Related Experiment Video
Updated: Feb 15, 2026

Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the
Jennifer Hornung Garvin1,2,3,4,5, Youngjun Kim2,6, Glenn Temple Gobbel7,8
1Health Information Management and Systems Division, School of Health and Rehabilitation Sciences, The Ohio State University, Columbus, OH, United States.
An automated natural language processing system accurately measures heart failure (HF) inpatient care quality. This tool, the Congestive Heart Failure Information Extraction Framework (CHIEF), shows high performance and potential for improving HF quality measurement efficiency.
Area of Science:
- Health Informatics
- Natural Language Processing (NLP)
- Cardiology
Background:
- Automated systems are needed to measure the quality of inpatient heart failure (HF) care.
- Natural Language Processing (NLP) offers a potential solution for automated quality measurement.
Purpose of the Study:
- To automate a specific United States Department of Veterans Affairs (VA) quality measure for inpatients with HF.
- To develop and evaluate the Congestive Heart Failure Information Extraction Framework (CHIEF) for HF quality assessment.
Main Methods:
- Automated the Congestive Heart Failure Inpatient Measure 19 (CHI19) focusing on left ventricular ejection fraction (LVEF) and medication prescriptions.
- Trained and tested the CHIEF using documents from 1083 inpatients across eight VA medical centers.
- Conducted stakeholder interviews to assess implementation feasibility and clinical utility.
Main Results:
- The CHIEF achieved high accuracy in classifying hospitalizations, with 98.9% sensitivity and 98.7% positive predictive value.
- The system successfully evaluated and classified 100% of the 1083 patient cases.
- Stakeholders identified facilitators and clinical applications for the CHIEF system.
Conclusions:
- The CHIEF system provides complete data for HF quality measurement.
- This automated NLP approach can enhance the efficiency, timeliness, and utility of HF quality assessments.
Related Concept Videos
Heart Failure II: Pathophysiology
Pathophysiology of Heart Failure
Heart Failure I: Introduction
Heart Failure VI: Adjunct Therapies
Heart Failure Drugs: Diuretics
Heart Failure V: Medical Management

