학술논문
Deep learning for electronic health records: A comparative review of multiple deep neural architectures.
Document Type
Academic Journal
Author
Ayala Solares JR; The George Institute for Global Health (UK), University of Oxford, United Kingdom; NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, United Kingdom.; Diletta Raimondi FE; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Zhu Y; The George Institute for Global Health (UK), University of Oxford, United Kingdom. Electronic address: yajie.zhu@georgeinstitute.ox.ac.uk.; Rahimian F; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Canoy D; The George Institute for Global Health (UK), University of Oxford, United Kingdom; NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, United Kingdom; Faculty of Medicine, University of New South Wales, Sydney, Australia.; Tran J; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Pinho Gomes AC; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Payberah AH; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Zottoli M; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Nazarzadeh M; The George Institute for Global Health (UK), University of Oxford, United Kingdom; Collaboration Center of Meta-Analysis Research, Torbat Heydariyeh University of Medical Sciences, Torbat Heydariyeh, Iran.; Conrad N; The George Institute for Global Health (UK), University of Oxford, United Kingdom.; Rahimi K; The George Institute for Global Health (UK), University of Oxford, United Kingdom; NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, United Kingdom.; Salimi-Khorshidi G; The George Institute for Global Health (UK), University of Oxford, United Kingdom.
Source
Publisher: Elsevier Country of Publication: United States NLM ID: 100970413 Publication Model: Print Cited Medium: Internet ISSN: 1532-0480 (Electronic) Linking ISSN: 15320464 NLM ISO Abbreviation: J Biomed Inform Subsets: MEDLINE
Subject
Language
English
Abstract
Despite the recent developments in deep learning models, their applications in clinical decision-support systems have been very limited. Recent digitalisation of health records, however, has provided a great platform for the assessment of the usability of such techniques in healthcare. As a result, the field is starting to see a growing number of research papers that employ deep learning on electronic health records (EHR) for personalised prediction of risks and health trajectories. While this can be a promising trend, vast paper-to-paper variability (from data sources and models they use to the clinical questions they attempt to answer) have hampered the field's ability to simply compare and contrast such models for a given application of interest. Thus, in this paper, we aim to provide a comparative review of the key deep learning architectures that have been applied to EHR data. Furthermore, we also aim to: (1) introduce and use one of the world's largest and most complex linked primary care EHR datasets (i.e., Clinical Practice Research Datalink, or CPRD) as a new asset for training such data-hungry models; (2) provide a guideline for working with EHR data for deep learning; (3) share some of the best practices for assessing the "goodness" of deep-learning models in clinical risk prediction; (4) and propose future research ideas for making deep learning models more suitable for the EHR data. Our results highlight the difficulties of working with highly imbalanced datasets, and show that sequential deep learning architectures such as RNN may be more suitable to deal with the temporal nature of EHR.
(Copyright © 2019 Elsevier Inc. All rights reserved.)
(Copyright © 2019 Elsevier Inc. All rights reserved.)