Predicting COVID-19 Symptoms From Free Text in Medical Records Using Artificial Intelligence: Feasibility Study.

Josefien Olmen Van Jens Van Nooten Hilde Philips Annet Sollie Walter Daelemans

Published in: JMIR medical informatics (2022)

The artificial intelligence model BERTje can reliably predict COVID-19-related information from medical records using text mining from the free text fields generated in primary care settings. This feasibility study invites researchers to examine further possibilities to use primary care routine data.

Keyphrases

artificial intelligence
primary care
big data
coronavirus disease
sars cov
machine learning
smoking cessation
deep learning
healthcare
general practice
electronic health record
clinical practice
health information
physical activity
drug induced