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

Bayesian Contact Tracing for Communicable
Respiratory Disease
Ayman Shalaby* and Daniel Lizotte

University of Waterloo, Waterloo, ON, Canada

Objective
The purpose of our work is to develop a system for automatic con-

tact tracing with the goal of identifying individuals who are most
likely infected, even if we do not have direct diagnostic information
on their health status. Control of the spread of respiratory pathogens
(e.g. novel influenza viruses) in the population using vaccination is
a challenging problem that requires quick identification of the infec-
tious agent followed by large-scale production and administration of
a vaccine. This takes a significant amount of time. A complementary
approach to control transmission is contact tracing and quarantining,
which are currently applied to sexually transmitted diseases (STDs).
For STDs, identifying the contacts that might have led to disease
transmission is relatively easy; however, for respiratory pathogens,
the contacts that can lead to transmission include a huge number of
face-to-face daily social interactions that are impossible to trace man-
ually.

Introduction
The evolution of novel influenza viruses in humans is a bio- logi-

cal phenomenon that can not be stopped. All existing data suggest
that vaccination against the morbidity and mortality of the novel in-
fluenza viruses is our best line of defence. Unfortunately, vaccina-
tion requires that the infectious agent to be quickly identified and a
safe vaccine in large quantities is produced and administered. As was
witnessed with the 2009 H1N1 influenza pandemic, these steps took
a frustratingly long period during which the novel influenza virus
continued its unstoppable and rapid global spreading.

In addition to the different vaccination strategies ( e.g. random
mass vaccination, age structured vaccination), isolation and quaran-
tining of infected individuals is another effective method used by the
public health agencies to control the spreading of infectious diseases.
Isolation is effective against any infectious disease, however it can be
very hard to detect infectious individuals in the population when:

1. Symptoms are ambiguous or easily misdiagnosed ( e.g. 2009
H1N1 influenza outbreak shared many symptoms with many other
influenza like illnesses)

2. When the symptoms emerge after the individual become infec-
tious.

Methods
We developed a dynamic Bayesian network model to process sen-

sor information from users’ cellphones together with (possibly in-
complete) diagnosis information to track the spread of disease in a
population. Our model tracks real-time proximity contacts and can
provide public health agencies with the probability of infection for
each individual in the model.

For testing our algorithm, we used a real-world mobile sensor
dataset with 120 individuals collected over a period of 9 months, and
we simulated an outbreak.

Results
We ran several experiments where different sub-populations were

“infected” and “diagnosed.” By using the contact information, our
model was able to automatically identify individuals in the population
who were likely to be infected even though they were not directly
“diagnosed” with an illness.

Conclusions
Automatic contact tracing for respiratory pathogens is a powerful

idea, however we have identified several implementation challenges.
The first challenge is scalability: we note that a contact tracing sys-
tem with a hundred thousand individuals requires a Bayesian model
with a billion nodes. Bayesian inference on models of this scale is an
open problem and an active area of research. The second challenge is
privacy protection: although the test data were collected

in an academic setting, deploying any system will require appro-
priate safeguards for user privacy. Nonetheless, our work llustrates
the potential for broader use of contact tracing for modeling and con-
trolling disease transmission.

Keywords
Outbreak Detection; Syndromic Surveillance; Mobile; Contact Trac-
ing; Bayesian Algorithms

*Ayman Shalaby
E-mail: aymanshalaby11@gmail.com

Online Journal of Public Health Informatics * ISSN 1947-2579 * http://ojphi.org * 5(1):e208, 2013