Assistant Professor of Biomedical Informatics
Senior Statistician, RODS Laboratory

Contact Info:

Research Interests

Dr. Wallstrom’s research interests involve the application of computational statistical methods to biosurveillance.

Education

Dates Attended: 09/93 – 07/99
Name and Location of Institution: University of Minnesota, Minneapolis MN
Degree Received and Year: PhD Statistics, 1999
Major Subject: Statistics

Dates Attended: 09/93 – 07/99
Name and Location of Institution: University of Minnesota, Minneapolis MN
Degree Received and Year: MS Statistics, 1998
Major Subject: Statistics

Dates Attended: 08/89 – 05/93
Name and Location of Institution: Carnegie Mellon University, Pittsburgh PA
Degree Received and Year: BS Applied Mathematics, 1993
Major Subject: Applied Mathematics

Publications

Journal Publications

Cami A, Wallstrom GL, Fowlkes AL, Panozzo CA, Hogan WR. Mining aggregates of over-the-counter products for syndromic surveillance. Pattern Recognition Letters. 2009 Feb; 30(3): 255-266. DOI: http://10.1016/j.patrec.2008.09.008.

Torres-Urquidy MH, Wallstrom GL, Schleyer TKL. Detection of Disease Outbreaks using Oral Manifestations. J Dent Res. 2009 Jan; 88(1):89-94. DOI: 10.1177/0022034508327546. PMID: 19131324

Jiang X, Wallstrom G, Cooper GF, Wagner MM. Bayesian prediction of an epidemic curve. J Biomed Inform. 2008 Jun 13. PMID: 18593605

Wallstrom G, Liebner J, Kass RE. An Implementation of Bayesian Adaptive Regression Splines (BARS) in C with S and R Wrappers. Journal of Statistical Software. June 2008; 26(1): 1-21. Issn: 15487660

Hogan WR, Cooper GF, Wallstrom GL, Wagner MM, Depinay JM. The Bayesian aerosol release detector: an algorithm for detecting and characterizing outbreaks caused by an atmospheric release of Bacillus anthracis. Stat Med. 2007 Dec 20;26(29):5225-52. PMID: 17948918

Wallstrom GL, Hogan WR. Unsupervised clustering of over-the-counter healthcare products into product categories. J Biomed Inform. 2007 Dec;40(6):642-8. Epub 2007 Apr 3. PMID: 17509942 PMCID: PMC2170432

Jiang X, Wallstrom G. A Bayesian Network for Outbreak Detection and Prediction. In Proceedings of the Twenty-First National Conference on Artificial Intelligence 2006. Menlo Park, Calif.: AAAI Press.

Wallstrom GL, Wagner M, Hogan W. High-fidelity injection detectability experiments: a tool for evaluating syndromic surveillance systems. MMWR Morb Mortal Wkly Rep. 2005 Aug 26;54 Suppl:85-91. PMID: 16177698

Wallstrom GL, Kass RE, Miller A, Cohn JF, Fox NA. Automatic correction of ocular artifacts in the EEG: a comparison of regression-based and component-based methods. Int J Psychophysiol. 2004 Jul;53(2):105-19. PMID: 15210288

Conference Proceedings

Cami A, Wallstrom GL, Hogan WR. Effect of Commuting on the Detection and Characterization Performance of the Bayesian Aerosol Release Detector. Bioinformatics and Biomeidcine Workshops, 2008. BIBMW 2008. IEEE International Conference. 2008 Nov. 3-5, pp. 91 -98. DOI: 10.1109/BIBMW.2008.4686214

Cami A, Wallstrom GL, Hogan WR. Integrating a Commuting Model with the Bayesian Aerosol Release Detector. Biosecure 2008 Dec, LNCS 5354, pp. 85-96, 2008.

Kong X, Wallstrom GL, Hogan WR. A Temporal Extension of the Bayesian Aerosol Release Detector. BioSecure 2008 Dec, LNCS 5354, pp. 97Ð107, 2008.

Zhang M, Kong X, Wallstrom G. Simulation of Multivariate Spatial-Temporal Outbreak Data for Detection Algorithm Evaluation. BioSecure 2008 Dec, LNCS 5354, pp. 155-163, 2008.

