Department of Stress Sciences and Psychosomatic Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
Sci Rep. 2024 Feb 26;14(1):4696. doi: 10.1038/s41598-024-55453-3.
Previous studies have successfully predicted overweight status by applying deep learning to 12-lead electrocardiogram (ECG); however, models for predicting underweight status remain unexplored. Here, we assessed the feasibility of deep learning in predicting extremely low body weight using 12-lead ECGs, thereby investigating the prediction rationale for highlighting the parts of ECGs that are associated with extremely low body weight. Using records of inpatients predominantly with anorexia nervosa, we trained a convolutional neural network (CNN) that inputs a 12-lead ECG and outputs a binary prediction of whether body mass index is ≤ 12.6 kg/m. This threshold was identified in a previous study as the optimal cutoff point for predicting the onset of refeeding syndrome. The CNN model achieved an area under the receiver operating characteristic curve of 0.807 (95% confidence interval, 0.745-0.869) on the test dataset. The gradient-weighted class activation map showed that the model focused on QRS waves. A negative correlation with the prediction scores was observed for QRS voltage. These results suggest that deep learning is feasible for predicting extremely low body weight using 12-lead ECGs, and several ECG features, such as lower QRS voltage, may be associated with extremely low body weight in patients with anorexia nervosa.
先前的研究已经成功地通过将深度学习应用于 12 导联心电图（ECG）来预测超重状态；然而，预测消瘦状态的模型仍未被探索。在这里，我们评估了使用 12 导联 ECG 进行深度学习预测极低体重的可行性，从而研究了突出与极低体重相关的 ECG 部分的预测原理。我们使用主要患有神经性厌食症的住院患者的记录来训练一个卷积神经网络（CNN），该网络输入 12 导联 ECG 并输出 BMI 是否≤12.6kg/m 的二进制预测。在之前的研究中，该阈值被确定为预测再喂养综合征发作的最佳截断点。CNN 模型在测试数据集上的受试者工作特征曲线下面积为 0.807（95%置信区间，0.745-0.869）。梯度加权类激活图显示，该模型专注于 QRS 波。与预测评分呈负相关的是 QRS 电压。这些结果表明，深度学习可以使用 12 导联 ECG 来预测极低体重，并且 QRS 电压等一些 ECG 特征可能与神经性厌食症患者的极低体重有关。
