基于CT影像组学与中医舌象特征构建肝细胞癌根治术后早期复发的Nomogram预测模型

doi:10.3969/j.issn.1006-5725.2025.16.022

Abstract

Abstract:

Objective To construct a Nomogram risk prediction model for early recurrence of hepatocellular carcinoma （HCC） radical hepatectomy based on CT imaging omics and traditional Chinese medicine tongue imaging features. Methods 216 patients who underwent HCC radical hepatectomy in the First Affiliated Hospital of Henan University of Traditional Chinese Medicine from September 2018 to September 2022 were selected，the clinical dataes were retrospective analyzed.The patients were randomly divided into modeling set （n = 152） and validation set （n = 64） by 7：3 ratio，the recurrence situation one year after surgery of the two groups were recorded.A recurrence prediction model was constructed by the modeling set of patient dataes， all patients underwent postoperative plain scan combined with enhanced CT examination， and the Imaging omics feature indicators was extracted， the tongue imaging characteristics was recorded，the Cox multivariate model was used to analyze the factors related to postoperative recurrence in the modeling set of patients， and a risk prediction model was constructed，the model was validated by validation set dataes. Results There were 52 patients in the modeling set experienced recurrence within 1 year， the recurrence rate was 34.21%；there were 23 cases of recurrence in the validation set patients within 1 year， the recurrence rate was 35.94%.The Cox multivariate model analysis showed that the Rad-score， Tongue texture and tongue shape were independent influence factors for postoperative recurrence of HCC （P < 0.05）. Based on this， the Nomogram column chart was established.The ROC analysis showed that the AUC of the column chart model for predicting postoperative recurrence in the modeling set and validation set patients were 0.811 and 0.824， the sensitivities were 0.875 and 0.833 respectively， the specificities were 0.617 and 0.750 respectively. Conclusions The early postoperative recurrence of HCC is related to Rad score， tongue texture， and tongue shape. Based on this， the Nomogram prediction model constructed has high accuracy in predicting early postoperative recurrence.

Key words: hepatocellular carcinoma radical hepatectomy, early recurrence, CT radiomics, tongue picture, prediction model

CLC Number:

R735.7

Zhaoyang WANG,Nan. ZHANG. Constructing a Nomogram prediction model for early recurrence of hepatocellular carcinoma radical hepatectomy based on CT imaging omics and traditional Chinese medicine tongue image features[J]. The Journal of Practical Medicine, 2025, 41(16): 2590-2596.

