Pokhrel Bhattarai Sunita, Dzikowicz Dillon J, Xue Ying, Block Robert, Tucker Rebecca G, Bhandari Shilpa, Boulware Victoria E, Stone Breanne, Carey Mary G
University of Rochester School of Nursing, NY, USA.
University of Rochester School of Nursing, NY, USA; University of Rochester Medical Center, NY, USA; Clinical Cardiovascular Research Center, University of Rochester Medical Center, NY, USA.
J Electrocardiol. 2025 Mar-Apr;89:153878. doi: 10.1016/j.jelectrocard.2025.153878. Epub 2025 Jan 10.
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.
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.
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 (IQR:1.8). A total of 914 echocardiograms and ECGs were matched; the time between ECG-Echocardiogram was 9 h (IQR of 9 h); ≤30 % LVEF (16.45 %, n = 140). Lasso demonstrated 42 ECG features important for estimating LVEF ≤30 %. The predictive model of LVEF ≤30 % showed 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 %.
An explainable machine learning model with physiologically feasible predictors may help screen patients with low LVEF in AHF.
在急诊科使用心电图（ECG）识别左心室射血分数（LVEF）低的患者可能会优化急性心力衰竭（AHF）的管理。我们旨在评估527个自动12导联心电图特征在估计AHF患者LVEF方面的有效性。
分析年龄>18岁且有AHF相关ICD编码、人口统计学特征、LVEF百分比、合并症和用药情况的患者病历。最小绝对收缩和选择算子（LASSO）确定重要的心电图特征并评估性能。
在851例患者中，平均年龄为74岁（四分位间距：11），男性占56%（n = 478），体重指数中位数为29 kg/m（四分位间距：1.8）。共匹配了914份超声心动图和心电图；心电图与超声心动图之间的时间间隔为9小时（四分位间距为9小时）；LVEF≤30%（16.45%，n = 140）。LASSO显示42个心电图特征对估计LVEF≤30%很重要。LVEF≤30%的预测模型曲线下面积（AUC）为0.86，95%置信区间（CI）为0.83至0.89，特异性为54%（50%至57%），敏感性为91（95%CI：88%至96%），准确性为60%（95%CI：60%至63%），阴性预测值为95%。
具有生理上可行预测因子的可解释机器学习模型可能有助于筛查AHF中LVEF低的患者。
