Layout 1


ISDS Annual Conference Proceedings 2012. This is an Open Access article distributed under the terms of the Creative Commons Attribution-
Noncommercial 3.0 Unported License (http://creativecommons.org/licenses/by-nc/3.0/), permitting all non-commercial use, distribution, and
reproduction in any medium, provided the original work is properly cited.

ISDS 2012 Conference Abstracts

Refinement of a Population-Based Bayesian Network for
Fusion of Health Surveillance Data
Howard Burkom*, Yevgeniy Elbert, Liane Ramac-Thomas, Christopher Cuellar and Vivian
Hung

Johns Hopkins Applied Physics Laboratory, Laurel, MD, USA

Objective
The project involves analytic combination of multiple evidence

sources to monitor health at hundreds of care facilities. A demon-
stration module featuring a population-based Bayes Network [1] was
refined and expanded for application in the Department of Defense
Electronic Surveillance System for Community-Based Epidemics
(ESSENCE).

Introduction
The ESSENCE demonstration module was built to help DoD

health monitors make routine decisions based on disparate evidence
sources such as daily counts of ILI-related chief complaints, ratios
of positive lab tests for influenza, patient age distribution, and counts
of antiviral prescriptions [1]. The module was a population-based
(rather than individual-based) Bayesian network (PBN) in that inputs
were algorithmic results from these multiple aggregate data streams,
and output was the degree of belief that the combined evidence re-
quired investigation. The module reduced total alerts substantially
and retained sensitivity to the majority of documented outbreaks
while clarifying underlying sources of evidence. The current effort
was to advance the prototype to production by refining components
of the fusion methodology to improve sensitivity while retaining the
reduced alert rate.

Methods
The multi-level approach to sensitivity improvement included ex-

panded syndromic queries, more data-sensitive algorithm selection,
improved transformation of algorithm outputs to alert states, and hi-
erarchical training of Bayesian networks. Components were tested
individually, and the net result was iteratively refined with perform-
ance using documented outbreaks. 

We examined time series of classes of prescribed drugs and labo-
ratory tests during known events and discussed outbreak-associated
elements with domain experts to liberalize data queries. Algorithms
were matched to data streams with injection testing applied to 4.5
years of data from 502 outpatient clinics. A hierarchical approach was
applied for improved training and verification of PBNs for events re-
lated to categories of Influenza-like Illness, Gastrointestinal, Fever,
Neurological, and Rash, chosen both for public health importance and
for availability of multiple supporting data types. Hierarchical, mod-
ular training was applied to common subnetworks, such as a severity
indicator PBN depending on case disposition, acute case indicators,
complex evaluation/management codes, and patient bounce-backs, de-
picted in Figure 1. Conversion of individual algorithm outputs to be-
lief states (e.g. “at least two red alerts/past 7 days”) was broadened
using analysis of lags between data sources. With data from the known
events, we calculated decision support thresholds for the parent-level
PBN decision nodes with a stochastic optimization technique maxi-
mizing the ratio of alert rates during outbreak to non-outbreak periods.

Results
The expanded data queries, more stream-specific algorithm selec-

tion, generalized state transformation, and hierarchical PBN training

detected 22 of an expanded collection of 24 documented outbreaks,
with incremental improvement ongoing. The mean alert rate drop
achieved by the Bayes Net was 87% (minimum of 85%) compared to
the combined alerts of all component algorithms across syndromes
and facilities.

Conclusions
Expansion and further technical validation upheld the PBN ap-

proach as a user-friendly means of analytic decision support given
multiple, variably weighted evidence sources. The PBN affords not
only sharply reduced alerting, but also transparent indication of evi-
dence underlying each alert. The older algorithm approach remains
available as backup. Beta testing of the resulting production system
will drive further modification.

Figure 1: PBN Subnetwork for Event Severity, based on Outpatient Data
Fields

Keywords
Fusion; Bayesian Network; Multivariate; Decision Support

Acknowledgments

Drs. Julie Pavlin and Rhonda Lizewski of the Armed Forces Health Sur-
veillance Center for data- and event-related consultation and Joe Lom-
bardo and Wayne Loschen of Johns Hopkins APL for consultation on
production enhancement.

References

Burkom H, Elbert Y, Ramac-Thomas L et al., Analytic fusion of
ESSENCE clinical evidence sources for routine decision support,
Emerging Health Threats Journal Supplements, eISSN 1752-8550,
ISSN 2001 1350 (print).

*Howard Burkom
E-mail: howard.burkom@jhuapl.edu

Online Journal of Public Health Informatics * ISSN 1947-2579 * http://ojphi.org * 5(1):e6, 2013