基于机器学习的双部位脉搏血氧测量法在危重新生儿先天性心脏病筛查中的应用
Machine Learning-Based Critical Congenital Heart Disease Screening Using Dual-Site Pulse Oximetry Measurements.
机构信息
Department of Pediatrics University of California Davis CA.
Department of Electrical & Computer Engineering University of California Davis CA.
出版信息
J Am Heart Assoc. 2024 Jun 18;13(12):e033786. doi: 10.1161/JAHA.123.033786. Epub 2024 Jun 15.
BACKGROUND
Oxygen saturation (Spo) screening has not led to earlier detection of critical congenital heart disease (CCHD). Adding pulse oximetry features (ie, perfusion data and radiofemoral pulse delay) may improve CCHD detection, especially coarctation of the aorta (CoA). We developed and tested a machine learning (ML) pulse oximetry algorithm to enhance CCHD detection.
METHODS AND RESULTS
Six sites prospectively enrolled newborns with and without CCHD and recorded simultaneous pre- and postductal pulse oximetry. We focused on models at 1 versus 2 time points and with/without pulse delay for our ML algorithms. The sensitivity, specificity, and area under the receiver operating characteristic curve were compared between the Spo-alone and ML algorithms. A total of 523 newborns were enrolled (no CHD, 317; CHD, 74; CCHD, 132, of whom 21 had isolated CoA). When applying the Spo-alone algorithm to all patients, 26.2% of CCHD would be missed. We narrowed the sample to patients with both 2 time point measurements and pulse-delay data (no CHD, 65; CCHD, 14) to compare ML performance. Among these patients, sensitivity for CCHD detection increased with both the addition of pulse delay and a second time point. All ML models had 100% specificity. With a 2-time-points+pulse-delay model, CCHD sensitivity increased to 92.86% (=0.25) compared with Spo alone (71.43%), and CoA increased to 66.67% (=0.5) from 0. The area under the receiver operating characteristic curve for CCHD and CoA detection significantly improved (0.96 versus 0.83 for CCHD, 0.83 versus 0.48 for CoA; both =0.03) using the 2-time-points+pulse-delay model compared with Spo alone.
CONCLUSIONS
ML pulse oximetry that combines oxygenation, perfusion data, and pulse delay at 2 time points may improve detection of CCHD and CoA within 48 hours after birth.
REGISTRATION
URL: https://www.clinicaltrials.gov/study/NCT04056104?term=NCT04056104&rank=1; Unique identifier: NCT04056104.
背景
氧饱和度（Spo）筛查并未导致更早地发现严重先天性心脏病（CCHD）。添加脉搏血氧仪特征（即灌注数据和股动脉脉搏延迟）可能会改善 CCHD 的检测，尤其是主动脉缩窄（CoA）。我们开发并测试了一种机器学习（ML）脉搏血氧仪算法来增强 CCHD 的检测。
方法和结果
六个地点前瞻性地招募了患有和不患有 CCHD 的新生儿，并记录了同时的导管前和导管后的脉搏血氧仪数据。我们专注于我们的 ML 算法在 1 个和 2 个时间点以及有/无脉搏延迟的模型。Spo 单独和 ML 算法之间的敏感性、特异性和接收者操作特征曲线下面积进行了比较。总共纳入了 523 名新生儿（无 CHD，317 名；CHD，74 名；CCHD，132 名，其中 21 名患有孤立性 CoA）。当将 Spo 单独算法应用于所有患者时，26.2%的 CCHD 会被遗漏。我们将样本缩小到同时具有 2 个时间点测量值和脉搏延迟数据的患者（无 CHD，65 名；CCHD，14 名），以比较 ML 性能。在这些患者中，随着脉搏延迟和第二个时间点的加入，CCHD 的检测敏感性增加。所有 ML 模型的特异性均为 100%。使用 2 个时间点+脉搏延迟模型，CCHD 的敏感性从 Spo 单独的 71.43%增加到 92.86%（=0.25），CoA 从 0.48 增加到 66.67%（=0.5）。CCHD 和 CoA 检测的接收者操作特征曲线下面积显著提高（CCHD 为 0.96 对 0.83，CoA 为 0.83 对 0.48；均=0.03）与 Spo 单独相比，使用 2 个时间点+脉搏延迟模型。
结论
结合氧合、灌注数据和 2 个时间点的脉搏延迟的 ML 脉搏血氧仪可能会提高出生后 48 小时内 CCHD 和 CoA 的检测率。
登记
网址：https://www.clinicaltrials.gov/study/NCT04056104?term=NCT04056104&rank=1;独特标识符：NCT04056104。
Zotero 插件