@article{64961a1fc07c42a18746661bc986f989,
title = "An aberration detection-based approach for sentinel syndromic surveillance of COVID-19 and other novel influenza-like illnesses",
abstract = "Coronavirus Disease 2019 has emerged as a significant global concern, triggering harsh public health restrictions in a successful bid to curb its exponential growth. As discussion shifts towards relaxation of these restrictions, there is significant concern of second-wave resurgence. The key to managing these outbreaks is early detection and intervention, and yet there is a significant lag time associated with usage of laboratory confirmed cases for surveillance purposes. To address this, syndromic surveillance can be considered to provide a timelier alternative for first-line screening. Existing syndromic surveillance solutions are however typically focused around a known disease and have limited capability to distinguish between outbreaks of individual diseases sharing similar syndromes. This poses a challenge for surveillance of COVID-19 as its active periods tend to overlap temporally with other influenza-like illnesses. In this study we explore performing sentinel syndromic surveillance for COVID-19 and other influenza-like illnesses using a deep learning-based approach. Our methods are based on aberration detection utilizing autoencoders that leverages symptom prevalence distributions to distinguish outbreaks of two ongoing diseases that share similar syndromes, even if they occur concurrently. We first demonstrate that this approach works for detection of outbreaks of influenza, which has known temporal boundaries. We then demonstrate that the autoencoder can be trained to not alert on known and well-managed influenza-like illnesses such as the common cold and influenza. Finally, we applied our approach to 2019–2020 data in the context of a COVID-19 syndromic surveillance task to demonstrate how implementation of such a system could have provided early warning of an outbreak of a novel influenza-like illness that did not match the symptom prevalence profile of influenza and other known influenza-like illnesses.",
keywords = "COVID-19, Deep learning, Syndromic surveillance",
author = "Andrew Wen and Liwei Wang and Huan He and Sijia Liu and Sunyang Fu and Sunghwan Sohn and Kugel, {Jacob A.} and Kaggal, {Vinod C.} and Ming Huang and Yanshan Wang and Feichen Shen and Jungwei Fan and Hongfang Liu",
note = "Funding Information: Research reported in this publication was supported by the National Center for Advancing Translational Science of the National Institutes of Health under award number U01TR002062 and by the National Library of Medicine under award number R01LM0011934. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The NLP engine and associated algorithm used to extract ILI symptoms as described in this study is available within the MedTagger project (https://www.github.com/OHNLP/MedTagger). Please consult the Wiki and README file accessible from the linked page for instructions on how to use for the COVID-19 use case. The aberration detection/sentinel syndromic surveillance component has been decoupled from institutional data sources and is available at https://github.com/OHNLP/AEGIS. As this is an active project undergoing improvement and new features that may lead to changes in the underlying code inconsistent with what was described in this manuscript, we have tagged the codebase as described in this manuscript with the COVID19 tag. Due to the results of the symptom extraction process being considered protected health information, data is not available as it would be difficult to distribute to anyone not engaged in an IRB-approved collaboration with the Mayo Clinic. AW: Designed, implemented study, performed experiments. AW, LW, HH, SL, SF, MH, YW, FS: Determined symptom inclusion/exclusion criteria for NLP algorithm and similar contributions to the divisional COVID-19 work group, preparation of NLP algorithm for public distribution, and other miscellaneous project tasks. HH, SL: Generation of graphs and figures as presented in manuscript. AW, SS, JAK, VCK: NLP engine work used for this study, interfacing with institutional data sources. JF, HL: Direction on study design and conceptualization, project leadership. All authors reviewed and contributed expertise to the final manuscript. Funding Information: Research reported in this publication was supported by the National Center for Advancing Translational Science of the National Institutes of Health under award number U01TR002062 and by the National Library of Medicine under award number R01LM0011934. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Publisher Copyright: {\textcopyright} 2020 Elsevier Inc.",
year = "2021",
month = jan,
doi = "10.1016/j.jbi.2020.103660",
language = "English (US)",
volume = "113",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
}