Janusz Wojtusiak, PhD

Image of Janusz Wojtusiak, PhD
Titles and Organizations

Professor, HAP
Division Director, Programs in Health Informatics, HAP
Director, Machine Learning and Inference Laboratory

Contact Information

Email: jwojtusi@gmu.edu
Phone: 703-993-4148
Building: Peterson Hall
Room 4425

Biography

Dr. Wojtusiak, Professor of Health Informatics and Director of the Machine Learning and Inference Laboratory, has expertise that spans machine learning, health informatics, artificial intelligence in clinical decision support and knowledge discovery in medical data, and a wide range of applications of these fields in health care. His particular area of interest is in developing algorithms that derive simple, transparent and usable models from complex health data to predict patient and population outcomes. He studies how to create and evaluate reproducible, unbiased and trustworthy algorithms and models.

Dr. Wojtusiak serves as the Division Director for Health Informatics in the Department of Health Administration and Policy. He oversees undergraduate, master’s and doctoral programs in health informatics. Dr. Wojtusiak teaches several courses focused on machine learning, data mining, artificial intelligence and computing applied in medicine, healthcare and individual/population health.

He authored or co-authored over 100 research publications and presentations and continues to collaborate with multiple national and international institutions.

Selected Community Service

  • Editorial Board, Computer Science Journal, AGH press
  • Associate Editor, Journal of Healthcare Informatics Research, Springer
  • Editorial Board, Internet of Things, Elsevier
  • National Science Foundation proposal reviewer and panelist in the Division of Intelligent and Information Systems
  • Polish Science Foundation proposal reviewer in Machine Learning
  • Judge at Fairfax County and Prince William County Regional Science Fair

Research

Research Interests

  • Health Informatics
  • Artificial Intelligence
  • Machine Learning
  • Clinical decision support
  • Population Health
  • Computational Methods in Health 

Publications

For complete list, see https://www.mli.gmu.edu/jwojt

Wojtusiak, J. and Asadzadehzanjani, N., “Discussion on Comparing Machine Learning Models for Health Outcome Prediction,” HEALTHINF 2022, 5, 713-720, 2022.

Wojtusiak, J., Alemi, F., Asadzadehzanjani, N., Levy, C. and Williams, A., “Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients,” BMC Medical Informatics and Decision Making, 21, 2021.

Wojtusiak, J., Wang, Y., Vakkalagadda, V., Alemi, F. and Roess, A., "Using Wi-Fi Infrastructure to Predict Contacts During Pandemics," IEEE International Conference on Healthcare Informatics, Victoria, Canada, 2021.

Wojtusiak, J. and Mogharab Nia, R., "Location Prediction Using GPS Trackers: Can Machine Learning Help Locate the Missing People with Dementia?," Internet of Things, Elsevier, 2021 (online since 2019).

Wojtusiak, J., "Reproducibility, Transparency and Evaluation of Machine Learning in Health Applications," HEALTHINF, 2021.

Wojtusiak, J., Asadzadehzanjani, N., Levy, C., Alemi, F. and Williams, A., "Online Decision Support Tool that Explains Temporal Prediction of Activities of Daily Living (ADL)," HEALTHINF, 2021.

Wojtusiak, J., Bagchi, P., Durbha, S., Mobahi, H., Mogharab Nia, R. and Roess, A., "COVID-19 Symptom Monitoring and Social Distancing in a University Population," Journal of Health Informatics Research, 2021.

Wojtusiak, J., Alemi, F., Asadzadehzanjani, N., Levy, C. and Williams, A., "Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients," BMC Medical Informatics and Decision Making, 21, 2021.

Wojtusiak, J., Bagchi, P., Durbha, S., Mobahi, H., Mogharab Nia, R. and Roess, A., "COVID-19 Symptom Monitoring and Social Distancing in a University Population," IEEE International Conference on Healthcare Informatics (ICHI), November, 2020.

Kheirbek, R., Alemi, Y., Wojtusiak, J., Kheirbek, L., Madison, S., Fokar, A., Doukky, R. and Moore, H.J., "Impact of Hospice and Palliative Care Service Utilization on All-Cause 30-Day Readmission Rate for Older Adults Hospitalized with Heart Failure," American Journal of Hospice and Palliative Medicine, 2019.

Kheirbek, R., Alemi, Y., Wojtusiak, J., Kheirbek, L., Madison, S., Fokar, A., Doukky, R. and Moore, H.J., "Impact of Hospice and Palliative Care Service Utilization on All-Cause 30-Day Readmission Rate for Older Adults Hospitalized with Heart Failure," American Journal of Hospice and Palliative Medicine, 2019.

Zare, M., Wojtusiak, J. and Nilashi, M., "Prediction of Patients’ Mortality during Hospitalizations," Journal of Soft Computing and Decision Support Systems, 5(4), 26-32, 2018.

Wojtusiak, J., Elashkar, E. and Mogharab Nia, R., "C-LACE2: computational risk assessment tool for 30-day post hospital discharge mortality," Health and Technology, Springer, 2018.

ElRafey, A. and Wojtusiak, J., "A Hybrid Active Learning and Progressive Sampling Algorithm," International Journal of Machine Learning and Computing, 8(5), 423-427, 2018.

ElRafey, A., & Wojtusiak, J. (2017). Recent advances in scaling‐down sampling methods in machine learning. Wiley Interdisciplinary Reviews: Computational Statistics.

Min, H., Avramovic, S., Wojtusiak, J., Khosla, R., Fletcher, R.D., Alemi, F., & Elfadel, K.R. (2017). A comprehensive multimorbidity index for predicting mortality in intensive care unit patients. Journal of palliative medicine, 1; 20(1),35-41.