Figures/Tables 10

Tab.1

Fig.1

Tab.2

Tab.3

Tab.4

Tab.5

Tab.6

Fig.2

Fig.3

Fig.4

References 32

[1]	杨帆，曹毛毛，李贺，等. 1990—2019年中国人群肝癌流行病学趋势分析及预测［J］. 中华消化外科杂志，2022，21（1）：106-113. doi:10.3760/cma.j.cn115610-20211203-00616 doi: 10.3760/cma.j.cn115610-20211203-00616
[2]	HUO T I， HO S Y， LIAO J I.Predicting post‐resection early recurrence of hepatocellular carcinoma： Defining the role of microvascular invasion［J］.Liver Int， 2023， 43（12）：2826-2827. doi:10.1111/liv.15743 doi: 10.1111/liv.15743
[3]	朱荣火，黄晶晶，黄鸿娜，等. 肝细胞癌切除术后早期复发的危险因素［J］. 实用肿瘤杂志，2023，38（4）：377-381. doi:10.13267/j.cnki.syzlzz.2023.060 doi: 10.13267/j.cnki.syzlzz.2023.060
[4]	戴聪，刘文源，刘宣彤，等. 肝细胞癌影像特征结合实验室指标在微血管侵犯中的预测价值［J］. 中国医科大学学报，2024，53（1）：75-79.
[5]	冯宇，周曼丽，王健章，等. 中医舌诊方法现代研究进展［J］. 陕西中医，2020，41（6）：838-840.
[6]	王宇立，方媛，徐静，等. 原发性肝癌患者高强度聚焦超声治疗前后舌象、脉象参数及中医体质变化［J］. 中华中医药杂志，2020，35（12）：6313-6317.
[7]	杨晓蕾，杨超，张钦婷，等. 恶性肿瘤患者中医体质类型相关研究［J］. 辽宁中医药大学学报，2015，17（8）：164-166.
[8]	周铖，赵文霞，贾冉，等. 原发性肝癌肝胆湿热证与肝郁脾虚证患者舌苔菌群特征及功能差异［J］. 中华中医药杂志，2023，38（6）：2861-2867.
[9]	ZHAO C， NGUYEN M H.Hepatocellular carcinoma screening and surveillance： Practice guidelines and real-life practice［J］.J Clin Gastroenterol， 2016， 50（2）：120-133. doi:10.1097/mcg.0000000000000446 doi: 10.1097/mcg.0000000000000446
[10]	WEN J， WANG X， XIA M，et al.Radiomics features based on dual-area CT predict the expression levels of fatty acid binding protein 4 and outcome in hepatocellular carcinoma［J］.Abdom Radiol， 2024， 49（6）：1905-1917. doi:10.1007/s00261-023-04177-5 doi: 10.1007/s00261-023-04177-5
[11]	王晓东，周翼，靳涛，等. 肝癌腹腔镜根治术后PCIA并胸椎旁神经阻滞的效果［J］. 青岛大学学报（医学版），2024，60（4）：565-569.
[12]	张振奇，贺莉. 弥散加权成像联合动态对比增强磁共振成像在肝细胞肝癌患者肝动脉化疗栓塞术后肿瘤活性检测中的应用价值［J］. 陕西医学杂志，2024，53（6）：773-776，781.
[13]	王秀香，李海霞，郭琳，等. 微球TACE对小肝癌治疗的影响及相关因素分析［J］. 药物生物技术，2024，31（1）：45-52.
[14]	NICOLAS M， CZERWONKO M， ARDILES V，et al.Laparoscopic vs open liver resection for metastatic colorectal cancer： Analysis of surgical margin status and survival［J］.Langenbecks Arch Surg， 2022， 407（3）：1113-1119. doi:10.1007/s00423-021-02396-2 doi: 10.1007/s00423-021-02396-2
[15]	周晨阳，周江敏，胡新昇，等.肝细胞癌患者术后早期复发的危险因素分析及风险评估模型构建［J］.中国普通外科杂志， 2020， 29（8）：973-978.
[16]	史瑞籽，杨培，曾新桃，等. 腹腔镜肝细胞癌根治风险预测模型的建立与验证［J］. 腹腔镜外科杂志，2023，28（6）：433-438，443.
[17]	LEE H， CHANG W， KIM H Y，et al.Improving radiomics reproducibility using deep learning-based image conversion of CT reconstruction algorithms in hepatocellular carcinoma patients［J］.Eur Radiol，2024， 34（3）：2036-2047. doi:10.1007/s00330-023-10135-y doi: 10.1007/s00330-023-10135-y
[18]	MAO B， MA J， DUAN S，et al.Preoperative classification of primary and metastatic liver cancer via machine learning-based ultrasound radiomics［J］.Eur Radiol， 2021，31（7）：4576-4586. doi:10.1007/s00330-020-07562-6 doi: 10.1007/s00330-020-07562-6
[19]	ZHANG T， DONG X， ZHOU Y，et al.Development and validation of a radiomics nomogram to discriminate advanced pancreatic cancer with liver metastases or other metastatic patterns.［J］.Cancer Biomark， 2021，32（4）：541-550. doi:10.3233/CBM-210190 doi: 10.3233/CBM-210190
[20]	LIGERO M， JORDI-OLLERO O， BERNATOWICZ K， et al.Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis［J］.Eur Radiol，2021， 31（3）：1460-1470. doi:10.1007/s00330-020-07174-0 doi: 10.1007/s00330-020-07174-0
[21]	LI W， ZHANG L， TIAN C，et al.Prognostic value of computed tomography radiomics features in patients with gastric cancer following curative resection［J］.Eur Radiol， 2019， 29（6）：3079-3089. doi:10.1007/s00330-018-5861-9 doi: 10.1007/s00330-018-5861-9
[22]	ZHUANG Y Y， FENG Y， KONG D，et al.Discrimination between benign and malignant gallbladder lesions on enhanced CT imaging using radiomics［J］.Acta Radiol， 2024，65（5）：422-431. doi:10.1177/02841851241242042 doi: 10.1177/02841851241242042
[23]	HECTORS S J， CHERNY M， YADAV K K，et al.Radiomics features measured with multiparametric MRI predict prostate cancer aggressiveness［J］.J Urol， 2019， 202（3）：498-505. doi:10.1097/ju.0000000000000272 doi: 10.1097/ju.0000000000000272
[24]	胡泽玉，周铖，杨清瑞，等. 原发性肝癌患者经肝动脉化疗栓塞术后舌苔菌群变化特征研究［J］. 中国微生态学杂志，2023，35（3）：263-268.
[25]	邵峰，曾普华，曾光，等. 基于临床数据分析原发性肝癌的证治规律［J］. 湖南中医药大学学报，2019，39（1）：40-44. doi:10.3969/j.issn.1674-070X.2019.01.010 doi: 10.3969/j.issn.1674-070X.2019.01.010
[26]	陈建杰. 肝癌中医药辨治思路［J］. 中西医结合肝病杂志，2019，29（2）：109-111.
[27]	徐巧笑，胡振斌，莫莎莎，等. 从"虚、毒、瘀"浅谈原发性肝癌病机和治疗［J］. 陕西中医，2023，44（10）：1431-1434.
[28]	邢金山，王立森，孙逊，等. 原发性肝癌中医四诊辨证诊疗临床观察［J］. 社区医学杂志，2019，17（18）：1130-1134.
[29]	杨晗，陈淑琪，陈继欣，等. 原发性肝癌肝动脉化疗栓塞术前后中医证素的变化特点研究［J］. 中医药导报，2020，26（10）：105-108.
[30]	谢武，何云，易敏铭. 刘辉华教授辨证论治肝病经验总结［J］. 贵州医药，2024，48（12）：1943-1945.
[31]	彭进，贾燕华，李宏. 原发性肝癌CT影像学特征与中医辨证分型的关系研究［J］. 四川中医，2021，39（10）：57-60.
[32]	高逸云，詹欣雨，周浩明.内质网应激调控巨噬细胞免疫应答在肝脏疾病中的作用［J］.器官移植，2024，15（6）：889-894.

