Improving Consensus Scoring of Crowdsourced Data Using the Rasch Model: Development and Refinement of a Diagnostic Instrument.

Christopher John Brady Lucy Iluka Mudie Xueyang Wang Eliseo Guallar David Steven Friedman

Published in: Journal of medical Internet research (2017)

Crowdsourced interpretations of retinal images provide rapid and accurate results as compared with a gold-standard grading. Creating a logistic regression model using Rasch analysis to weight crowdsourced classifications by worker ability improves accuracy of aggregated grades as compared with simple majority vote.

Keyphrases

optical coherence tomography
body mass index
deep learning
physical activity
weight loss
electronic health record
convolutional neural network
high resolution
weight gain
machine learning
clinical practice
mass spectrometry
patient reported outcomes
artificial intelligence