Adapting Animal Models to Assess Sufficiency of Fluid Resuscitation in Humans (Student Abstract)

Fluid resuscitation is an initial treatment frequently employed to treat shock, restore lost blood, protect tissues from injury, and prevent organ dysfunction in critically ill patients. However, it is not without risk (e.g., overly aggressive resuscitation may cause organ damage and even death). We leverage machine learning models trained to assess sufficiency of resuscitation in laboratory animals subjected to induced hemorrhage and transfer them to use with human trauma patients. Our key takeaway is that animal experiments and models can inform human healthcare, especially when human data is limited or when collecting relevant human data via potentially harmful protocols is unfeasible.

Authors

• Ryan Schuerkamp Auton Lab, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA College of Engineering and Computing, Miami University, Oxford, OH 45056, USA
• Xinyu Li Huazhong University of Science and Technology
• Brian Kunzer Auton Lab, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA
• Leonard S. Weiss School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
• Hernando Gómez School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
• Francis X. Guyette School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
• Michael R. Pinsky School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
• Artur Dubrawski Auton Lab, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA

Keywords

• AI For Healthcare
• Applications Of AI
• Domain Adaptation
• Machine Learning