Statistical Challenges of Implementing an Automated EHR-based Prediction Model in Real Time

When: September 6th at Noon
Where: Virtual on Teams
Speaker: Dandan Liu, Associate Professor of Biostatistics, Executive Director Vanderbilt Biostatistics Data Coordinating Center (VBDCC), Director Vanderbilt Institute for Clinical and Translational Research (VICTR) Methods Program

Description:
Clinical prediction models have been widely acknowledged as informative tools providing evidence-based support for clinical decision making. However, such prediction models are often underused in clinical practice due to many reasons including the challenge of handling missing information upon real-time risk calculation and challenge of heterogeneity in standard of care across health care systems that impede adaption of existing prediction models. 

In this talk, Dr. Liu will showcase a real-world example of implementing an automated prediction model at multiple emergency department to identify emergency department patients with acute heart failure who can be safely discharged home rather than admitted to an inpatient setting, to demonstrate these challenges and associated opportunities for innovative statistical methods development and implementation. 

Click here to register!