Online Program Home
My Program

Abstract Details

Activity Number: 551 - Risk Prediction Methods and Applications in Risk Stratified Prevention
Type: Invited
Date/Time: Wednesday, July 31, 2019 : 2:00 PM to 3:50 PM
Sponsor: ENAR
Abstract #300255 Presentation
Title: Racial and Ethnic Fairness in Clinical Risk Prediction with an Application to Suicide Risk Prediction
Author(s): Rebecca Yates Coley* and Eric Johnson and Susan Shortreed
Companies: Kaiser Permanente Washington Health Research Institute and Kaiser Permanente Washington Health Research Institute and Kaiser Permanente Washington Health Research Institute
Keywords: precision medicine; risk prediction; electronic health record; decision support
Abstract:

There is growing interest in using risk prediction tools in clinical settings to inform diagnoses and treatment. Use of predictive algorithms in non-clinical applications have led to discrimination on the basis of race and ethnicity, leading to concerns about the potential for clinical risk prediction models to exacerbate race- and ethnicity-based health disparities. In this talk, we outline a framework for exploring the potential for a clinical prediction tool to perform differently across racial and ethnic groups given differential assessment of risk factors and the outcome and risk modification. We demonstrate this approach in a risk prediction model for 90-day suicide attempt risk following a mental health visit. We also discuss subjective considerations surrounding relative benefit and harm of possible interventions.


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

Back to the full JSM 2019 program