基于XGBoost算法构建肝癌肝切除术后肝衰竭早期识别预测模型

doi:10.3877/cma.j.issn.2095-3232.2025.05.010

目的

基于极端梯度提升（XGBoost）算法构建肝癌肝切除术后肝衰竭（PHLF）早期识别模型，并探讨该模型的预测效能。

方法

回顾性分析2018年11月至2022年1月在南方医院接受肝切除术的583例肝癌患者临床资料。其中男504例，女79例；年龄23~77岁，中位年龄54岁。收集患者术前、术中、术后临床指标，计算相关临床评分。将数据集按8∶2随机分为训练集和验证集，基于XGBoost算法，采用五折交叉验证和损失函数进行超参数调整，构建PHLF预测模型。通过ROC曲线评价XGBoost模型的预测效能，并与传统评分系统进行比较；同时对特征变量进行重要性排序，并采用沙普利加和解释法（SHAP）对模型进行可视化解释。

结果

583例患者中训练集为467例，63例发生PHLF，验证集为116例，15例发生PHLF。训练集单因素分析和Lasso回归分析显示，术前INR、AST、ALB、手术时间、大范围肝切除、术后第1天（D1）INR、AST、TB等8项临床指标与PHLF明显相关。XGBoost模型在训练队列和验证队列中的ROC曲线下面积（AUC）分别为0.973和0.904。使用SHAP值来量化每个特征对模型预测结果的影响，其中D1 INR的权重最大，D1 AST值与PHLF风险呈正相关。基于INR和AST构建PHLF预测评分公式，PHLF预测评分=-13.395+1.2×术前AST(U/L)/100+9.236×D1 INR。该评分模型AUC为0.838，敏感度为0.825，特异度为0.748。

结论

基于XGBoost算法构建的PHLF预测模型在肝癌训练集和验证集中均表现出高准确性和稳健性，有作为临床决策辅助工具的潜力，有助于及早识别PHLF高风险的患者，及时进行干预，从而改善肝癌患者预后。

关键词: 癌，肝细胞, 极端梯度提升算法, 肝切除术后肝衰竭, 机器学习

Objective

To construct a predictive model for early identification of post-hepatectomy liver failure (PHLF) for liver cancer using the extreme gradient boosting (XGBoost), and evaluate its predictive efficiency.

Methods

Clinical data of 583 patients with liver cancer who underwent hepatectomy in Nanfang Hospital from November 2018 to January 2022 were retrospectively analyzed. Among them, 504 patients were male and 79 female, aged from 23 to 77 years, with a median age of 54 years. Clinical indexes of all enrolled patients before, during and after hepatectomy were collected, and relevant clinical scores were calculated. The data set was randomly divided into the training and validation sets according to a ratio of 8∶2. Based on XGBoost, the PHLF prediction model was constructed by using 5-fold cross validation and loss function to adjust the hyperparameters. The prediction efficiency of XGBoost model was evaluated by the ROC curve and compared with traditional scoring system. Meantime, the importance of the feature variables was ranked. Shapley additive explanation (SHAP) was used to visually explain the model.

Results

Among 583 patients, 467 cases were assigned into the training set and 63 cases developed PHLF. 116 cases were allocated in the validation set and 15 developed PHLF. Univariate analysis and Lasso regression analysis showed that 8 clinical indexes including preoperative INR, AST, ALB, operation time, extensive hepatectomy, INR, AST and TB at postoperative 1 d (D1) were significantly associated with PHLF in the training set. The area under the ROC curve (AUC) of XGBoost model in training and validation sets was 0.973 and 0.904, respectively. SHAP value was employed to quantify the impact of each feature on the prediction results of the model, D1 INR had the largest weight, and high D1 AST was positively correlated with the increase of PHLF risk. Based on INR and AST, the PHLF prediction score formula was constructed, and the PHLF prediction score=-13.395+1.2×preoperative AST(U/L)/100+9.236×D1 INR. The AUC of the scoring model was 0.838, the sensitivity was 0.825 and the specificity was 0.748, respectively.

Conclusions

The PHLF prediction model based on XGBoost yields high accuracy and robustness in both the training and validation sets of liver cancer, which has the potential as an auxiliary tool for clinical decision-making, contributes to promptly identifying patients with high-risk PHLF and delivering immediate interventions, thereby improving clinical prognosis of patients with liver cancer.

