Natural Language Processing and Graph Theory: Making Sense of Imaging Records in a Novel Representation Frame.

Laurent Binsfeld Gonçalves Ivan Nesic Marko Obradovic Bram Stieltjes Thomas Weikert Jens Bremerich

Published in: JMIR medical informatics (2022)

Automatically extracting the date of referrals from unstructured radiology reports using deep learning NLP algorithms is feasible. Graphs refined the selection of distinct pathology pathways, facilitated the revelation of missing comparisons, and enabled the query of specific referring exam sequences. Further work is needed to evaluate its benefits in clinics, research, and resource planning.

Keyphrases

deep learning
artificial intelligence
convolutional neural network
machine learning
high resolution
primary care
neural network
autism spectrum disorder
emergency department
mass spectrometry
genetic diversity