■中心血流动力学参数通常通过肺动脉栓塞术进行测量,这是一种对患者有一定风险的侵入性手术,并非在所有情况下都常规可用。
■本研究旨在开发一种非侵入性方法来识别平均肺毛细血管楔压(mPCWP)升高。
■我们利用马萨诸塞州总医院248,955份临床记录的数据开发了一种深度学习模型,该模型可以使用12导联心电图(ECG)推断mPCWP>15mmHg。在这些数据中,242,216条记录用于预训练生成有用的ECG表示的模型。剩余的6,739条记录包含与mPCWP的直接测量的相遇。这些数据中有80%用于模型开发和测试(5,390),其余记录包括用于评估模型的保持集(1,349)。我们开发了一个相关的不可靠性评分,用于识别模型预测何时可能不可信。
■该模型实现了0.80±0.02(测试集)和0.79±0.01(保持集)的接收器工作特征曲线(AUC)下面积。模型性能随不可靠性而变化,其中不可靠评分高的患者对应于模型性能较差的子组:例如,在不靠性评分最高十分位的保持组中,患者的AUC降低为0.70±0.06.
■可以从ECG推断mPCWP,这种推断的可靠性是可以衡量的。当无法迅速进行侵入性监测时,深度学习模型可以提供可以为临床护理提供信息的信息。
UNASSIGNED: Central hemodynamic parameters are typically measured via pulmonary artery catherization-an invasive procedure that involves some risk to the patient and is not routinely available in all settings.
UNASSIGNED: This study sought to develop a noninvasive method to identify elevated mean pulmonary capillary wedge pressure (mPCWP).
UNASSIGNED: We leveraged data from 248,955 clinical records at the Massachusetts General Hospital to develop a deep learning model that can infer when the mPCWP >15 mmHg using the 12-lead electrocardiogram (ECG). Of these data, 242,216 records were used to pre-train a model that generates useful ECG representations. The remaining 6,739 records contain encounters with direct measurements of the mPCWP. Eighty percent of these data were used for model development and testing (5,390), and the remaining records comprise a holdout set (1,349) that was used to evaluate the model. We developed an associated unreliability score that identifies when model predictions are likely to be untrustworthy.
UNASSIGNED: The model achieves an area under the receiver operating characteristic curve (AUC) of 0.80 ± 0.02 (test set) and 0.79 ± 0.01 (holdout set). Model performance varies as a function of the unreliability, where patients with high unreliability scores correspond to a subgroup where model performance is poor: for example, patients in the holdout set with unreliability scores in the highest decile have a reduced AUC of 0.70 ± 0.06.
UNASSIGNED: The mPCWP can be inferred from the ECG, and the reliability of this inference can be measured. When invasive monitoring cannot be expeditiously performed, deep learning models may provide information that can inform clinical care.