Key words: Carcinoma, hepatocellular, XGBoost algorithm, Post-hepatectomy liver failure(PHLF), Machine learning

表1 训练集肝癌PHLF发生的单因素分析

指标	非PHLF组	PHLF组	统计值	P值
BMI(kg/m², $x ¯ ± s$ )	23.1±3.1	22.1±2.7	t=2.689	0.016
腹水[例(%)]	10 (2)	5 (8)	χ²=5.229	0.039
肿瘤最大直径[cm, M(Q₁, Q₃)]	4.0 (2.5, 6.0)	6.5 (4.0, 9.0)	Z=-4.649	<0.001
AFP [µg/L, M(Q₁, Q₃)]	14 (3, 260)	69 (9, 960)	Z=-3.281	0.001
术前INR [M(Q₁, Q₃)]	0.99 (0.94, 1.04)	1.06 (1.01, 1.12)	Z=-5.914	<0.001
术前ALT [U/L, M(Q₁, Q₃)]	27 (19, 39)	32 (24, 55)	Z=-2.848	0.004
术前AST [U/L, M(Q₁, Q₃)]	26 (20, 35)	39 (30, 56)	Z=-5.877	<0.001
术前ALB(g/L, $x ¯ ± s$ )	40±4	37±4	t=5.282	<0.001
术前TB [μmol/L, M(Q₁, Q₃)]	12 (9, 16)	15 (10, 18)	Z=-2.532	0.011
术前Na[mmol/L, M(Q₁, Q₃)]	141 (139, 142)	140 (139, 142)	Z=-2.173	0.030
腹腔镜手术[例(%)]	320 (79)	38 (60)	χ²=10.870	0.002
大范围肝切除[例(%)]	39 (10)	32 (51)	χ²=71.551	<0.001
手术时间 (min, $x ¯ ± s$ )	197±92	298±137	t=-5.652	<0.001
术中出血量[ml, M(Q₁, Q₃)]	100 (50, 200)	300 (175, 515)	Z=-6.565	<0.001
术中输血量[ml, M(Q₁, Q₃)]	0 (0, 0)	0 (0, 400)	Z=-5.279	<0.001
D1 INR [M(Q₁, Q₃)]	1.1 (1.0, 1.2)	1.3(1.2, 1.4)	Z=-8.309	<0.001
D1 LY[× 10⁹/L, M(Q₁, Q₃)]	0.8(0.5, 1.0)	0.6 (0.4, 0.9)	Z=-2.131	0.033
D1 RBC[× 10¹²/L, M(Q₁, Q₃)]	4.26 (3.81, 4.73)	3.99 (3.62, 4.32)	Z=-2.974	0.003
D1 Hb(g/L, $x ¯ ± s$ )	129±18	121±20	t=3.247	0.005
D1 ALT[U/L, M(Q₁, Q₃)]	174 (103, 307)	230 (136, 453)	Z=-2.660	0.008
D1 AST [U/L, M(Q₁, Q₃)]	188 (109, 297)	275 (197, 499)	Z=-4.242	<0.001
D1 TP(g/L, $x ¯ ± s$ )	59±6	55±7	t=4.037	<0.001
D1 ALB(g/L, $x ¯ ± s$ )	35±4	32±5	t=5.154	<0.001
D1 TB[μmol/L, M(Q₁, Q₃)]	15 (10, 22)	21(15, 36)	Z=-4.617	<0.001
D1 K[mmol/L, M(Q₁, Q₃)]	4.1(3.9, 4.4)	4.3 (4.0, 4.6)	Z=-3.164	0.002

表1 训练集肝癌PHLF发生的单因素分析

指标	非PHLF组	PHLF组	统计值	P值
BMI(kg/m², $x ¯ ± s$ )	23.1±3.1	22.1±2.7	t=2.689	0.016
腹水[例(%)]	10 (2)	5 (8)	χ²=5.229	0.039
肿瘤最大直径[cm, M(Q₁, Q₃)]	4.0 (2.5, 6.0)	6.5 (4.0, 9.0)	Z=-4.649	<0.001
AFP [µg/L, M(Q₁, Q₃)]	14 (3, 260)	69 (9, 960)	Z=-3.281	0.001
术前INR [M(Q₁, Q₃)]	0.99 (0.94, 1.04)	1.06 (1.01, 1.12)	Z=-5.914	<0.001
术前ALT [U/L, M(Q₁, Q₃)]	27 (19, 39)	32 (24, 55)	Z=-2.848	0.004
术前AST [U/L, M(Q₁, Q₃)]	26 (20, 35)	39 (30, 56)	Z=-5.877	<0.001
术前ALB(g/L, $x ¯ ± s$ )	40±4	37±4	t=5.282	<0.001
术前TB [μmol/L, M(Q₁, Q₃)]	12 (9, 16)	15 (10, 18)	Z=-2.532	0.011
术前Na[mmol/L, M(Q₁, Q₃)]	141 (139, 142)	140 (139, 142)	Z=-2.173	0.030
腹腔镜手术[例(%)]	320 (79)	38 (60)	χ²=10.870	0.002
大范围肝切除[例(%)]	39 (10)	32 (51)	χ²=71.551	<0.001
手术时间 (min, $x ¯ ± s$ )	197±92	298±137	t=-5.652	<0.001
术中出血量[ml, M(Q₁, Q₃)]	100 (50, 200)	300 (175, 515)	Z=-6.565	<0.001
术中输血量[ml, M(Q₁, Q₃)]	0 (0, 0)	0 (0, 400)	Z=-5.279	<0.001
D1 INR [M(Q₁, Q₃)]	1.1 (1.0, 1.2)	1.3(1.2, 1.4)	Z=-8.309	<0.001
D1 LY[× 10⁹/L, M(Q₁, Q₃)]	0.8(0.5, 1.0)	0.6 (0.4, 0.9)	Z=-2.131	0.033
D1 RBC[× 10¹²/L, M(Q₁, Q₃)]	4.26 (3.81, 4.73)	3.99 (3.62, 4.32)	Z=-2.974	0.003
D1 Hb(g/L, $x ¯ ± s$ )	129±18	121±20	t=3.247	0.005
D1 ALT[U/L, M(Q₁, Q₃)]	174 (103, 307)	230 (136, 453)	Z=-2.660	0.008
D1 AST [U/L, M(Q₁, Q₃)]	188 (109, 297)	275 (197, 499)	Z=-4.242	<0.001
D1 TP(g/L, $x ¯ ± s$ )	59±6	55±7	t=4.037	<0.001
D1 ALB(g/L, $x ¯ ± s$ )	35±4	32±5	t=5.154	<0.001
D1 TB[μmol/L, M(Q₁, Q₃)]	15 (10, 22)	21(15, 36)	Z=-4.617	<0.001
D1 K[mmol/L, M(Q₁, Q₃)]	4.1(3.9, 4.4)	4.3 (4.0, 4.6)	Z=-3.164	0.002

图1 训练集肝癌PHLF发生影响因素的Lasso回归分析注：Lasso回归模型中采用20折交叉验证的最佳参数（λ）的选择，绘制二项偏差与log（λ）的关系曲线，在最小标准和最小标准的1标准差最优值处画虚线垂直线；PHLF为肝切除术后肝衰竭

表2 基于XGBoost算法构建的肝癌PHLF预测模型与传统评分系统效能比较

模型	训练集						验证集
模型	AUC	准确度	敏感度	特异度	Z值	P值	AUC	准确度	敏感度	特异度	Z值	P值
XGBoost	0.973	0.911	0.937	0.908			0.904	0.707	0.867	0.683
ALBI	0.712	0.606	0.762	0.582	7.209	<0.001	0.692	0.810	0.533	0.851	2.408	0.016
PALBI	0.673	0.424	0.921	0.347	9.037	<0.001	0.515	0.397	0.400	0.396	4.334	<0.001
Child-Pugh	0.636	0.801	0.397	0.864	10.256	<0.001	0.648	0.828	0.400	0.891	4.275	<0.001

表2 基于XGBoost算法构建的肝癌PHLF预测模型与传统评分系统效能比较

模型	训练集						验证集
模型	AUC	准确度	敏感度	特异度	Z值	P值	AUC	准确度	敏感度	特异度	Z值	P值
XGBoost	0.973	0.911	0.937	0.908			0.904	0.707	0.867	0.683
ALBI	0.712	0.606	0.762	0.582	7.209	<0.001	0.692	0.810	0.533	0.851	2.408	0.016
PALBI	0.673	0.424	0.921	0.347	9.037	<0.001	0.515	0.397	0.400	0.396	4.334	<0.001
Child-Pugh	0.636	0.801	0.397	0.864	10.256	<0.001	0.648	0.828	0.400	0.891	4.275	<0.001

图2 基于XGBoost算法构建的PHLF预测模型中特征重要性排名注：D1为术后第1天，XGBoost为极端梯度提升算法，PHLF为肝切除术后肝衰竭

图3 基于XGBoost 算法构建的PHLF预测模型中变量的SHAP分布图注：图中每个点代表一例患者的一个变量值，不同颜色代表变量值的相对高低；模型中，每例患者的每个预测变量均可转化为对预测结果的贡献，即SHAP值，SHAP值越大，说明患者PHLF的发生风险就越大；D1为术后第1天，XGBoost为极端梯度提升算法，PHLF为肝切除术后肝衰竭，SHAP为沙普利加和解释法

[1]	郑荣寿, 陈茹, 韩冰峰, 等. 2022年中国恶性肿瘤流行情况分析[J]. 中华肿瘤杂志, 2024, 46(3): 221-231. DOI: 10.3760/cma.j.cn112152-20240119-00035.
[2]	Maki H, Hasegawa K. Advances in the surgical treatment of liver cancer[J]. Biosci Trends, 2022, 16(3): 178-188. DOI: 10.5582/bst.2022.01245.
[3]	张东欣, 姜珊, 董家鸿. 大范围肝切除术后肝功能衰竭的研究进展[J]. 中国现代普通外科进展, 2015, 18(4): 295-299. DOI: 10.3969/j.issn.1009-9905.2015.04.010.
[4]	Søreide JA, Deshpande R. Post hepatectomy liver failure (PHLF): recent advances in prevention and clinical management[J]. Eur J Surg Oncol, 2021, 47(2): 216-224. DOI: 10.1016/j.ejso.2020.09.001.
[5]	Shan J, Quan F, Wuyun G, et al. Management of post-hepatectomy complications[J]. World J Gastroenterol, 2013, 19(44): 7983-7991. DOI: 10.3748/wjg.v19.i44.7983.
[6]	Wang JJ, Feng J, Gomes C, et al. Development and validation of prediction models and risk calculators for posthepatectomy liver failure and postoperative complications using a diverse international cohort of major hepatectomies[J]. Ann Surg, 2023, 278(6): 976-984. DOI: 10.1097/SLA.0000000000005916.
[7]	蔡启晨, 张俊勇, 龚建平. 肝切除术后肝功能衰竭的预防和治疗进展[J]. 医学理论与实践, 2021, 34(10): 1648-1650, 1653. DOI: 10.19381/j.issn.1001-7585.2021.10.009.
[8]	Zhang Z, Ho KM, Hong Y. Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care[J]. Crit Care, 2019, 23(1): 112. DOI: 10.1186/s13054-019-2411-z.
[9]	Li Y, Duan H, Wang S. An XGBoost predictive model of ongoing pregnancy in patients following hysteroscopic adhesiolysis[J]. Reprod Biomed Online, 2023, 46(6): 965-972. DOI: 10.1016/j.rbmo.2023.01.019.
[10]	Xu J, Chen T, Fang X, et al. Prediction model of pressure injury occurrence in diabetic patients during ICU hospitalization: XGBoost machine learning model can be interpreted based on SHAP[J]. Intensive Crit Care Nurs, 2024, 83: 103715. DOI: 10.1016/j.iccn.2024.103715.
[11]	Xu X, Xing Z, Xu Z, et al. A deep learning model for prediction of post hepatectomy liver failure after hemihepatectomy using preoperative contrast-enhanced computed tomography: a retrospective study[J]. Front Med, 2023, 10: 1154314. DOI: 10.3389/fmed.2023.1154314.
[12]	Rahbari NN, James Garden O, Padbury R, et al. Posthepatectomy liver failure: a definition and grading by the International Study Group of Liver Surgery (ISGLS)[J]. Surgery, 2011, 149(5): 713-724. DOI: 10.1016/j.surg.2010.10.001.
[13]	Johnson PJ, Berhane S, Kagebayashi C, et al. Assessment of liver function in patients with hepatocellular carcinoma: a new evidence-based approach-the ALBI grade[J]. J Clin Oncol, 2015, 33(6): 550-558. DOI: 10.1200/JCO.2014.57.9151.
[14]	Liu PH, Hsu CY, Hsia CY, et al. ALBI and PALBI grade predict survival for HCC across treatment modalities and BCLC stages in the MELD Era[J]. J Gastroenterol Hepatol, 2017, 32(4): 879-886. DOI: 10.1111/jgh.13608.
[15]	Arisaka S, Matsuyama R, Goto K, et al. Predictive ability of preoperative PT-INR and postoperative MCP1 for post-hepatectomy liver failure[J]. In Vivo, 2020, 34(3): 1255-1263. DOI: 10.21873/invivo.11899.
[16]	Silva AS, Greensmith M, Praseedom RK, et al. Early derangement of INR predicts liver failure after liver resection for hepatocellular carcinoma[J]. Surgeon, 2022, 20(5): e288-e295. DOI: 10.1016/j.surge.2022.01.002.
