTS: A CNN with 6 layers was the most effective architecture, outperforming SVMs with better generalizability to identify incidents by type and severity. The CNN achieved high F scores (> 85%) across all test data sets when identifying common incident types including falls, medications, pressure injury, and aggression. When identifying common severity levels (medium/low), CNN outperformed SVMs, improving F scores by 11.9%-45.1% across all 3 test data sets. DISCUSSION: Automated identification of incident reports using machine learning is challenging because of a lack of large labelled training data sets and the unbalanced distribution of incident classes. The standard classification strategy is to build multiple binary classifiers and pool their predictions. CNNs can extract hierarchical features and assist in addressing class imbalance, which may explain their success in identifying incident report types.
CONCLUSION: A CNN with word embedding was effective in identifying incidents by type and severity, providing better generalizability than SVMs.
© The Author(s) 2019. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  clinical incident reports; multiple classification; neural networks; patient safety; text classification; word embedding

Mesh:

Year:  2019        PMID: 31730700      PMCID: PMC7647259          DOI: 10.1093/jamia/ocz146

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  25 in total

1.  Automated identification of extreme-risk events in clinical incident reports.

Authors:  Mei-Sing Ong; Farah Magrabi; Enrico Coiera
Journal:  J Am Med Inform Assoc       Date:  2012-01-11       Impact factor: 4.497

2.  A comparison of word embeddings for the biomedical natural language processing.

Authors:  Yanshan Wang; Sijia Liu; Naveed Afzal; Majid Rastegar-Mojarad; Liwei Wang; Feichen Shen; Paul Kingsbury; Hongfang Liu
Journal:  J Biomed Inform       Date:  2018-09-12       Impact factor: 6.317

3.  Automated Classification of Multi-Labeled Patient Safety Reports: A Shift from Quantity to Quality Measure.

Authors:  Chen Liang; Yang Gong
Journal:  Stud Health Technol Inform       Date:  2017

Review 4.  Developing and deploying a patient safety program in a large health care delivery system: you can't fix what you don't know about.

Authors:  J P Bagian; C Lee; J Gosbee; J DeRosier; E Stalhandske; N Eldridge; R Williams; M Burkhardt
Journal:  Jt Comm J Qual Improv       Date:  2001-10

5.  'Connecting the dots': leveraging visual analytics to make sense of patient safety event reports.

Authors:  Raj M Ratwani; Allan Fong
Journal:  J Am Med Inform Assoc       Date:  2014-10-21       Impact factor: 4.497

6.  Predicting age by mining electronic medical records with deep learning characterizes differences between chronological and physiological age.

Authors:  Zichen Wang; Li Li; Benjamin S Glicksberg; Ariel Israel; Joel T Dudley; Avi Ma'ayan
Journal:  J Biomed Inform       Date:  2017-11-04       Impact factor: 6.317

7.  Patient safety incident reporting: a qualitative study of thoughts and perceptions of experts 15 years after 'To Err is Human'.

Authors:  Imogen Mitchell; Anne Schuster; Katherine Smith; Peter Pronovost; Albert Wu
Journal:  BMJ Qual Saf       Date:  2015-07-27       Impact factor: 7.035

8.  Medication errors: how reliable are the severity ratings reported to the national reporting and learning system?

Authors:  Steven D Williams; Darren M Ashcroft
Journal:  Int J Qual Health Care       Date:  2009-08-13       Impact factor: 2.038

9.  Using multiclass classification to automate the identification of patient safety incident reports by type and severity.

Authors:  Ying Wang; Enrico Coiera; William Runciman; Farah Magrabi
Journal:  BMC Med Inform Decis Mak       Date:  2017-06-12       Impact factor: 2.796

10.  Towards an International Classification for Patient Safety: key concepts and terms.

Authors:  William Runciman; Peter Hibbert; Richard Thomson; Tjerk Van Der Schaaf; Heather Sherman; Pierre Lewalle
Journal:  Int J Qual Health Care       Date:  2009-02       Impact factor: 2.038

View more
  3 in total

1.  Evaluating resampling methods and structured features to improve fall incident report identification by the severity level.

Authors:  Jiaxing Liu; Zoie S Y Wong; H Y So; Kwok Leung Tsui
Journal:  J Am Med Inform Assoc       Date:  2021-07-30       Impact factor: 4.497

2.  Can Unified Medical Language System-based semantic representation improve automated identification of patient safety incident reports by type and severity?

Authors:  Ying Wang; Enrico Coiera; Farah Magrabi
Journal:  J Am Med Inform Assoc       Date:  2020-10-01       Impact factor: 4.497

3.  Using Healthcare Resources Wisely: A Predictive Support System Regarding the Severity of Patient Falls.

Authors:  Hsi-Hao Wang; Chun-Che Huang; Paul C Talley; Kuang-Ming Kuo
Journal:  J Healthc Eng       Date:  2022-08-01       Impact factor: 3.822

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.