摘要
目的分析腹腔镜胰十二指肠切除(LPD)术后临床相关胃排空延迟(CR-DGE)的危险因素,并基于多模型比较的机器学习方法建立预测LPD术后CR-DGE的模型。方法回顾性分析2019年1月至2023年12月在郑州大学人民医院行LPD的278例胰头和壶腹周围区域肿瘤患者的临床资料,其中男性167例,女性111例,年龄59(53,66)岁。依据术后是否发生CR-DGE分为两组:CR-DGE组(n=94)和非CR-DGE组(n=184)。比较两组患者的胰管直径、术中出血量、手术时间等主要临床资料。基于最小绝对收缩和选择算子(LASSO)算法对围手术期指标进行筛选,完成变量选择之后,将278例患者按8∶2的比例分为训练集(n=222)和验证集(n=56)。选用随机森林、自适应增强、轻量梯度提升、多层感知机、支持向量机、K近邻算法、决策树、补集朴素贝叶斯8种机器学习模型对训练集建模。采用验证集受试者工作特征曲线下面积(AUC)确定最优模型。通过校准图和决策曲线分析判断最优模型的预测性能。通过沙普利加和解释法(SHAP)分析各特征对预测的贡献。结果单因素分析显示,CR-DGE组和非CR-DGE组患者在年龄[66(62,69)岁比56(51,60)岁]、糖尿病[42.6%(40/94)比11.4%(21/184)]、纤维蛋白原[3.43(2.74,4.18)g/L比3.84(3.19,4.68)g/L]、胰管直径[2.00(1.50,2.70)mm比3.40(1.60,5.00)mm]、术中出血量[300(200,600)ml比200(150,300)ml]、手术时间[472(430,502)min比430(365,475)min]、临床相关胰瘘[34.0%(32/94)比3.8%(7/184)]、腹腔积液[46.8%(44/94)比12.5%(23/184)]、术后出血[20.2%(19/94)比3.3%(6/184)]、腹腔感染[28.7%(27/94)比11.4%(21/184)]以及术后胃肠减压时间[4.00(2.00,6.00)d比3.00(2.00,5.00)d]方面的差异均具有统计学差异(均P<0.05)。将LASSO筛选出的11个特征变量分别纳入8种机器学习模型,结果显示随机森林模型在验证集中的性能最佳,AUC=0.894(95%CI:0.800~0.985),准确度为0.820,灵敏度为0.606。校准图和决策曲线分析结果显示,随机森林模型的性能良好。采用SHAP分析对模型进行解释,显示年龄、胰管直径、术前天冬氨酸转氨酶是随机森林模型中贡献度较大的预测因子。结论本研究建立的随机森林模型对LPD术后CR-DGE的预测性能良好,有助于临床早期识别CR-DGE高风险患者。
Objective To analyze the risk factors for clinically relevant delayed gastric emptying(CR-DGE)following laparoscopic pancreaticoduodenectomy(LPD)and to develop a model to predict the postoperative CR-DGE after LPD using the machine-learning approach with multi-model comparison.Methods Clinical data of 278 patients with tumors located in the pancreatic head and periampullary region undergoing LPD at People’s Hospital of Zhengzhou University from January 2019 to December 2023 were retrospectively analyzed,including 167 males and 111 females,aged 59(53,66)years.According to the occurrence of DGE,patients were divided into the CR-DGE group(n=94)and the non-CR-DGE group(n=184).Main clinical characteristics were compared between the groups,including pancreatic duct diameter,intraoperative blood loss and operative time.The perioperative indicators were selected using the least absolute shrinkage and selection operator(LASSO)algorithm.Following variable selection,278 patients were allocated into a training set(n=222)and a validation set(n=56)in an 8∶2 ratio.Eight machine learning models were selected to model the training set:random forest,adaptive boosting,light gradient boosting,multilayer perceptron,support vector machine,K-nearest neighbor algorithm,decision tree and complementary set plain bayes.The area under the curve(AUC)of receiver operating characteristic curve of the validation set was utilized to identify the optimal model.The predictive performance of the optimal model was evaluated using calibration plots and decision curve analysis(DCA).The contribution of each feature to the prediction is assessed using Shapley additive explanation(SHAP).Results Univariate analysis showed statistically significant differences between the CR-DGE and non-CR-DGE groups in terms of age[66(62,69)years vs.56(51,60),years],diabetes[42.6%(40/94)vs.11.4%(21/184)],level of fibrinogen[3.43(2.74,4.18)g/L vs.3.84(3.19,4.68)g/L],pancreatic duct diameter[2.00(1.50,2.70)mm vs.3.40(1.60,5.00)mm],intraoperative blood loss[300(200,600)ml vs.200(150,300)ml],operative time[472(430,502)min vs.430(365,475)min],clinically relevant postoperative pancreatic fistula[34.0%(32/94)vs.3.8%(7/184)],abdominal fluid accumulation[46.8%(44/94)vs.12.5%(23/184)],postoperative hemorrhage[20.2%(19/94)vs.3.3%(6/184)],abdominal infection[28.7%(27/94)vs.11.4%(21/184)]and duration of postoperative gastrointestinal decompression[4.00(2.00,6.00)d vs.3.00(2.00,5.00)d](all P<0.05).The eleven variables selected via LASSO were incorporated into each of the eight machine learning models.Results demonstrated that the random forest model achieved the highest performance in the validation set,with an AUC of 0.894(95%CI:0.800-0.985),accuracy of 0.820 and sensitivity of 0.606.Calibration plots and DCA confirmed the robustness of the random forest model.SHAP analysis indicated that age,pancreatic duct diameter and preoperative aspartate aminotransferase were important predictors in the random forest model.Conclusion The random forest model developed in this study demonstrated a good predictive performance for CR-DGE after LPD and may assist in the early identification of high-risk patients in clinical practice.
作者
李济振
朱恒立
付晴安
唐昌乾
魏星博
蔡驰宇
王连才
李冬筱
李德宇
Li Jizhen;Zhu Hengli;Fu Qingan;Tang Changqian;Wei Xingbo;Cai Chiyu;Wang Liancai;Li Dongxiao;Li Deyu(Department of Hepatobiliary and Pancreatic Surgery,People's Hospital of Zhengzhou University,Zhengzhou 450003,China;Department of Cardiology,Second Affiliated Hospital of Nanchang University,Nanchang 330006,China;Department of Hepatobiliary and Pancreatic Surgery,People's Hospital of Henan University,Zhengzhou 450003,China;Department of Gastroenterology,People's Hospital of Zhengzhou University,Zhengzhou 450003,China)
出处
《中华肝胆外科杂志》
北大核心
2025年第2期101-106,共6页
Chinese Journal of Hepatobiliary Surgery
基金
国家自然科学基金(82103617、82103618)
河南省科技研发计划联合基金(232301420056)。
关键词
腹腔镜
胰十二指肠切除术
胃排空延迟
机器学习
Laparoscopes
Pancreaticoduodenectomy
Clinically relevant delayed gastric emptying
Machine learning
