Deep Learning Predicts Heart Failure With Preserved, Mid-Range, and Reduced Left Ventricular Ejection Fraction From Patient Clinical Profiles

Abstract

Background: Left ventricular ejection fraction (LVEF) is the gold standard for evaluating heart failure (HF) in coronary artery disease (CAD) patients. It is an essential metric in categorizing HF patients as preserved (HFpEF), mid-range (HFmEF), and reduced (HFrEF) ejection fraction but differs, depending on whether the ASE/EACVI or ESC guidelines are used to classify HF.Objectives: We sought to investigate the effectiveness of using deep learning as an automated tool to predict LVEF from patient clinical profiles using regression and classification trained models. We further investigate the effect of utilizing other LVEF-based thresholds to examine the discrimination ability of deep learning between HF categories grouped with narrower ranges.Methods: Data from 303 CAD patients were obtained from American and Greek patient databases and categorized based on the American Society of Echocardiography and the European Association of Cardiovascular Imaging (ASE/EACVI) guidelines into HFpEF (EF > 55%), HFmEF (50% ≤ EF ≤ 55%), and HFrEF (EF < 50%). Clinical profiles included 13 demographical and clinical markers grouped as cardiovascular risk factors, medication, and history. The most significant and important markers were determined using linear regression fitting and Chi-squared test combined with a novel dimensionality reduction algorithm based on arc radial visualization (ArcViz). Two deep learning-based models were then developed and trained using convolutional neural networks (CNN) to estimate LVEF levels from the clinical information and for classification into one of three LVEF-based HF categories.Results: A total of seven clinical markers were found important for discriminating between the three HF categories. Using statistical analysis, diabetes, diuretics medication, and prior myocardial infarction were found statistically significant (p < 0.001). Furthermore, age, body mass index (BMI), anti-arrhythmics medication, and previous ventricular tachycardia were found important after projections on the ArcViz convex hull with an average nearest centroid (NC) accuracy of 94%. The regression model estimated LVEF levels successfully with an overall accuracy of 90%, average root mean square error (RMSE) of 4.13, and correlation coefficient of 0.85. A significant improvement was then obtained with the classification model, which predicted HF categories with an accuracy ≥93%, sensitivity ≥89%, 1-specificity <5%, and average area under the receiver operating characteristics curve (AUROC) of 0.98.Conclusions: Our study suggests the potential of implementing deep learning-based models clinically to ensure faster, yet accurate, automatic prediction of HF based on the ASE/EACVI LVEF guidelines with only clinical profiles and corresponding information as input to the models. Invasive, expensive, and time-consuming clinical testing could thus be avoided, enabling reduced stress in patients and simpler triage for further intervention.

Artificial intelligence-enabled electrocardiogram screens low left ventricular ejection fraction with a degree of confidence

“…The present study provided a continuous EF estimation with Pearson correlation coefficients of 0.61 and 0.58 as well as MAEs of 7.56 and 7.51 in the internal and external validation sets, respectively, which was compatible with the state-of-the-art performance. 29 , 30 Although previous studies used traditional regression output to estimate the EF, our DLM trained by the probability density function of a normal distribution also showed similar performance ( Supplemental Figure S2 ). The advantage of the proposed DLM was to provide a probabilistic forecast to better describe the prediction.…”

Leveraging Machine Learning Techniques to Forecast Chronic Total Occlusion before Coronary Angiography

“…Machine learning methods use computational algorithms to identify models in large datasets with multiple variables and can be used to construct predictive models [ 14 ]. Machine learning has demonstrated the potential for improving diagnostic accuracy and prognostic outcomes over conventional statistical methods [ 15 ]. There are also a number of other advantages to machine learning algorithms over traditional statistical modelling.…”

Deep Learning-Based Prediction Model of Heart Failure with Improved Ejection Fraction

“…Over the past few years, an increasing number of studies concentrate on deep learning models, and most of them are based on visualizations such as ECG, echocardiogram and cardiac magnetic resonance to train models 14 . Currently, studies have been conducted domestically and worldwide to analyze diverse types of clinical data such as electrocardiograms and echocardiograms, which based on deep learning to classify and evaluate the three traditional types of heart failure and risk stratification 3,15 . However, until recently, there is no research about constructing a prediction model for HFimpEF concerning deep learning.…”

“…According to the 2022 American College of Cardiology and the American Heart Association and the Heart Failure Society of America (ACC/AHA/HFSA) 2 , HF can be classified into four categories: heart failure with reduced ejection fraction (HFrEF) with an EF ≤40%, heart failure with preserved ejection fraction (HFpEF) with an EF ≥50%, heart failure with mildly reduced ejection fraction (HFmrEF) with an EF between 41 and 49%, and heart failure with improved ejection fraction (HFimpEF) with previous EF ≤40% and a follow-up EF of more than 40%. In recent years, deep learning algorithms have been widely implemented in the medical field to assist in diagnosis. Deep learning-based clinical profile can accelerate the diagnosis of HFrEF, HFpEF and HFmrEF patients 3 . However, the challenging remains in the diagnosis of HFimpEF requires multiple echocardiograms or cardiac magnetic resonance and laboratory data.…”