fb pixel
The University of Winnipeg

Dr. Camilo E. Valderrama

Camilo E. Valderrama Title: Assistant Professor
Phone: 204.258.3825
Office: 3D06A
Email: c.valderrama@uwinnipeg.ca
Website: https://sites.google.com/view/camilovalderrama/

Degrees:
B.Sc., Universidad Icesi, Colombia
Ph.D., Emory University
Post-Doctorate, University of Calgary

Affiliations:
Adjunct Assistant Professor. Departments of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada

Teaching Areas:
Machine Learning, Data Science, Pattern Recognition

Courses:
ACS-2906, Computer Architecture and System Software
ACS-4953, Introduction to Machine Learning
ACS-4930, Research Project
GACS-7203, Pattern Recognition

Research Interests:

Keywords: Machine Learning, Statistical Modeling, Biomedical Signal Processing, Health Data Science, Interpretable Artificial Intelligence, EEG Analysis


My research focuses on developing data-driven methodologies integrating machine learning, statistics, and signal processing to support patient safety, risk reduction, and well-being promotion. Instead of concentrating on a specific medical area, I have prioritized the development of transversal methodologies that can be applied across different contexts. This journey began during my PhD, where I worked on a project aimed at reducing perinatal deaths in vulnerable communities in Guatemala, which has one of the highest rates of perinatal mortality globally. My role on that project was to develop signal processing and machine learning methods to process one-dimensional Doppler ultrasound signals recorded with an inexpensive transducer to identify high-risk pregnancies requiring medical evaluation. Later, as a postdoctoral fellow, I focused on reducing patient risk through two primary projects. In my first project, I developed predictive models to identify redundant blood tests for intensive care unit (ICU) patients, a common issue that jeopardizes patient health and wastes clinical resources. My second project was interdisciplinary and aimed to address the high exposure of Canadian children to unhealthy food advertising on digital media. My role was to develop machine learning models to predict whether ads were food-related and targeted children. Now, as an Assistant Professor, I have continued to advance data-driven methodologies for patient safety through two main applications. First, due to the rising trend of emotional and mental disorders in Canada, I focus on developing methodologies that process electroencephalographic (EEG) signals to detect emotional states. Recognizing emotional states is essential for treating individuals with emotional disorders and offering strategies to improve their daily interactions. Second, I work on developing interpretable methodologies that leverage public birth datasets to identify risks associated with low birth weight (LBW), helping to identify high-risk pregnancies.

Publications:

To explore more of Camilo's publications, please click on the following links:

Selected publications:

  • Niaki M.; Dharia S.; Chen Y., Valderrama C. E. (2025). Bipartite Graph Adversarial Network for Subject-Independent Emotion Recognition. IEEE Journal of Biomedical and Health Informatics, https://doi.org/doi:10.1109/JBHI.2025.3570187.
  • Sheoran A., Valderrama C.E. (2025). Impact of sex differences on subject-independent EEG-based emotion recognition models. Computers in Biology and Medicine, 190, 110036. doi: https://doi.org/10.1016/j.compbiomed.2025.110036
  • Dola, S. S.; Nur, M. M. T; Valderrama, C. E. (2025). Developing Adjustable Birth Weight Cutoffs Based on Maternal Height and Apgar Scores. Machine Learning: Health. 1 015009, https://doi.org/10.1088/3049-477X/adfd63
  • Dharia, S. Y.; Liu, Q.; Smith, S. D; Valderrama, C. E. (2025). A Novel Approach for the Early Identification of Genetic Risk Factors for Alzheimer's Disease Using EEG and Psychometric Data. IEEE Journal of Biomedical and Health Informatics, https://doi.org/10.1109/JBHI.2025.3639217
  • Dola S. S., Valderrama, C.E. (2024). Exploring parental factors influencing low birth weight on the 2022 CDC natality dataset. BMC Medical Informatics and Decision Making, 24(1), 367. doi: https://doi.org/10.1186/s12911-024-02783-x