Related Experiment Video
Updated: Feb 7, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Discovering and identifying New York heart association classification from electronic health records
Rui Zhang1,2, Sisi Ma3,4, Liesa Shanahan5
1Institute for Health Informatics, University of Minnesota, Minneapolis, MN, USA. zhan1386@umn.edu.
Insights
Extracting New York Heart Association (NYHA) class from electronic health records (EHR) is crucial for heart failure (HF) management. Natural language processing (NLP) effectively identifies NYHA class from clinical notes, improving patient care assessment.
Area of Science:
- Cardiology
- Medical Informatics
- Natural Language Processing
Background:
- Cardiac Resynchronization Therapy (CRT) is a key treatment for heart failure (HF).
- New York Heart Association (NYHA) class is vital for assessing HF patient response to CRT.
- NYHA class data is often missing in structured Electronic Health Record (EHR) data but present in clinical notes.
Purpose of the Study:
- To evaluate methods for extracting NYHA class from EHR data for heart failure patients.
- To compare rule-based versus machine learning-based Natural Language Processing (NLP) approaches for NYHA class identification.
- To determine the most effective source and method for capturing NYHA class information in EHRs.
Main Methods:
- A cohort of 36,276 heart failure or CRT patients' EHR data was analyzed.
- NYHA class identification was explored using diagnosis codes, procedure codes, and clinical notes.
- Rule-based and machine learning-based NLP methods were compared for extracting NYHA class from unstructured clinical notes.
Main Results:
- Only 19.2% of patients had NYHA class documented in their EHR.
- Clinical notes were the richest source for NYHA class information (95%), significantly outperforming diagnosis (31%) and procedure codes (2%).
- Machine learning NLP models, particularly a random forest with n-gram features, achieved a high F-measure of 93.78%, outperforming rule-based methods.
Conclusions:
- NYHA class documentation within EHRs is inconsistent and often suboptimal.
- Natural Language Processing (NLP) offers a viable and effective solution for extracting crucial NYHA class data from clinical notes.
- Accurate and consistent NYHA class extraction can enhance the understanding of HF progression and CRT effectiveness.
Background:
Cardiac Resynchronization Therapy (CRT) is an established pacing therapy for heart failure patients. The New York Heart Association (NYHA) class is often used as a measure of a patient's response to CRT. Identifying NYHA class for heart failure (HF) 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. Though NYHA is rarely stored in EHR structured data, such information is often documented in unstructured clinical notes.
Methods:
We accessed HF patients' data in a local EHR system and identified potential sources of NYHA, including local diagnosis codes, procedures, and clinical notes. We further investigated and compared the performances of rule-based versus machine learning-based natural language processing (NLP) methods to identify NYHA class from clinical notes.
Results:
Of the 36,276 patients with a diagnosis of HF or a CRT implant, 19.2% had NYHA class mentioned at least once in their EHR. While NYHA class existed in descriptive fields association with diagnosis codes (31%) or procedure codes (2%), the richest source of NYHA class was clinical notes (95%). A total of 6174 clinical notes were matched with hospital-specific custom NYHA class diagnosis codes. Machine learning-based methods outperformed a rule-based method. The best machine-learning method was a random forest with n-gram features (F-measure: 93.78%).
Conclusions:
NYHA class is documented in different parts in EHR for HF patients and the documentation rate is lower than expected. NLP methods are a feasible way to extract NYHA class information from clinical notes.
Related Concept Videos
01:11Purpose of Health Records I
Here's a breakdown of how health records serve these purposes:
01:19Purpose of Health Records II
01:30Heart Failure IV: Classification and Diagnostic Evaluation
01:24Data Reporting and Recording
02:54Classification of Elements and Compounds
Compounds are pure substances composed of two or more elements in fixed, definite proportions. Compounds are classified as ionic or molecular (covalent) based on the bonds...
04:00Periodic Classification of the Elements