Min, H., Mobahi, H., Irvin, K., Avramovic, S., & Wojtusiak, J. (2017). Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology. Journal of Biomedical Semantics, 16; 8(1),39.

Kheirbek, R., Wojtusiak, J., Alemi, F., & Vlaicu, S. (2016). Lack of evidence for racial disparity in 30-day all-cause readmission rate for older US veterans hospitalized with heart failure. Quality Management in Health Care, 25(4), 191 196.

Wojtusiak, J., Alemi, F., Levy, C., & Williams, A. (2016). Predicting functional decline and recovery following hospitalization of residents in veterans affairs nursing homes. The Gerontologist, 56 (1), 42-51.

Levy, C., Zargoush, M., Williams, A., Williams, A.R., Giang, P., Wojtusiak, J., Kheirbek, R., & Alemi, F. (2016). Sequence of functional loss and recovery in nursing homes. The Gerontologist, 56 (1).

Levy C., Alemi F., Williams A.E., Williams A.R., Wojtusiak J., Sutton B., P Giang, Pracht, E., & Argyros, L. (2015). Shared homes as an alternative to nursing home care: impact of VA’s medical foster home program on hospitalization. The Gerontologist, 56(1).

Helmchen, L.A., Burke, M.E., Wojtusiak, J. (2015). Designing highly reliable adverse-event detection systems to predict subsequent claims. Journal of Healthcare Risk Management, 34(4):7-17.

Levy, C., Kheirbek, R., Alemi, F., Wojtusiak, J., Sutton, B., Williams, A.R., Williams, A. (2015). Predictors of 6-month mortality among nursing home residents: diagnoses maybe more predictive than functional disability. Journal of Palliative Medicine, 18(2):100-6.

Ngufor, C., & Wojtusiak, J. (2014). Learning from large distributed data: a scaling down sampling scheme for efficient data processing. International Journal of Machine Learning and Computing (IJMLC), 4(3), 216-224.

Domanski, P.A., Brown, J.S., Heo, J., Wojtusiak, J., & McLinden, M.O. (2014). “A thermodynamic analysis of refrigerants: Performance limits of the vapor compression cycle,” International Journal of Refrigeration, 38, 71-79.

Ngufor, C., & Wojtusiak, J. (2013). Unsupervised labeling of data for supervised learning and its application to medical claims prediction. Computer Science Journal, AGH Press, 14, 2, 191-214.

Wojtusiak, J., Warden, T., & Herzog, O. (2012). Machine learning in agent-based stochastic simulation: Inferential theory and evaluation in transportation logistics. Computers & Mathematics with Applications, 64, 12, 3658-3665.

Wojtusiak, J., Warden, T., & Herzog, O. (2012). The learnable evolution model in agent-based delivery optimization. Memetic Computing, 4, 3, 165-181.

Yashar, D., Wojtusiak, J., Kaufman, K., & Domanski, P.A. (2012). A dual mode evolutionary algorithm for designing optimized refrigerant circuitries for finned tube heat exchangers. HVAC&R Research, 18, 5, 834-844.

Michalski, R. S., & Wojtusiak, J. (2012). Reasoning with missing, not-applicable and irrelevant meta-values in concept learning and pattern discovery. Journal of Intelligent Information Systems, 39, 141-166, Springer.

Wojtusiak, J., Gewa, C.A., & Pawloski, L.A. (2011). Dietary assessment in Africa: integration with innovative technology,” African Journal of Food, Agriculture, Nutrition, and Development, 11, 7.

Landon, B.E. , Reschovsky, J.D. , Pham, H.H., Kitsantas, P., Wojtusiak, J., & Hadley, J. (2009). Creating a parsimonious typology of physician financial incentives," Health Services and Outcomes Research Methodology, 9, 219-233.

Wojtusiak, J., Chorowski, J., Pietrzykowski, J., & Zurada, J. M. (2009). Searching and reasoning with distributed resources in computational intelligence and machine learning. Journal of Applied Computer Science Methods, 1, 2.

Wojtusiak, J., Michalski, R. S., Simanivanh, T., & Baranova, A. V. (2009). Towards application of rule learning to the meta-analysis of clinical data: An example of the metabolic syndrome. International Journal of Medical Informatics, 4, 1, pp. 43-54.

Wojtusiak, J. (2009). The LEM3 system for multitype evolutionary optimization. Computing and Informatics, 28, pp. 225-236.

Zurada, J. M., Mazurowski, M.A., Abdullin, A., Ragade, R., Wojtusiak, J., & Gentle, J. E. (2009). Building virtual community in computational intelligence and machine learning. Computational Intelligence Magazine, 4, 1, pp. 43-54.

Wojtusiak, J. & Michalski, R. S. (2008). Analyzing diaries for analytical relapse prevention using natural induction: A method and preliminary results," Quality Management in Health Care, 17.

Wojtusiak, J. (2007). Handling constrained optimization problems and using constructive induction to improve representation spaces in learnable evolution model. SIGEVOlution, Dissertation Corner, 2(3), 24-25.

Honors and Awards

  • Shirley S. Travis Habit of Excellence Award, 2016, College of Health and Human Services, George Mason University
  • Award for Outstanding Doctoral Work, 2008, George Mason University Department of Computational and Data Sciences
  • Best poster presentation Award, 2007, Sixth International Conference on Machine Learning and Applications

Degrees

  • PhD, Computational Sciences and Informatics, George Mason University
  • MS, Computer Science, Jagiellonian University, Krakow, Poland