Gutmann Andrea S, Mandl Maximilian M, Rieder Clemens, Hoechter Dominik J, Dietz Konstantin, Geisler Benjamin P, Boulesteix Anne-Laure, Tomasi Roland, Hinske Ludwig C
Department of Anaesthesiology, LMU University Hospital, LMU Munich, Munich, Germany.
Institute for Medical Information Processing, Biometry and Epidemiology (IBE), Faculty of Medicine, LMU Munich, Pettenkofer School of Public Health, Munich, Germany.
BMC Med Inform Decis Mak. 2025 Sep 3;25(1):326. doi: 10.1186/s12911-025-03148-8.
Brain tissue oxygenation is usually inferred from arterial partial pressure of oxygen (paO), which is in turn often inferred from pulse oximetry measurements or other non-invasive proxies. Our aim was to evaluate the feasibility of continuous paO prediction in an intraoperative setting among neurosurgical patients undergoing craniotomies with modern machine learning methods.
Data from routine clinical care of lung-healthy neurosurgical patients were extracted from databases of the respective clinical systems and normalized. We used recursive feature elimination to identify relevant features for the prediction of paO. Six machine learning regression algorithms (gradient boosting, k-nearest neighbors, random forest, support vector, neural network, linear model with stochastic gradient descent) and a multivariable linear regression were then tuned and fitted to the selected features. A performance matrix consisting of standard deviation of absolute errors (σ), mean absolute percentage error (MAPE), adjusted R, root mean squared error (RMSE), mean absolute error (MAE) and Spearman's ρ was finally computed based on the test set, and used to compare and rank each algorithm.
We analyzed N = 4,581 patients with n = 17,821 observations. Between 5 and 22 features were selected from the analysis of the training dataset comprising 3,436 patients with 13,257 observations. The best algorithm, a regularized linear model with stochastic gradient descent, could predict paO values with σ = 86.4 mmHg, MAPE = 16 %, adjusted R = 0.77, RMSE = 44 mmHg and Spearman's ρ = 0.83. Further improvement was possible by calibrating the algorithm with the first measured paO/FiO (p/F) ratio during surgery.
PaO can be predicted by perioperative routine data in neurosurgical patients even before blood gas analysis. The prediction improves further when including the first measured p/F ratio, realizing quasi-continuous paO monitoring.
脑组织氧合通常从动脉血氧分压（paO）推断而来，而动脉血氧分压又常常从脉搏血氧饱和度测量值或其他非侵入性指标推断得出。我们的目的是评估在接受开颅手术的神经外科患者术中，使用现代机器学习方法连续预测paO的可行性。
从各个临床系统的数据库中提取肺部健康的神经外科患者常规临床护理数据并进行标准化处理。我们使用递归特征消除法来识别预测paO的相关特征。然后对六种机器学习回归算法（梯度提升、k近邻、随机森林、支持向量、神经网络、带随机梯度下降的线性模型）和多变量线性回归进行调优并拟合到所选特征上。最后根据测试集计算出由绝对误差标准差（σ）、平均绝对百分比误差（MAPE）、调整后的R、均方根误差（RMSE）、平均绝对误差（MAE）和斯皮尔曼ρ组成的性能矩阵，并用于比较各算法并对其进行排名。
我们分析了N = 4581例患者，有n = 17821条观测值。在对包含3436例患者13257条观测值的训练数据集进行分析时，选取了5至22个特征。最佳算法是带随机梯度下降的正则化线性模型，其预测paO值时σ = 86.4 mmHg，MAPE = 16%，调整后的R = 0.77，RMSE = 44 mmHg，斯皮尔曼ρ = 0.83。在手术期间用首次测得的paO/FiO（p/F）比值对该算法进行校准可进一步改善预测效果。
神经外科患者的paO甚至在进行血气分析之前就可以通过围手术期常规数据进行预测。纳入首次测得的p/F比值时预测效果会进一步改善，从而实现近似连续的paO监测。
