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

Enabling Syndromic Surveillance in Pakistan
Ross Maciejewski*1, Shehzad Afzal2, Adam J. Fairfield1, Arif Ghafoor2, David S. Ebert2,
Naeem Ayyaz4 and Maaz Ahmed3

1Computer Science, Arizona State University, Tempe, AZ, USA; 2Purdue University, West Lafayette, IN, USA; 3King Edward Medical
University, Lahore, Pakistan; 4University of Engineering and Technology, Lahore, Pakistan

Objective
This work presents our first steps in developing a Global Real-time

Infectious Disease Surveillance System (GRIDDS) employing robust
and novel in-fectious disease epidemiology models with real-time in-
ference and pre/exercise planning capabilities for Lahore, Pakistan.
The objective of this work is to address the infectious disease sur-
veillance challenges (specific to developing countries such as Pak-
istan) and develop a collaborative capability for monitoring and
managing outbreaks of natural or manmade infectious diseases in
Pakistan.

Methods
Utilizing our partner hospitals in the Lahore, Punjab area, we have

begun developing a theoretical model of patient hospital visits with
respect to diseases and syndromes within Pakistan. Our first thrust
has focused on the collection, categorization and cleansing of data
based on expert knowledge from our partnering institutions in Pak-
istan. Data consists of a patient’s home address and chief complaint
which is then categorized into syndromes. Home addresses are
geocoded utilizing the Google API with a resultant 72% accuracy.
Unknown geolocations are aggregated only at the hospital level.
Using this cleaned data, we employ methods similar to our previous
work [1] on syndromic surveillance for early disease detection. Cur-
rently, we have collected over 600,000 patient records over 1.5 years.

We employ the use of choropleth maps, isopleth maps utilizing
kernel density estimation of patient addresses, traditional control
chart methods such as exponentially weighted moving averages
(EWMA), and a non-parametric time series analysis approach (sea-
sonal trend decomposition using loess smoothing (STL) [2]) which
requires only 90 days of historical data to be put into operation. The
time series models are deployed as part of a real-time surveillance
system in which temporal anomalies over regions can be analyzed
and disease outbreaks reported.

Results
Figure 1 illustrates our visual analytics toolkit in operation. Here

we see the location of our partner hospital in the Lahore region. The
hospital coverage is in the most populous location of the city, pro-
viding data as a sentinel site for the overall health of the city. Cur-
rently, our system employs the use of interactive filters and linked
isopleth or choropleth maps with time series analysis on mouse over.

Conclusions
Currently our research has focused on one partner location within

the city of Lahore. Our ongoing work is focusing on the adoption of
such a system to other regions of the country and the development of
disease spread simulations (particularly Dengue Fever) utilizing base-
line data collected by our partners. We plan to integrate these models
into our visual analytics system for real-time planning and simula-
tion.

Keywords
syndromic surveillance; visual analytics; pakistan

Acknowledgments

This work is supported by the Defense Threat Reduction Agency Award
Number HDTRA1-10-1-0083.

References

[1] Maciejewski, R., et al.., “Forecasting Hotspot – A Predictive Analyt-
ics Approach,” IEEE Transactions on Visualization and Computer
Graphics, 17(4): 440-453, 2011.

[2] Hafen, R. P., et al., “Syndromic surveillance: STL modeling, visual-
izing and monitoring disease counts,” BMC Medical Informatics and
Decision Making, 2009.

*Ross Maciejewski
E-mail: rmacieje@asu.edu

Online Journal of Public Health Informatics * ISSN 1947-2579 * http://ojphi.org * 5(1):e106, 2013