Grader Variability and the Importance of Reference Standards for Evaluating Machine Learning Models for Diabetic Retinopathy.

Journal: Ophthalmology

Published Date: Aug 1, 2018

Abstract

PURPOSE: Use adjudication to quantify errors in diabetic retinopathy (DR) grading based on individual graders and majority decision, and to train an improved automated algorithm for DR grading.

Authors

Jonathan Krause

Artificial Intelligence Laboratory, Computer Science Department, Stanford University, Stanford, CA 94305.
Varun Gulshan

Google Inc, Mountain View, California.
Ehsan Rahimy

Department of Ophthalmology, Palo Alto Medical Foundation, Palo Alto, California.
Peter Karth

Oregon Eye Consultants, Eugene, Oregon.
Kasumi Widner

Google Inc, Mountain View, California.
Greg S Corrado

Google Health, Palo Alto, CA USA.
Lily Peng

Google Inc, Mountain View, California.
Dale R Webster

Google Inc, Mountain View, California.

Keywords

Algorithms Clinical Competence Diabetic Retinopathy Female Humans Machine Learning Male Mass Screening Middle Aged Ophthalmologists Reference Standards Retrospective Studies ROC Curve

External Resources

View on PubMed Access via DOI PubMed (29548646)

Grader Variability and the Importance of Reference Standards for Evaluating Machine Learning Models for Diabetic Retinopathy.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals