Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram
Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram
复制标题
DOI：
10.1001/jamacardio.2019.0640
复制
发表时间：
2019-05-01
期刊：
影响因子：
24
通讯作者：
Friedman, Paul A.
中科院分区：
文献类型：
--
作者：
Galloway, Conner D.;Valys, Alexander V.;Friedman, Paul A.
重要性对于慢性肾脏病（CKD）患者，高钾血症很常见，与致命性心律失常相关，通常无症状，而指南指导的血清钾监测未得到充分利用。深度学习模型可以从心电图（ECG）中进行无创性高钾血症筛查，从而改善对这种危及生命的疾病的检测。目的评估深度学习模型在CKD患者心电图高钾血症检测中的性能。设计，设置，使用1994年至2017年在明尼苏达州罗切斯特的马约诊所就诊的449380名患者的1576581个ECG来训练深度卷积神经网络（DNN）。DNN使用2个（导联I和II）或4个（导联I、II、V3和V5）ECG导联进行训练，以检测血清钾水平为5.5 mEq/L或更低（转换为毫摩尔/升，乘以1），并使用明尼苏达州、佛罗里达和亚利桑那州马约诊所的回顾性数据进行验证。该验证包括61965例3期或以上CKD患者。每例患者在记录ECG后4小时内抽取血清钾计数。数据分析时间为2018年4月12日至2018年6月25日。结果使用深度学习模型。主要结果和指标以血清钾水平为参考标准，受试者工作特征曲线下面积（AUC）、灵敏度和特异度。该模型在2个操作点进行评估，一个是同等的特异性和敏感性，另一个是高灵敏度（90%）。3个验证数据集中的高钾血症患病率范围为2.6%（n = 1282/50 099;明尼苏达州）至4.8%（n = 287/6011;佛罗里达）。使用ECG导联I和II，深度学习模型的AUC为明尼苏达州的0.883（95% CI，0.873-0.893），佛罗里达的0.860（95% CI，0.837-0.883）和亚利桑那州的0.853（95% CI，0.830-0.877）。使用90%灵敏度工作点，灵敏度为90.2%（95%CI为88.4%~ 91.7%），特异性为63.2%（95%CI，62.7%-63.6%）;敏感性为91.3%（95%CI为87.4%~ 94.3%），特异性为54.7%（95% CI，53.4%-56.0%）（佛罗里达）;敏感性为88.9%（95%CI为84.5%~ 92.4%），特异性为55.0%（95%CI，53.7%-56.3%）。结论和相关性在这项研究中，仅使用2个ECG导联，深度学习模型检测到肾脏疾病患者的高钾血症，AUC为0.853至0.883。将人工智能应用于ECG可以筛查高钾血症。前瞻性研究是必要的。
IMPORTANCE For patients with chronic kidney disease (CKD), hyperkalemia is common, associated with fatal arrhythmias, and often asymptomatic, while guideline-directed monitoring of serum potassium is underused. A deep-learning model that enables noninvasive hyperkalemia screening from the electrocardiogram (ECG) may improve detection of this life-threatening condition.OBJECTIVE To evaluate the performance of a deep-learning model in detection of hyperkalemia from the ECG in patients with CKD.DESIGN, SETTING, AND PARTICIPANTS A deep convolutional neural network (DNN) was trained using 1 576 581 ECGs from 449 380 patients seen at Mayo Clinic, Rochester, Minnesota, from 1994 to 2017. The DNN was trained using 2 (leads I and II) or 4 (leads I, II, V3, and V5) ECG leads to detect serum potassium levels of 5.5 mEq/L or less (to convert to millimoles per liter, multiply by 1) and was validated using retrospective data from the Mayo Clinic in Minnesota, Florida, and Arizona. The validation included 61 965 patients with stage 3 or greater CKD. Each patient had a serum potassium count drawn within 4 hours after their ECG was recorded. Data were analyzed between April 12, 2018, and June 25, 2018.EXPOSURES Use of a deep-learning model.MAIN OUTCOMES AND MEASURES Area under the receiver operating characteristic curve (AUC) and sensitivity and specificity, with serum potassium level as the reference standard. The model was evaluated at 2 operating points, 1 for equal specificity and sensitivity and another for high (90%) sensitivity.RESULTS Of the total 1 638 546 ECGs, 908 000 (55%) were from men. The prevalence of hyperkalemia in the 3 validation data sets ranged from 2.6%(n = 1282 of 50 099; Minnesota) to 4.8%(n = 287 of 6011; Florida). Using ECG leads I and II, the AUC of the deep-learning model was 0.883 (95% CI, 0.873-0.893) for Minnesota, 0.860 (95% CI, 0.837-0.883) for Florida, and 0.853 (95% CI, 0.830-0.877) for Arizona. Using a 90% sensitivity operating point, the sensitivity was 90.2%(95% CI, 88.4%-91.7%) and specificity was 63.2%(95% CI, 62.7%-63.6%) for Minnesota; the sensitivity was 91.3%(95% CI, 87.4%-94.3%) and specificity was 54.7%(95% CI, 53.4%-56.0%) for Florida; and the sensitivity was 88.9% (95% CI, 84.5%-92.4%) and specificity was 55.0%(95% CI, 53.7%-56.3%) for Arizona.CONCLUSIONS AND RELEVANCE In this study, using only 2 ECG leads, a deep-learning model detected hyperkalemia in patients with renal disease with an AUC of 0.853 to 0.883. The application of artificial intelligence to the ECG may enable screening for hyperkalemia. Prospective studies are warranted.