Hongqiao International Institute of Medicine, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, 1111 XianXia Road, Shanghai, 200336, China.
Department of Anesthesiology, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, 1111 XianXia Road, Shanghai, 200336, China.
BMC Med Inform Decis Mak. 2023 Aug 10;23(1):156. doi: 10.1186/s12911-023-02253-w.
Prediction tools for various intraoperative bleeding events remain scarce. We aim to develop machine learning-based models and identify the most important predictors by real-world data from electronic medical records (EMRs).
An established database of surgical inpatients in Shanghai was utilized for analysis. A total of 51,173 inpatients were assessed for eligibility. 48,543 inpatients were obtained in the dataset and patients were divided into haemorrhage (N = 9728) and without-haemorrhage (N = 38,815) groups according to their bleeding during the procedure. Candidate predictors were selected from 27 variables, including sex (N = 48,543), age (N = 48,543), BMI (N = 48,543), renal disease (N = 26), heart disease (N = 1309), hypertension (N = 9579), diabetes (N = 4165), coagulopathy (N = 47), and other features. The models were constructed by 7 machine learning algorithms, i.e., light gradient boosting (LGB), extreme gradient boosting (XGB), cathepsin B (CatB), Ada-boosting of decision tree (AdaB), logistic regression (LR), long short-term memory (LSTM), and multilayer perception (MLP). An area under the receiver operating characteristic curve (AUC) was used to evaluate the model performance.
The mean age of the inpatients was 53 ± 17 years, and 57.5% were male. LGB showed the best predictive performance for intraoperative bleeding combining multiple indicators (AUC = 0.933, sensitivity = 0.87, specificity = 0.85, accuracy = 0.87) compared with XGB, CatB, AdaB, LR, MLP and LSTM. The three most important predictors identified by LGB were operative time, D-dimer (DD), and age.
We proposed LGB as the best Gradient Boosting Decision Tree (GBDT) algorithm for the evaluation of intraoperative bleeding. It is considered a simple and useful tool for predicting intraoperative bleeding in clinical settings. Operative time, DD, and age should receive attention.
各种术中出血事件的预测工具仍然稀缺。我们旨在通过电子病历（EMR）中的真实世界数据开发基于机器学习的模型并确定最重要的预测因素。
利用上海外科住院患者的现有数据库进行分析。共评估了 51173 名住院患者的资格。在数据集中共获得 48543 名住院患者，并根据手术期间的出血情况将患者分为出血（N=9728）和无出血（N=38815）组。从 27 个变量中选择候选预测因子，包括性别（N=48543）、年龄（N=48543）、BMI（N=48543）、肾脏疾病（N=26）、心脏病（N=1309）、高血压（N=9579）、糖尿病（N=4165）、凝血障碍（N=47）和其他特征。使用 7 种机器学习算法（即，轻梯度提升（LGB）、极端梯度提升（XGB）、组织蛋白酶 B（CatB）、决策树的 AdaBoost（AdaB）、逻辑回归（LR）、长短期记忆（LSTM）和多层感知（MLP））构建模型。接收器操作特征曲线下的面积（AUC）用于评估模型性能。
住院患者的平均年龄为 53±17 岁，57.5%为男性。与 XGB、CatB、AdaB、LR、MLP 和 LSTM 相比，LGB 结合多个指标对术中出血的预测性能最佳（AUC=0.933、敏感性=0.87、特异性=0.85、准确性=0.87）。LGB 确定的三个最重要的预测因素是手术时间、D-二聚体（DD）和年龄。
我们提出 LGB 作为评估术中出血的最佳梯度提升决策树（GBDT）算法。它被认为是一种在临床环境中预测术中出血的简单而有用的工具。应注意手术时间、DD 和年龄。
