Session ID: 
105

Building a Machine Learning Model to Drive Clinical Insights

8:30am - 9:30am Wednesday, March 11
Orlando - Orange County Convention Center
W304A

Description

Continuous monitoring of blood pressure to avoid the onset of arterial hypotension is crucial during surgery and critical care. Current technologies are not very effective, and there is a need to improve prediction precision and timing relative to hypotensive event onset. Recent studies suggest that the prodromal stage of hemodynamic instability is characterized by subtle, complex changes in different physiologic variables. These changes can result in unique dynamic arterial waveform “signatures" that require machine learning and complex feature extraction techniques to be utilized. In this study, machine learning approaches were applied to arterial waveforms to develop an algorithm that observes subtle signs to predict hypotension episodes. Further, for the first time, real-world evidence and advanced data analytics were leveraged to quantify the association between hypotension exposure duration for various thresholds and critically ill sepsis patient morbidity and mortality outcomes.

Learning Objectives

  • Describe training and validating machine learning algorithms using complex physiological data
  • Use machine learning algorithm to drive clinical insights
  • Demonstrate how real-world evidence, captured in existing healthcare data, and advanced analytics can be used to inform clinical practice

Speaker(s)

Director R&D, Algorithms & Signal Processing,
Edwards Lifesciences
Principal,
Boston Strategic Partners, Inc.

Continuing Education Credits

ABPM
1.00
CAHIMS
1.00
CME
1.00
CNE
1.00
CPHIMS
1.00

Audience

Data Scientist
Physician or Physician’s Assistant
Research and Development Professional

Level

Advanced