DIA 2021 Virtual Global Annual Meeting

Component Type: Session
Level: Intermediate
CE: ACPE 1.00 Knowledge UAN: 0286-0000-21-645-L04-P; CME 1.00; IACET 1.00; RN 1.00

Artificial intelligence technology is now being used to support decision-making in clinical trials and medical devices. This session will discuss fairness, bias, and how to respond to discrimination and security failures in predictive modeling systems.

Learning Objectives

Describe the different types of fairness metrics and algorithms for detecting and mitigating unintended machine learning algorithmic bias; Discuss a standardized workflow that focuses on artificial intelligence/machine learning model interpretability, post-hoc explanations, and discrimination testing.

Chair

David O Olaleye, PhD, MSc

Speaker

Application of Fairness and Bias Detection Metrics to a Real-World Clinical Prediction Problem
David O Olaleye, PhD, MSc

Real-World Experiences Helping Healthcare Companies Prepare For and Respond to Liabilities that Arise from Discrimination, Privacy, and Security Failures in Predictive Modeling Systems
Patrick Hall, MS

Disparities in Medication Access and Compliance: The Role of Machine Learning
Toyin Tofade, PharmD, MS