[17]	Lin S, Song Z, Peng H, et al. A novel nomogram based on preoperative parameters to predict posthepatectomy liver failure in patients with hepatocellular carcinoma[J]. Surgery, 2023, 174(4): 865-873. DOI: 10.1016/j.surg.2023.06.025.
[18]	Ye JZ, Mai RY, Guo WX, et al. Nomogram for prediction of the international study Group of Liver Surgery (ISGLS) grade B/C Posthepatectomy liver failure in HBV-related hepatocellular carcinoma patients: an external validation and prospective application study[J]. BMC Cancer, 2020, 20(1): 1036. DOI: 10.1186/s12885-020-07480-2.
[19]	Shi JY, Sun LY, Quan B, et al. A novel online calculator based on noninvasive markers (ALBI and APRI) for predicting post-hepatectomy liver failure in patients with hepatocellular carcinoma[J]. Clin Res Hepatol Gastroenterol, 2021, 45(4): 101534. DOI: 10.1016/j.clinre.2020.09.001.
[20]	Santol J, Kim S, Gregory LA, et al. An APRI+ALBI-based multivariable model as a preoperative predictor for posthepatectomy liver failure[J]. Ann Surg, 2025, 281(5): 861-871. DOI: 10.1097/SLA.0000000000006127.
[21]	麦荣云, 曾洁, 叶甲舟, 等. 术前天冬氨酸转氨酶与血小板比值指数预测原发性肝癌肝切除术后肝衰竭的价值[J]. 第二军医大学学报, 2019, 40(1): 61-67. DOI: 10.16781/j.0258-879x.2019.01.0061.
[22]	Vassanasiri W, Rungsakulkij N, Suragul W, et al. Early postoperative serum aspartate aminotransferase for prediction of post-hepatectomy liver failure[J]. Perioper Med, 2022, 11(1): 51. DOI: 10.1186/s13741-022-00283-y.
[23]	Grąt M, Hołówko W, Lewandowski Z, et al. Early post-operative prediction of morbidity and mortality after a major liver resection for colorectal metastases[J]. HPB, 2013, 15(5): 352-358. DOI: 10.1111/j.1477-2574.2012.00596.x.
[24]	Takahashi K, Gosho M, Miyazaki Y, et al. Preoperative albumin-bilirubin score and liver resection percentage determine postoperative liver regeneration after partial hepatectomy[J]. World J Gastroenterol, 2024, 30(14): 2006-2017. DOI: 10.3748/wjg.v30.i14.2006.
[25]	Baumgartner R, Engstrand J, Rajala P, et al. Comparing the accuracy of prediction models to detect clinically relevant post-hepatectomy liver failure early after major hepatectomy[J]. Br J Surg, 2024, 111(1): znad433. DOI: 10.1093/bjs/znad433.
[26]	Liu JY, Ellis RJ, Lina Hu Q, et al. Post hepatectomy liver failure risk calculator for preoperative and early postoperative period following major hepatectomy[J]. Ann Surg Oncol, 2020, 27(8): 2868-2876. DOI: 10.1245/s10434-020-08239-6.
[27]	Rahnemai-Azar AA, Cloyd JM, Weber SM, et al. Update on liver failure following hepatic resection: strategies for prediction and avoidance of post-operative liver insufficiency[J]. J Clin Transl Hepatol, 2018, 6(1): 97-104. DOI: 10.14218/JCTH.2017.00060.
[28]	Kriengkrai W, Somjaivong B, Titapun A, et al. Predictive factors for post-hepatectomy liver failure in patients with cholangiocarcinoma[J]. Asian Pac J Cancer Prev, 2023, 24(2): 575-580. DOI: 10.31557/APJCP.2023.24.2.575.
[29]	Truant S, El Amrani M, Skrzypczyk C, et al. Factors associated with fatal liver failure after extended hepatectomy[J]. HPB, 2017, 19(8): 682-687. DOI: 10.1016/j.hpb.2017.04.006.
[30]	Baumgartner R, Gilg S, Björnsson B, et al. Impact of post-hepatectomy liver failure on morbidity and short-and long-term survival after major hepatectomy[J]. BJS Open, 2022, 6(4): zrac097. DOI: 10.1093/bjsopen/zrac097.
[31]	Sparrelid E, Olthof PB, Dasari BVM, et al. Current evidence on posthepatectomy liver failure: comprehensive review[J]. BJS Open, 2022, 6(6): zrac142. DOI: 10.1093/bjsopen/zrac142.

