Online Program Home
My Program

Abstract Details

Activity Number: 192
Type: Contributed
Date/Time: Monday, August 1, 2016 : 10:30 AM to 12:20 PM
Sponsor: Quality and Productivity Section
Abstract #321022
Title: Biostatistics-Quality Improvement Collaboration Supporting a Learning Health Care System
Author(s): Henry Domenico*
Companies: Vanderbilt University School of Medicine
Keywords: Healthcare ; Quality Improvement ; Study Design ; Predictive Modeling ; Data Driven Decision Making ; Patient Outcomes
Abstract:

The fastest way for a healthcare system to improve outcomes is to become a learning healthcare system (LHS). A LHS is one in which research works together with operations. Optimal care strategies are identified by using a combination of novel study design and electronic health record (EHR) data. Once the optimal care strategy is identified, it is adopted as part of routine care. A LHS also utilizes EHR data to be proactive rather than reactive when preventing adverse outcomes. At the center of a LHS is biostatistics tightly integrated into quality improvement. Biostatisticians can ensure that decisions are not based on flawed evidence, such as that resulting from regression to the mean. Using this approach of implementing a scientific process into the workflow, we have conducted a cluster RCT enrolling 9340 which answers an important infection prevention question. This study was performed on a limited budget, without the need for external funding. We are using a similar approach to evaluate our Cornelius predictive modeling project, which gathers patient EHR data and predicts risk of adverse outcome. Here we present our lessons learned after 4 years with this collaboration.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association