组别	例数	性别/例		年龄/岁	肿瘤分期/例			肝硬化/例		肿瘤最大直径/cm
组别	例数	男	女	年龄/岁	Ⅰ期	Ⅱ期	Ⅲ期	是	否	肿瘤最大直径/cm
建模集	152	80	72	50.21 ± 13.84	61	54	37	100	52	5.36 ± 1.82
验证集	64	36	28	52.09 ± 12.67	28	20	16	38	26	5.09 ± 2.03
t/Z/χ² 值		0.237		0.934	-0.291			0.803		0.962
P值		0.626		0.351	0.771			0.370		0.337

CT影像组学特征	系数
wavelet-HLL-firstorder-Maximum	0.459
wavelet-LHL-firstorder-Skewness	0.421
wavelet-HLLfirstorder Median	-0.285
wavelet-LHL-glszm-SmallAreaEmphasis	0.315
logarithm-glcm-Idmn	0.348
gradient-firstorder-Minimum	0.372

组别	例数	Rad-score（x ± s）	舌质			舌苔			舌形
组别	例数	Rad-score（x ± s）	红	绛红	淡红	厚腻	薄白	淡红	裂纹	胖大	偏平状
复发组	52	1.87 ± 0.65	16（30.77）	28（53.85）	8（15.38）	26(50.00）	17（32.69）	9（17.31）	27(51.92）	16（30.77）	9(17.31）
未复发组	100	1.20 ± 0.43	46（46.00）	18（18.00）	36（36.00）	20(20.00）	42（42.00）	38（38.00）	18（18.00）	54（54.00）	28(28.00）
t/χ² 值		7.603	21.494			15.675			18.914
P值		< 0.001	< 0.001			< 0.001			< 0.001

指标	复发组（n = 52）	未复发组（n = 100）	t/χ² 值	P值
性别/[例（%）]			0.047	0.829
男	28（53.85）	52（52.00）
女	24（46.15）	48（48.00）
年龄/岁	51.47 ± 12.08	50.06 ± 14.41	0.604	0.547
肿瘤分期/[例（%）]			19.444	< 0.001
Ⅰ期	9（17.31）	50（50.00）
Ⅱ期	19（36.54）	32（32.00）
Ⅲ期	24（46.15）	18（18.00）
肝硬化/[例（%）]			0.635	0.426
是	32（61.54）	68（68.00）
否	20（38.46）	32（32.00）
手术方式/[例（%）]			0.240	0.624
射频消融术	24（46.15）	42（42.00）
腹腔镜肝癌切除术	28（53.85）	58（58.00）
肿瘤最大直径/cm	5.42 ± 1.96	4.98 ± 1.60	1.487	0.139
AST/（U/L）	86.47 ± 18.50	81.23 ± 22.17	1.460	0.146
ALT/（U/L）	92.39 ± 23.42	87.61 ± 25.51	1.126	0.262
AFP/（ng/mL）	153.41 ± 37.58	140.05 ± 30.73	2.352	0.020

