Automatic Classification of Thyroid Findings Using Static and Contextualized Ensemble Natural Language Processing Systems: Development Study.

Dongyup Shin Hye Jin Kam Min-Seok Jeon Ha Young Kim

Published in: JMIR medical informatics (2021)

The proposed SCENT demonstrates good classification performance despite the unique characteristics of the Korean language and problems of data lack and imbalance, especially for the extremely low amount of critical condition data. The result of SCENT-v1 indicates that different perspectives of static and contextual input token representations can enhance classification performance. SCENT-v2 has a strong impact on the prediction of healthy thyroid conditions.

Keyphrases

deep learning
machine learning
big data
convolutional neural network
electronic health record
autism spectrum disorder
artificial intelligence
mental health
working memory
data analysis
neural network