Related Experiment Video
Updated: Jul 15, 2025
09:20
Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction
Published on: February 13, 2021
6.5K
Automated Identification of Heart Failure with Reduced Ejection Fraction using Deep Learning-based Natural Language
Arash A Nargesi1,2, Philip Adejumo2, Lovedeep Dhingra2
1Heart and Vascular Center, Brigham and Women's Hospital, Harvard School of Medicine, Boston, MA.
Medrxiv : the Preprint Server for Health Sciences
|September 25, 2023
Summary
A new deep learning model accurately identifies patients with heart failure with reduced ejection fraction (HFrEF) from discharge summaries. This tool automates HFrEF identification, crucial for improving quality of care measurement.
Area of Science:
- Artificial Intelligence in Medicine
- Clinical Natural Language Processing
- Cardiovascular Health Informatics
Background:
- Automated tools are needed to measure care quality for heart failure with reduced ejection fraction (HFrEF).
- Accurate identification of HFrEF patients at hospital discharge is essential for quality assessment and improvement.
- Current methods lack the accessibility and accuracy required for a national quality improvement program.
Approach:
- Developed a novel deep learning language model using a semi-supervised learning framework.
- Trained and validated the model on discharge summaries from Yale New Haven Hospital (2015-2019), defining HFrEF by ejection fraction <40%.
- Externally validated the model on diverse datasets including Northwestern Medicine, Yale community hospitals, and the MIMIC-III database.
Key Points:
- The deep learning model achieved high performance in internal validation with an AUROC of 0.97 and AUPRC of 0.97.
- External validation demonstrated robust performance across multiple institutions (AUROC range: 0.91-0.95, AUPRC range: 0.91-0.96).
- Model-based HFrEF prediction significantly improved reclassification compared to chart diagnosis codes (NRI 60.2 ± 1.9%, p < 0.001).
Conclusions:
- A deep learning language model was successfully developed and validated for automated HFrEF identification from clinical notes.
- This model offers a precise and accurate method for identifying HFrEF patients, supporting automated quality assessment.
- The tool represents a significant advancement in automating quality measurement and improvement initiatives for HFrEF care.
Related Concept Videos
01:30Heart Failure IV: Classification and Diagnostic Evaluation
19
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
19
01:29Heart Failure II: Pathophysiology
14
Systolic Heart Failure and Compensatory MechanismsSystolic heart failure (also termed HFrEF, Heart Failure with Reduced Ejection Fraction) is the most prevalent type of heart filure. It results in a decreased volume of blood being pumped from the ventricle. The aortic arch and carotid sinuses have baroreceptors that detect reduced blood pressure, triggering the sympathetic nervous system (SNS) to release epinephrine and norepinephrine. Initially, this response aims to boost heart rate and...
14
01:17Pathophysiology of Heart Failure
1.6K
Heart failure (HF) is a progressive syndrome involving ventricles that leads to inadequate cardiac output. It can be classified based on location and output or ejection fraction. Ejection fraction (EF) is an essential measurement in the diagnosis and surveillance of HF. Reduced EF corresponds to systolic heart failure (HFrEF). However, HF with preserved ejection fraction (HFpEF) is becoming increasingly prevalent. Also known as diastolic HF, this form of HF is related to aging. The...
1.6K
01:27Heart Failure I: Introduction
14
Heart failure refers to a clinical syndrome caused by structural or functional cardiac disorders that prevent the heart from pumping an adequate amount of blood to meet the body's metabolic needs. This condition often arises from myocardial infarction or ischemia, leading to decreased cardiac output, reduced tissue perfusion, impaired gas exchange, fluid volume imbalance, and decreased functional ability.Heart failure can result from disruptions in the mechanisms that regulate cardiac output...
14
01:30Heart Failure V: Medical Management
12
Medical Management of Acute Decompensated Heart Failure (ADHF)The primary goals of therapy for patients hospitalized with acute decompensated heart failure (ADHF) include:Relieving symptomsOptimizing volume statusSupporting oxygenation and ventilationMaintaining cardiac output (CO) and end-organ perfusionIdentifying and addressing the cause of ADHFPreventing complicationsProviding patient education on factors precipitating HF exacerbationPlanning for dischargeOngoing monitoring and assessment...
12
01:30Heart Failure VII: Nursing Interventions
89
The first step in nursing management of a patient with heart failure involves thoroughly assessing the patient's medical history.Subjective Data: Obtain the patient's medical history of coronary artery disease, hypertension, myocardial infarction, and symptoms like dyspnea, orthopnea, and paroxysmal nocturnal dyspnea.Objective Data: Conduct a physical examination to identify findings such as jugular vein distention, pulmonary crackles, tachycardia, murmurs, peripheral edema, and vital signs,...
89