Predicting ICD-9 code groups with fuzzy similarity based supervised multi-label classification of unstructured clinical nursing notes

作者：

Highlights：

• Design of a fuzzy similarity matching approach for raw clinical data.

• Extracting patient-specific information from unstructured nursing notes.

• Eliminating the dependency on structured EHRs by utilizing clinical text.

• Our approach outperforms the structured data based state-of-the-art model.

摘要

•Design of a fuzzy similarity matching approach for raw clinical data.•Extracting patient-specific information from unstructured nursing notes.•Eliminating the dependency on structured EHRs by utilizing clinical text.•Our approach outperforms the structured data based state-of-the-art model.

论文关键词：Clinical decision support systems,Disease prediction,Healthcare analytics,ICD-9 code group prediction,Machine learning,Natural language processing

论文评审过程：Received 10 May 2019, Revised 28 November 2019, Accepted 30 November 2019, Available online 3 December 2019, Version of Record 7 February 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.105321