Scholarlink

<p>Regional cerebral oxygen saturation (rSO<sub>2</sub>) is used to monitor cerebral perfusion with emerging evidence that optimization of rSO<sub>2</sub> may improve neurological and non-neurological outcomes. To manipulate rSO<sub>2</sub> an understanding of the variables that drive its behavior is necessary, and this can be accomplished using supervised machine learning. This study aimed to establish a hierarchy by which various hemodynamic and ventilatory variables contribute to intraoperative changes in rSO<sub>2</sub>. A post-hoc analysis 146 patients undergoing high risk surgery. rSO<sub>2</sub> was partitioned into segments with a change of at least 3% points over 5&#xa0;min. Features from hemodynamic and ventilatory variables were used to train a machine learning classification algorithm (XGBoost) for prediction of association with either up or down-sloping rSO<sub>2</sub>. The classifier was optimized and validated using five-fold cross validation. Feature importance was quantified based on information gain and permutation feature importance. The optimized classifier demonstrated a mean accuracy of 77.1% (SD 8.0%) and a mean area-under-ROC-curve of 0.86 (SD 0.06). The most important features based on information gain were the slope of the associated ETCO<sub>2</sub> signal, the slope of the SPO<sub>2</sub> signal, and the mean of the MAP signal. CO<sub>2</sub> is a significant mediator of changes in rSO<sub>2</sub> in an intraoperative setting, through its established effects on cerebral blood flow. This study furthers our overall understanding of the complex physiologic process that governs cerebral oxygenation by quantifying the hierarchy by which rSO<sub>2</sub> is affected. <b>Clinical Trial Number</b> NCT01838733 (ClinicalTrials.gov).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Characterizing drivers of change in intraoperative cerebral saturation using supervised machine learning

  • 期刊论文

  • 发表日期：

    2025年2月7日

查看全文
  • Philip J. Pries,
  • W. Alan C. Mutch,
  • Duane J. Funk

摘要

Regional cerebral oxygen saturation (rSO2) is used to monitor cerebral perfusion with emerging evidence that optimization of rSO2 may improve neurological and non-neurological outcomes. To manipulate rSO2 an understanding of the variables that drive its behavior is necessary, and this can be accomplished using supervised machine learning. This study aimed to establish a hierarchy by which various hemodynamic and ventilatory variables contribute to intraoperative changes in rSO2. A post-hoc analysis 146 patients undergoing high risk surgery. rSO2 was partitioned into segments with a change of at least 3% points over 5 min. Features from hemodynamic and ventilatory variables were used to train a machine learning classification algorithm (XGBoost) for prediction of association with either up or down-sloping rSO2. The classifier was optimized and validated using five-fold cross validation. Feature importance was quantified based on information gain and permutation feature importance. The optimized classifier demonstrated a mean accuracy of 77.1% (SD 8.0%) and a mean area-under-ROC-curve of 0.86 (SD 0.06). The most important features based on information gain were the slope of the associated ETCO2 signal, the slope of the SPO2 signal, and the mean of the MAP signal. CO2 is a significant mediator of changes in rSO2 in an intraoperative setting, through its established effects on cerebral blood flow. This study furthers our overall understanding of the complex physiologic process that governs cerebral oxygenation by quantifying the hierarchy by which rSO2 is affected. Clinical Trial Number NCT01838733 (ClinicalTrials.gov).