Ravi B Parikh: What’s the Best Way to Present AI Clinical Decision Support Outputs?
Ravi B Parikh, Medical Oncologist and Director of the Human-Algorithm Collaboration Lab (HACLab) at Emory University and Winship Cancer Institute, shared a post on LinkedIn:
“New in Society for Medical Decision Making (SMDM) MDM w/ Penn Center for Cancer Care Innovation (PC3I) Marilyn Schapira: What’s the best way to present AI clinical decision support outputs to improve decisions? In our randomized vignette study, presentation strategy influenced physicians’ accuracy, but had little influence on decision-making.
What does this mean? Accuracy of AI/ML important, but perhaps less important than the way outputs are presented/integrated into workflows. Our study suggests that iterating on information presentation may have little impact; more “in-your face” behavioral economics strategies may be necessary”
Title: The Impact of Machine Learning Mortality Risk Prediction on Clinician Prognostic Accuracy and Decision Support: A Randomized Vignette Study
Authors: Ravi B. Parikh, William J. Ferrell, Anthony Girard, Jenna White, Sophia Fang, Justin E. Bekelman, Marilyn M. Schapira
You can read the Full Article in the Sage Journals.
More posts featuring Ravi B Parikh on OncoDaily.
-
Challenging the Status Quo in Colorectal Cancer 2024
December 6-8, 2024
-
ESMO 2024 Congress
September 13-17, 2024
-
ASCO Annual Meeting
May 30 - June 4, 2024
-
Yvonne Award 2024
May 31, 2024
-
OncoThon 2024, Online
Feb. 15, 2024
-
Global Summit on War & Cancer 2023, Online
Dec. 14-16, 2023