[1]	汪锐, 陈自武, 杨朴强, 田静, 陈莹, 林成, 汪伟. 基于血清标志物机器学习模型对慢性阻塞性肺疾病急性加重期机械通气风险的预测分析[J/OL]. 中华肺部疾病杂志(电子版), 2025, 18(04): 615-619.
[2]	袁洳靖, 孙居仙, 程树群. 肝癌合并门静脉癌栓放射治疗[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(05): 659-666.
[3]	林水荣, 宋子敏, 于玺, 李绍强, 华赟鹏, 沈顺利. 术前抗病毒治疗对HBV相关肝癌肝切除术后肝衰竭影响[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(05): 700-706.
[4]	张燕, 许丁伟, 胡满琴, 黄昊扬, 宋光娜, 黄洁. 术前免疫炎症指标对肝癌肝切除术患者生存预后的预测价值[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(05): 707-715.
[5]	方兴保, 庞国莲, 李月宏, 蔡艳. 基于多组学分析MCAM在肝癌中表达及其与生存预后和免疫细胞浸润的关系[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(05): 716-724.
[6]	龚财芳, 姚娟, 李欢, 熊永福, 赵俊宇, 游川. 肝癌肝切除术后胃肠功能障碍的诊治和防治进展[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 640-645.
[7]	王楚斯, 刘家伟, 卢逸, 汤照峰. ICG荧光显影在腹腔镜肝癌切除术中临床应用[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 549-553.
[8]	匡嘉文, 陈铁军, 龚远锋, 唐辉, 唐云强. TACE-HAIC联合仑伐替尼和PD-1抑制剂四联治疗Ⅲa期肝癌的疗效[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 554-560.
[9]	吴添庆, 郑梽楷, 贺珉睿, 潘扬勋, 王骏成, 陈锦滨, 周仲国. 华蟾素治疗肝癌肝动脉灌注化疗术后疼痛的疗效和安全性[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 569-575.
[10]	张宏伟, 邢玉雪, 贾哲, 赫嵘, 张珂, 蒋力. 术前输注血小板在肝癌合并肝硬化门静脉高压症肝脾联合切除患者中的疗效[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 576-581.
[11]	刘晓萍, 汪嵘嵘, 吴佳慧, 吴紫云, 周伯宣. 多组学分析HAPLN1与肝癌预后及免疫细胞浸润关系[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 609-618.
[12]	郭勇, 贾思颖, 高士杰, 涂康生. RNFT2在肝细胞癌中表达及其对细胞增殖、侵袭和患者预后影响[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 619-627.
[13]	陈佩玥, 董芸, 邓大炜, 龚财芳, 赵俊宇, 游川. 肝癌围手术期营养风险筛查和肠内营养支持研究进展[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 631-635.
[14]	杨钰泽, 徐家豪, 杨一石, 王明达, 杨田. 肝细胞癌新辅助治疗进展[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 515-521.
[15]	罗臻, 韦鹏程, 孙馨, 李照. 肝细胞癌骨转移研究进展[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(04): 522-527.

阅读次数

全文

摘要

选择文件类型/文献管理软件名称

选择包含的内容

Construction of prediction model for early identification of post-hepatectomy liver failure for liver cancer based on XGBoost

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

Construction of prediction model for early identification of post-hepatectomy liver failure for liver cancer based on XGBoost