PMID- 30034925
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20201001
IS  - 2156-1125 (Print)
IS  - 2156-1125 (Linking)
VI  - 2017
DP  - 2017 Nov
TI  - Automatic Methods to Extract New York Heart Association Classification from 
      Clinical Notes.
PG  - 1296-1299
LID - 10.1109/BIBM.2017.8217848 [doi]
AB  - 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.
FAU - Zhang, Rui
AU  - Zhang R
AD  - Institute for Health Informatics, and College of Pharmacy, University of 
      Minnesota, Minneapolis, MN, USA.
FAU - Ma, Sisi
AU  - Ma S
AD  - Institute for Health Informatics, and Department of Medicine, University of 
      Minnesota, Minneapolis, MN, USA.
FAU - Shanahan, Liesa
AU  - Shanahan L
AD  - Medtronic, Inc., Minneapolis, MN, USA.
FAU - Munroe, Jessica
AU  - Munroe J
AD  - Medtronic, Inc., Minneapolis, MN, USA.
FAU - Horn, Sarah
AU  - Horn S
AD  - Medtronic, Inc., Minneapolis MN, USA.
FAU - Speedie, Stuart
AU  - Speedie S
AD  - Institute for Health Informatics, University of Minnesota, Minneapolis, MN, USA.
LA  - eng
GR  - UL1 TR000114/TR/NCATS NIH HHS/United States
PT  - Journal Article
DEP - 20171218
PL  - United States
TA  - Proceedings (IEEE Int Conf Bioinformatics Biomed)
JT  - Proceedings. IEEE International Conference on Bioinformatics and Biomedicine
JID - 101525347
PMC - PMC6051704
MID - NIHMS931056
OTO - NOTNLM
OT  - Clinical Notes
OT  - Electronic Health Records
OT  - Natural Language Processing
OT  - New York Heart Association (NYHA)
EDAT- 2018/07/24 06:00
MHDA- 2018/07/24 06:01
PMCR- 2018/07/18
CRDT- 2018/07/24 06:00
PHST- 2018/07/24 06:00 [entrez]
PHST- 2018/07/24 06:00 [pubmed]
PHST- 2018/07/24 06:01 [medline]
PHST- 2018/07/18 00:00 [pmc-release]
AID - 10.1109/BIBM.2017.8217848 [doi]
PST - ppublish
SO  - Proceedings (IEEE Int Conf Bioinformatics Biomed). 2017 Nov;2017:1296-1299. doi: 
      10.1109/BIBM.2017.8217848. Epub 2017 Dec 18.