Cardiac Resynchronization Therapy (CRT) is an established pacing therapy for heart failure patients. The New York Heart Association (NYHA) classification is often used as a measure of a patient's response to CRT. Identifying NYHA class for heart failure patients in an electronic health record (EHR) consistently, over time, can provide better understanding of the progression of heart failure and assessment of CRT response and effectiveness. However, NYHA is rarely stored in EHR structured data such information is often documented in unstructured clinical notes. In this study, we thus investigated the use of natural language processing (NLP) methods to identify NYHA classification from clinical notes. We collected 6,174 clinical notes that were matched with hospital-specific custom NYHA class diagnosis codes. Machine-learning based methods performed similar with a rule-based method. The best machine-learning method, support vector machine with n-gram features, performed the best (93% F-measure). Further validation of the findings is required.
|Original language||English (US)|
|Title of host publication||Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017|
|Editors||Illhoi Yoo, Jane Huiru Zheng, Yang Gong, Xiaohua Tony Hu, Chi-Ren Shyu, Yana Bromberg, Jean Gao, Dmitry Korkin|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||4|
|State||Published - Dec 15 2017|
|Event||2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 - Kansas City, United States|
Duration: Nov 13 2017 → Nov 16 2017
|Name||Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017|
|Other||2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017|
|Period||11/13/17 → 11/16/17|
Bibliographical noteFunding Information:
Research supported by Medtronic through a contract with the University of Minnesota and by the Clinical and Translational Science Institute grant from National Center for Advancing Translational Sciences of the National Institutes
Research supported by Medtronic through a contract with the University of Minnesota and by the Clinical and Translational Science Institute grant from National Center for Advancing Translational Sciences of the National Institutes of Health (UL1TR000114, Blazar)
J. Munroe, L. Shanahan and S. Horn are employees of Medtronic, Inc. that manufactures and markets Cardiac Resynchronization Therapy devices. The research reported in this article was performed in collaboration with the named Medtronic, Inc. employees by R. Zhang, S. Ma and S. Speedie, faculty members at the University of Minnesota under a contract with the University of Minnesota funded by Medtronic, Inc. The University of Minnesota researchers did not receive any additional compensation for their work.
© 2017 IEEE.
- Clinical Notes
- Electronic Health Records
- Natural Language Processing
- New York Heart Association (NYHA)