Park Insun, Park Jae Hyon, Koo Young Hyun, Koo Chang-Hoon, Koo Bon-Wook, Kim Jin-Hee, Oh Ah-Young
Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam, Korea.
Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicines, Seoul, Korea.
Yonsei Med J. 2025 Mar;66(3):160-171. doi: 10.3349/ymj.2024.0020.
To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries.
Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an open-source registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers.
A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767-0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763-0.772), AdaBoost regressor (0.752; 95% CI, 0.743-0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669-0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all <0.001).
ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.
开发一种用于预测非心脏手术诱导后低血压（PIH）的机器学习（ML）分类器。
从开源数据库VitalDB中的3669例病例获取术前数据和早期生命体征。PIH定义为诱导后20分钟内或从诱导至切开时持续平均动脉压（MAP）<65 mmHg。使用六种不同的ML算法创建二元分类器以预测PIH。主要结果是ML分类器的受试者操作特征曲线下面积（AUROC）。
共有2321例（63.3%）病例出现PIH。在ML分类器中，随机森林回归器和极端梯度提升回归器显示出最高的AUROC，均记录为0.772。排除这些模型后，轻梯度提升机回归器显示出第二高的AUROC[0.769；95%置信区间（CI），0.767 - 0.771]，其次是梯度提升回归器（0.768；95% CI，0.763 - 0.772）、AdaBoost回归器（0.752；95% CI，0.743 - 0.761）和自动相关性确定回归（0.685；95% CI，0.669 - 0.701）。前三个重要特征是从麻醉诱导到气管插管时的平均舒张压（DBP）、最低MAP和最低DBP，且这些特征在PIH病例中较低（均<0.001）。
ML分类器在预测PIH方面表现出中等性能，具有实时预测的潜力。
