Abstract

Creating evidence for acute management in spinal cord injury (SCI) is challenged by the difficulties of conducting randomized controlled trials. Real-world data provides a complementary, rich source of information that can be leveraged to generate evidence, gain understanding, and build prediction tools. In this presentation, we will discuss the use of machine learning in electronic health record data from acute hospitalization after SCI for research through two examples: hemodynamic management optimization in the operating room, and the use of routine blood data as dynamic biomarkers for outcome prediction.

Biography

Abel Torres Espín is an Assistant Professor at the School of Public Health Sciences at the University of Waterloo. He holds a BSc in Biology (Universitat de Barcelona), an MSc in biostatistics and bioinformatics (Universitat Oberta de Catalunya), and a PhD in Neuroscience (Universitat Autonoma de Barcelona). After his PhD, Abel moved to Edmonton to pursue a postdoctoral research period at the University of Alberta with Dr. Karim Fouad, followed by a postdoctoral position at the University of California, San Francisco in the U.S. with Dr. Adam Ferguson. Abel has been at the University of Waterloo since 2023, where he directs the health.data DRIVEN lab and teaches health data science courses. He and his team are currently working on applying computational, statistical, causal, and machine-learning methods for neuroepidemiology and personalized health research, as well as to predict and understand disease complexity in neurological conditions. Abel is also interested in data-driven discovery, open science, reproducibility, and data sharing.