Natural language processing to identify lupus nephritis phenotype in electronic health records.

Yu DengJennifer A PachecoAnika GhoshAnh ChungChengsheng MaoJoshua C SmithJuan ZhaoWei-Qi WeiApril BarnadoChad DornChunhua WengCong LiuAdam CordonJingzhi YuYacob TedlaAbel KhoRosalind Ramsey-GoldmanTheresa WalunasYuan Luo

Published in: BMC medical informatics and decision making (2024)

Our NLP MetaMap mixed model improved the F-measure greatly compared to the structured data only algorithm in both internal and external validation datasets. The NLP algorithms can serve as powerful tools to accurately identify lupus nephritis phenotype in EHR for clinical research and better targeted therapies.

Keyphrases

electronic health record
machine learning
clinical decision support
deep learning
adverse drug
autism spectrum disorder
artificial intelligence