Authors: Beren Semiz, Georgia Institute of Technology, Atlanta, GA, Sinan Hersek,
Georgia Institute of Technology, Atlanta, GA, Maziyar Baran Pouyan, Georgia Institute of Technology, Atlanta, GA, Cynthia Partida, University of California San Francisco, San Francisco, CA, Leticia Blazquez, University of California San Francisco, San Francisco, CA, Van Selby, University of California San Francisco, San Francisco, CA, Georg Wieselthaler, University of California San Francisco, San Francisco, CA, Omer T. Inan, Georgia Institute of Technology, Atlanta, GA, Liviu Klein, University of California San Francisco, San Francisco, CA,
Background: Pump thrombosis (PT), the most common cause of failure in ventricular assist devices (VADs), can be mitigated with earlier diagnosis before triggering any clinical events or requiring VAD replacement. Applying machine learning algorithms on pump acoustical signals provides substantial information regarding thrombosis states, and potentially allows for sensitive detection of PT assisting hemolysis biomarkers and pump powers.
Hypothesis: Acoustical signatures of VADs can provide substantial information regarding PT.
Conclusion: Applying machine learning algorithms on pump acoustical signals provides substantial information regarding thrombosis states, and potentially allows for sensitive detection of PT assisting hemolysis biomarkers and pump powers.
View Research -->