Zhang M, Wallstrom GL. Template-Driven Spatial-Temporal Outbreak Simulation for Outbreak Detection Evaluation. AMIA Annu Symp Proc. 2008 Nov 6:854-8. PMID: 18999301 [PubMed - in process].

Shaffer L, Funk J, Rajala-Schultz P, Wallstrom G, Wagner MM, Saville W. Early Outbreak Detection using an Automated Data Feed of Test Orders from a Veterinary Diagnostic Laboratory. Lecture Notes in Computer Science: Intelligence and Security Informatics: Biosurveillance, 2007; 4506: 1-10. ISSN 0302-9743 (Print); 1611-3349 (Online).

Wagner MM, Wallstrom GL, Onisko A. Issue a boil-water advisory or wait for definitive information? A decision analysis. AMIA Annu Symp Proc. 2005:774-8. PMID: 1677914.

Li R, Wallstrom GL, Hogan WR. A multivariate procedure for identifying correlations between diagnoses and over-the-counter products from historical datasets. AMIA Annu Symp Proc. 2005:450-4. PMID: 16779080

Hogan WR, Wallstrom GL, Wagner MM. An evaluation of three policies for updating product categories in the National Retail Data Monitor. AMIA Annu Symp Proc. 2005:325-9. PMID: 16779055

Book Chapters

Wallstrom GL, Wagner MM, Onisko A. Probabilistic Interpretation of Surveillance Data. In Handbook of Biosurveillance. eds. M. Wagner, A. Moore, R. Aryel. Elsevier, 2006, 417-422.

Wagner MM, Wallstrom G. Methods for Algorithm Evaluation. In Handbook of Biosurveillance. eds. M. Wagner, A. Moore, R. Aryel. Elsevier, 2006, 301-310.

Onisko A, Wallstrom G, Wagner MM. Decision Analysis. In Handbook of Biosurveillance. eds. M. Wagner, A. Moore, R. Aryel. Elsevier, 2006, 405-416.

Grants

R01 PH000024-01       Wallstrom (PI)       09/30/07 - 09/29/09
Centers for Disease Control and Prevention (CDC)
Disaster Planning and Management
The major goal of this project is to support the BioSense Initiative by developing a software platform for biosurveillance staff and researchers that allow them to measure the sensitivity, specificity, detection timeliness, and smallest detectable outbreak of a surveillance system.
Role: PI

1 RO1 PH000026-01       Hogan (PI)       09/30/05 - 09/29/09
Centers for Disease Control and Prevention
Improving detection of outbreaks due to aerosol attacks.
The major goal of this project is to determine the ability of the Bayesian Aerosol Release Detector (BARD) to address the problem of early detection of bioterrorism attacks where bioterrorists release a biological agent into the atmosphere as an aerosol.
Role: Co-Investigator

IIS-0325581       Cooper (PI)       09/15/03 - 08/31/09
National Science Foundation
Bayesian Modeling for Biosurveillance
The major goal of this project is to develop algorithms for the analysis of public health surveillance data.
Role: Co-Investigator

1 R01 HL087119-01A1       Chapman, B. (PI)       03/01/08 - 02/28/11
National Institutes of Health
Automated Detection of Thromboembolic Disease in CT Images
This project tests the feasibility of using a CAD tool to automatically diagnose thromboembolic disease as manifested in volumetric pulmonary and peripheral CT angiography (CTA) and CT venography (CTV) images. We will construct a database of 450 CTA/V that were acquired to rule out thromboembolic disease, along with corresponding clinical data which will be used to establish the true disease state. We will develop a set of vascular analysis algorithms that will be applied to the CTA/V images to automatically extract a centerline model of the relevant vascular trees. Detailed morphological measurements of the vasculature will be made automatically using the centerline model. These measurements will form the input vector to a computer-aided detection (CAD) algorithms based on artificial neural networks. The CAD algorithms will be used to determine the presence of thrombus or emboli within the vascular trees. The efficacy of the CAD algorithms will be assessed using FROC methods. Performance level of the CAD algorithms will be compared to the clinical radiologists’ interpretations of the performance experiment.
Role: Co-Investigator