Estimating Ejection Fraction from the 12 Lead ECG among Patients with Acute Heart Failure

Background

Identifying patients with low left ventricular ejection fraction (LVEF) in the emergency department using an electrocardiogram (ECG) may optimize acute heart failure (AHF) management. We aimed to assess the efficacy of 527 automated 12-lead ECG features for estimating LVEF among patients with AHF.

Method

Medical records of patients >18 years old and AHF-related ICD codes, demographics, LVEF %, comorbidities, and medication were analyzed. Least Absolute Shrinkage and Selection Operator (LASSO) identified important ECG features and evaluated performance.

Results

Among 851 patients, the mean age was 74 years (IQR:11), male 56% (n=478), and the median body mass index was 29 kg/m ² (IQR:1.8). A total of 914 echocardiograms and ECGs were matched; the time between ECG-Echocardiogram was 9 hours (IQR of 9 hours); < 30% LVEF (16.45%, n=140). Lasso demonstrated 42 ECG features important for estimating LVEF < 30%. The predictive model of LVEF < 30% demonstrated an area under the curve (AUC) of 0.86, a 95% confidence interval (CI) of 0.83 to 0.89, a specificity of 54% (50% to 57%), and a sensitivity of 91 (95% CI: 88% to 96%), accuracy 60% (95% CI:60 % to 63%) and, negative predictive value of 95%.

Conclusions

An explainable machine learning model with physiologically feasible predictors may be useful in screening patients with low LVEF in AHF.

Clinical Perspective

What is new?

• Among 527 ECG features, 42 were important in estimating < 30% reduced left ventricular ejection fraction (LVEF), showing the model’s high diagnostic accuracy (AUC of 0.86).

• The model exhibits exceptional sensitivity (91%) in predicting < 30% LVEF

• ECG-derived metrics offer the potential for early detection of reduced LVEF, especially in settings with limited advanced diagnostic tools.

What are the clinical implications?

• Enhanced diagnostic accuracy allows for the earlier detection of reduced LVEF through ECG analysis, which is critical in an environment where an echocardiogram is unavailable.

• ECG features enable patient risk stratification for reduced LVEF, facilitating targeted management and optimization of healthcare resources.

• The findings underscore the importance of integrating ECG features into AI-based diagnostic models for rapid, accurate LVEF estimation, supporting more informed clinical decisions and enabling effective remote patient monitoring.