Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug 13:10:e57349.
doi: 10.2196/57349.

A Bayesian System to Detect and Track Outbreaks of Influenza-Like Illnesses Including Novel Diseases: Algorithm Development and Validation

John M Aronis  1 , Ye Ye  1 , Jessi Espino  1 , Harry Hochheiser  1 , Marian G Michaels  2 , Gregory F Cooper  1
Affiliations

A Bayesian System to Detect and Track Outbreaks of Influenza-Like Illnesses Including Novel Diseases: Algorithm Development and Validation

John M Aronis et al. JMIR Public Health Surveill. .

Abstract

Background: The early identification of outbreaks of both known and novel influenza-like illnesses (ILIs) is an important public health problem.

Objective: This study aimed to describe the design and testing of a tool that detects and tracks outbreaks of both known and novel ILIs, such as the SARS-CoV-2 worldwide pandemic, accurately and early.

Methods: This paper describes the ILI Tracker algorithm that first models the daily occurrence of a set of known ILIs in hospital emergency departments in a monitored region using findings extracted from patient care reports using natural language processing. We then show how the algorithm can be extended to detect and track the presence of an unmodeled disease that may represent a novel disease outbreak.

Results: We include results based on modeling diseases like influenza, respiratory syncytial virus, human metapneumovirus, and parainfluenza for 5 emergency departments in Allegheny County, Pennsylvania, from June 1, 2014, to May 31, 2015. We also include the results of detecting the outbreak of an unmodeled disease, which in retrospect was very likely an outbreak of the enterovirus D68 (EV-D68).

Conclusions: The results reported in this paper provide support that ILI Tracker was able to track well the incidence of 4 modeled influenza-like diseases over a 1-year period, relative to laboratory-confirmed cases, and it was computationally efficient in doing so. The system was also able to detect a likely novel outbreak of EV-D68 early in an outbreak that occurred in Allegheny County in 2014 as well as clinically characterize that outbreak disease accurately.

Keywords: Bayesian modeling; COVID-19; NLP; Pennsylvania; SARS-CoV-2; algorithm; biosurveillance; coronavirus; disease modeling; emergency department; enterovirus D68; hospital; hospitals; human metapneumovirus; influenza; influenza-like illnesses; natural language processing; novel disease; novel diseases; outbreak; parainfluenza; patient care; public health; respiratory syncytial; surveillance.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: JE is President of General Biodefense LLC. All other authors have no conflicts of interest to declare.

Figures

Figure 1
Figure 1
A Bayesian network model for the 20 most informative findings in the RSV model. RSV: respiratory syncytial virus; SpO2: measure of the saturation of peripheral blood oxygen.
Figure 2
Figure 2
Expected and confirmed cases for June 1, 2014, to May 31, 2015 (7-day moving average). hMPV: human metapneumovirus; ILI: influenza-like illness; RSV: respiratory syncytial virus.
Figure 3
Figure 3
Daily empirical P values from June 1, 2014, to May 31, 2015.
Figure 4
Figure 4
Daily absolute counts of the top 10 excess findings from July to October 2014.
Figure 5
Figure 5
Daily empirical P values from June 1, 2014, to May 31, 2015, with a synthetic outbreak added to March 2015.
Figure 6
Figure 6
Comparison of empirical P values from ILI Tracker and AR Alarm for June 1, 2014 to May 31, 2015, with a synthetic outbreak added to March 2015. AR: autoregression; ILI: influenza-like illness.
See this image and copyright information in PMC

Update of

Similar articles

See all similar articles

Cited by

References

    1. Dato V, Shephard R, Wagner M. Outbreaks and investigations. In: Wagner MM, Moore AW, Aryel RM, editors. Handbook of Biosurveillance. Cambridge, MA: Elsevier Academic Press; 2006. pp. 13–26.
    1. Wagner MM, Gresham LS, Dato V. Case detection, outbreak detection, and outbreak characterization. In: Wagner MM, Moore AW, Aryel RM, editors. Handbook of Biosurveillance. Cambridge, MA: Academic Press; 2006. pp. 27–50.
    1. Velikina R, Dato V, Wagner MM. Governmental public health. In: Wagner MM, Moore AW, Aryel RM, editors. Handbook of Biosurveillance. Cambridge, MA: Academic Press; 2006. pp. 67–88.
    1. Wagner MM, Hogan WR, Aryel RM. The healthcare system. In: Wagner MM, Moore AW, Aryel RM, editors. Handbook of Biosurveillance. Cambridge, MA: Academic Press; 2006. pp. 89–110.
    1. Brokopp C, Resultan E, Holmes H, Wagner MM. Laboratories. In: Wagner MM, Moore AW, Aryel RM, editors. Handbook of Biosurveillance. Cambridge, MA: Academic Press; 2006. pp. 129–142.

Publication types

LinkOut - more resources