Left ventricular ejection fraction is disrupted in patients on maintenance hemodialysis and can be estimated using deep learning models on electrocardiograms. Smaller sample sizes within this population may be mitigated using transfer learning.

We identified patients on hemodialysis with transthoracic echocardiograms within 7 days of electrocardiogram using diagnostic/procedure codes. We developed four models: (1) trained from scratch in patients on hemodialysis, (2) pretrained on a publicly available set of natural images (ImageNet), (3) pretrained on all patients not on hemodialysis, and (4) pretrained on patients not on hemodialysis and fine-tuned on patients on hemodialysis. We assessed the ability of the models to classify left ventricular ejection fraction into clinically relevant categories of ≤40%, 41% to ≤50%, and >50%. We compared performance by area under the receiver operating characteristic curve.

We extracted 705,075 electrocardiogram:echocardiogram pairs for 158,840 patients not on hemodialysis used for development of models 3 and 4 and n=18,626 electrocardiogram:echocardiogram pairs for 2168 patients on hemodialysis for models 1, 2, and 4. The transfer learning model achieved area under the receiver operating characteristic curves of 0.86, 0.63, and 0.83 in predicting left ventricular ejection fraction categories of ≤40% (n=461), 41%–50% (n=398), and >50% (n=1309), respectively. For the same tasks, model 1 achieved area under the receiver operating characteristic curves of 0.74, 0.55, and 0.71, respectively; model 2 achieved area under the receiver operating characteristic curves of 0.71, 0.55, and 0.69, respectively, and model 3 achieved area under the receiver operating characteristic curves of 0.80, 0.51, and 0.77, respectively. We found that predictions of left ventricular ejection fraction by the transfer learning model were associated with mortality in a Cox regression with an adjusted hazard ratio of 1.29 (95% confidence interval, 1.04 to 1.59).

A deep learning model can determine left ventricular ejection fraction for patients on hemodialysis following pretraining on electrocardiograms of patients not on hemodialysis. Predictions of low ejection fraction from this model were associated with mortality over a 5-year follow-up period.

This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2022_06_06_CJN16481221.mp3

维持性血液透析患者的左心室射血分数受到干扰，可以使用心电图深度学习模型进行估计。使用迁移学习可以减少该群体中较小的样本量。

我们使用诊断/程序代码在心电图检查后 7 天内通过经胸超声心动图确定了接受血液透析的患者。我们开发了四种模型：（ 1 ）在血液透析患者中​​从头开始训练，（ 2 ）在一组公开的自然图像（ImageNet）上进行预训练，（ 3 ）在所有未进行血液透析的患者上进行预训练，以及（ 4 ）在患者上进行预训练未进行血液透析并针对进行血液透析的患者进行微调。我们评估了模型将左心室射血分数分为≤40%、41%至≤50%和>50%的临床相关类别的能力。我们按接收者操作特征曲线下的面积比较性能。

我们提取了 158,840 名未接受血液透析的患者的 705,075 个心电图：超声心动图对，用于模型 3 和 4 的开发，并且为模型 1、2 和 4 提取了 2168 名接受血液透析的患者的n = 18,626 个心电图：超声心动图对。迁移学习模型实现了以下面积受试者工作特征曲线分别为 0.86、0.63 和 0.83，预测左心室射血分数类别为 ≤40% ( n =461)、41%–50% ( n =398) 和 >50% ( n =1309)，分别。对于相同的任务，模型 1 的接收者操作特征曲线下面积分别为 0.74、0.55 和 0.71；模型 2 的接收者操作特征曲线下面积分别为 0.71、0.55 和 0.69，模型 3 的接收者操作特征曲线下面积分别为 0.80、0.51 和 0.77。我们发现，转移学习模型对左心室射血分数的预测与 Cox 回归中的死亡率相关，调整后的风险比为 1.29（95% 置信区间，1.04 至 1.59）。

深度学习模型可以在对未进行血液透析的患者进行心电图预训练后，确定进行血液透析的患者的左心室射血分数。该模型对低射血分数的预测与 5 年随访期间的死亡率相关。

本文包含播客 https://www.asn-online.org/media/podcast/CJASN/2022_06_06_CJN16481221.mp3