Department of Pediatrics, University of Virginia School of Medicine, Charlottesville, VA, USA.
Department of Medicine, University of Virginia School of Medicine, Charlottesville, VA, USA.
Pediatr Res. 2023 Jun;93(7):1913-1921. doi: 10.1038/s41390-022-02444-7. Epub 2023 Jan 2.
Heart rate characteristics aid early detection of late-onset sepsis (LOS), but respiratory data contain additional signatures of illness due to infection. Predictive models using cardiorespiratory data may improve early sepsis detection. We hypothesized that heart rate (HR) and oxygenation (SpO) data contain signatures that improve sepsis risk prediction over HR or demographics alone.
We analyzed cardiorespiratory data from very low birth weight (VLBW, <1500 g) infants admitted to three NICUs. We developed and externally validated four machine learning models to predict LOS using features calculated every 10 m: mean, standard deviation, skewness, kurtosis of HR and SpO, and cross-correlation. We compared feature importance, discrimination, calibration, and dynamic prediction across models and cohorts. We built models of demographics and HR or SpO features alone for comparison with HR-SpO models.
Performance, feature importance, and calibration were similar among modeling methods. All models had favorable external validation performance. The HR-SpO model performed better than models using either HR or SpO alone. Demographics improved the discrimination of all physiologic data models but dampened dynamic performance.
Cardiorespiratory signatures detect LOS in VLBW infants at 3 NICUs. Demographics risk-stratify, but predictive modeling with both HR and SpO features provides the best dynamic risk prediction.
Heart rate characteristics aid early detection of late-onset sepsis, but respiratory data contain signatures of illness due to infection. Predictive models using both heart rate and respiratory data may improve early sepsis detection. A cardiorespiratory early warning score, analyzing heart rate from electrocardiogram or pulse oximetry with SpO, predicts late-onset sepsis within 24 h across multiple NICUs and detects sepsis better than heart rate characteristics or demographics alone. Demographics risk-stratify, but predictive modeling with both HR and SpO features provides the best dynamic risk prediction. The results increase understanding of physiologic signatures of neonatal sepsis.
心率特征有助于早期发现迟发性败血症（LOS），但呼吸数据因感染而包含疾病的其他特征。使用心肺数据的预测模型可能会提高早期败血症的检测效果。我们假设心率（HR）和氧合（SpO2）数据中包含的特征可改善败血症风险预测，优于 HR 或人口统计学数据。
我们分析了来自三个新生儿重症监护病房（NICU）的极低出生体重（VLBW，<1500g）婴儿的心肺数据。我们开发并外部验证了四个机器学习模型，以使用每 10m 计算的特征来预测 LOS，包括 HR 和 SpO2 的平均值、标准差、偏度、峰度和交叉相关。我们比较了模型和队列之间的特征重要性、区分度、校准和动态预测。我们建立了人口统计学和 HR 或 SpO2 特征的模型，以便与 HR-SpO2 模型进行比较。
在建模方法中，性能、特征重要性和校准结果相似。所有模型在外部验证中均具有良好的表现。HR-SpO2 模型的性能优于仅使用 HR 或 SpO2 的模型。人口统计学数据模型提高了所有生理数据模型的区分度，但降低了动态性能。
心肺特征可在 3 家 NICU 中检测出 VLBW 婴儿的 LOS。人口统计学数据可以进行风险分层，但同时使用 HR 和 SpO2 特征进行预测建模可提供最佳的动态风险预测。
心率特征可帮助早期发现迟发性败血症，但呼吸数据包含因感染引起的疾病特征。使用心率和呼吸数据的预测模型可能会提高早期败血症的检测效果。一种心肺早期预警评分，通过分析来自心电图或脉搏血氧仪的心率和 SpO2，可在多个 NICU 中在 24 小时内预测迟发性败血症，并比心率特征或人口统计学数据单独检测败血症的效果更好。人口统计学数据可以进行风险分层，但同时使用 HR 和 SpO2 特征进行预测建模可提供最佳的动态风险预测。结果增加了对新生儿败血症生理特征的理解。
