Department of Anesthesiology, the Eighth Affiliated Hospital, Sun Yat-sen University, Shenzhen 518033, China.
Department of Anesthesiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510000, China.
Postgrad Med J. 2023 Nov 20;99(1178):1280-1286. doi: 10.1093/postmj/qgad087.
Controlled low central venous pressure (CLCVP) technique has been extensively validated in clinical practices to decrease intraoperative bleeding during liver resection process; however, no studies to date have attempted to propose a scoring method to better understand what risk factors might still be responsible for bleeding when CLCVP technique was implemented.
We aimed to use machine learning to develop a model for detecting the risk factors of major bleeding in patients who underwent liver resection using CLCVP technique. We reviewed the medical records of 1077 patients who underwent liver surgery between January 2017 and June 2020. We evaluated the XGBoost model and logistic regression model using stratified K-fold cross-validation (K = 5), and the area under the receiver operating characteristic curve, the recall rate, precision rate, and accuracy score were calculated and compared. The SHapley Additive exPlanations was employed to identify the most influencing factors and their contribution to the prediction.
The XGBoost classifier with an accuracy of 0.80 and precision of 0.89 outperformed the logistic regression model with an accuracy of 0.76 and precision of 0.79. According to the SHapley Additive exPlanations summary plot, the top six variables ranked from most to least important included intraoperative hematocrit, surgery duration, intraoperative lactate, preoperative hemoglobin, preoperative aspartate transaminase, and Pringle maneuver duration.
Anesthesiologists should be aware of the potential impact of increased Pringle maneuver duration and lactate levels on intraoperative major bleeding in patients undergoing liver resection with CLCVP technique. What is already known on this topic-Low central venous pressure technique has already been extensively validated in clinical practices, with no prediction model for major bleeding. What this study adds-The XGBoost classifier outperformed logistic regression model for the prediction of major bleeding during liver resection with low central venous pressure technique. How this study might affect research, practice, or policy-anesthesiologists should be aware of the potential impact of increased PM duration and lactate levels on intraoperative major bleeding in patients undergoing liver resection with CLCVP technique.
在肝切除术过程中，控制性低中心静脉压（CLCVP）技术已在临床实践中得到广泛验证，可以减少术中出血；然而，迄今为止尚无研究试图提出一种评分方法，以更好地了解在实施 CLCVP 技术时哪些危险因素仍可能导致出血。
我们旨在使用机器学习为使用 CLCVP 技术进行肝切除术的患者建立检测大出血风险因素的模型。我们回顾了 2017 年 1 月至 2020 年 6 月期间接受肝手术的 1077 名患者的病历。我们使用分层 K 折交叉验证（K=5）评估 XGBoost 模型和逻辑回归模型，计算并比较了受试者工作特征曲线下面积、召回率、精度率和准确率评分。采用 Shapley 加法解释法确定最具影响力的因素及其对预测的贡献。
XGBoost 分类器的准确率为 0.80，精度为 0.89，优于准确率为 0.76、精度为 0.79 的逻辑回归模型。根据 Shapley 加法解释摘要图，最重要的前六个变量从最重要到最不重要依次为术中血细胞比容、手术时间、术中乳酸、术前血红蛋白、术前天冬氨酸转氨酶和阻断时间。
麻醉师应注意增加阻断时间和乳酸水平对接受 CLCVP 技术行肝切除术患者术中大出血的潜在影响。
本研究主题已知内容-低中心静脉压技术已在临床实践中得到广泛验证，尚无预测大出血的模型。本研究新增内容-XGBoost 分类器在预测低中心静脉压技术行肝切除术术中大出血方面优于逻辑回归模型。本研究可能对研究、实践或政策产生的影响-麻醉师应注意增加阻断时间和乳酸水平对接受 CLCVP 技术行肝切除术患者术中大出血的潜在影响。
