About Me

I am a PhD student in the School of Public Health Sciences at the University of Waterloo, supervised by Professor Abel Torres Espin. My academic background bridges computer science, data analytics, and public health, and my research focuses on applying machine learning and statistical modeling to explore complex health outcomes and promote data-driven healthcare innovation.

Through my research and academic work, I aim to advance precision health, promote the ethical use of AI in healthcare, and bridge the gap between data science and clinical decision-making.

Research Interests

  • Precision health and personalized medicine
  • Machine learning and AI for health research
  • Health informatics and digital health
  • Predictive modeling and quantitative analysis
 

Education

  • MSc – Public Health Sciences (Health Informatics), University of Waterloo, Canada
  • MCS – Computer Science and Higher Education, Drahomanov Ukrainian State University, Ukraine
  • BEd – Computer Science and Education, T.H. Shevchenko National University “Chernihiv Collegium”, Ukraine

My MSc Thesis

Title: Multi-Outcome Trajectories in Traumatic Brain Injury

Traumatic Brain Injury (TBI) presents a global health challenge, affecting millions of individuals annually and resulting in diverse outcome trajectories that complicate patient management. The heterogeneity in TBI outcomes, influenced by varied clinical presentations and injury responses, requires advanced analytical approaches. The analysis of trajectories using single metrics, such as the Glasgow Outcome Scale Extended Score (GOSE), falls short of capturing the multi-faceted nature of TBI progression, often overlooking the complexity of individual patient experiences.

The thesis reports on two studies. First, a systematic scoping review was conducted to synthesize the current research on trajectory analysis in TBI, followed by a modeling study. This work identifies six distinct multi-outcome trajectories in TBI patients by employing Latent Class Mixed Models (LCMM) and clustering approaches. Utilizing longitudinal data from the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) study — a prospective multicenter observational cohort study conducted at 18 level 1 trauma centers across the United States, which includes 17 selected outcome measures collected at four time points post-injury — provides a comprehensive understanding of the heterogeneous progression of TBI.

By addressing the limitations of single-outcome analyses, this research contributes to a better understanding of TBI progression that can lead to the optimization of TBI management and treatment. The future integration of these trajectories will facilitate the development of personalized treatment strategies, ultimately improving patient outcomes.