指标	赋值情况
Rad-score、血清AFP以原值带入
舌质	淡红= 1，红= 2，绛红= 3
舌苔	淡红= 1，薄白= 2，厚腻= 3
舌形	偏平= 1，胖大= 2，裂纹= 3
肿瘤分期	Ⅰ期= 1，Ⅱ期= 2，Ⅲ期= 3

Constructing a Nomogram prediction model for early recurrence of hepatocellular carcinoma radical hepatectomy based on CT imaging omics and traditional Chinese medicine tongue image features

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 32

Related Articles 15

Recommended Articles

Metrics

Comments

指标	β	SE	Wald χ²	P值	HR	95%CI
Rad-score	1.347	0.563	5.727	0.017	3.845	1.276~11.586
舌质	0.715	0.259	7.656	0.006	2.045	1.232~3.395
舌苔	1.508	0.825	3.342	0.068	4.518	0.897~22.756
舌形	0.640	0.276	5.376	0.020	1.896	1.104~3.256
肿瘤分期	1.480	0.935	2.506	0.113	4.392	0.703~27.439
血清AFP	1.160	0.689	2.831	0.092	3.189	0.826~12.312

[1]	Kui DONG,jie WU,Jing YAN,Haitao LIU,Jun WANG,Guan′en. QIAO. Study on risk factors of colorectal adenomatous polyps and construction and validation of prediction model [J]. The Journal of Practical Medicine, 2025, 41(6): 838-845.
[2]	Hong ZHANG,Rong ZHANG,Pengcheng YANG,Liyan LUO,Wenlong ZHANG,Yurong CHENG,Wenlin LIU,Wenbin. DONG. Construction of risk prediction model for preterm infant respiratory distress syndrome in Dali Prefecture [J]. The Journal of Practical Medicine, 2025, 41(15): 2342-2348.
[3]	Yuhai QIAO,Chunhua DU,Xinhong ZHAO,Xiaodong MENG,Jianfei. ZHANG. Construction and validation of a risk prediction model for clinical characteristics of patients with chronic non⁃bacterial prostatitis [J]. The Journal of Practical Medicine, 2025, 41(14): 2224-2230.
[4]	Xianqun TAN,Fenglin ZHANG,Guangyan ZOU,Xidong CHEN. Establishment of a risk prediction model for neurogenic bladder dysfunction after spinal cord injury [J]. The Journal of Practical Medicine, 2025, 41(13): 2058-2064.
[5]	Zhen ZHANG,Donghao WANG,Yang LYU. A prognostic model for patients was established based on negative fluid balance during septic shock treatment [J]. The Journal of Practical Medicine, 2025, 41(11): 1687-1693.
[6]	Peng YANG,Yimeng XU,Wei HAN. Risk factors for postoperative pulmonary infection after pancreaticoduodenectomy and establishment of predictive model [J]. The Journal of Practical Medicine, 2025, 41(11): 1705-1710.
[7]	Liangjiang HUANG,Dewen MAO,Jinghui ZHENG,Minggang WANG,Chun YAO. Application of artificial intelligence in HE risk prediction modelling and research advances [J]. The Journal of Practical Medicine, 2024, 40(3): 289-294.
[8]	Ming HOU,Youqiang LI,Xuemei LI,Junfeng JIA,Junying CHANG. Construction of a risk prediction model of lung involvement based on chest CT and clinical features in patients with primary Sjogren's syndrome [J]. The Journal of Practical Medicine, 2024, 40(3): 400-405.
[9]	Haojie TANG,Zilong YANG,Zhaoxian YU,Zhiyu FENG,Haiping DONG,Xiang LI,Wei ZHAO,Haobin. KUANG. Construction and evaluation of a risk prediction model for linezolid-related neurological adverse reactions in patients with multidrug-resistant tuberculosis [J]. The Journal of Practical Medicine, 2024, 40(19): 2690-2695.
[10]	Xin HUANG,Pu ZHANG,Yu GAO,Kai CHEN,Xiaofeng LI,Huiyang GU,Xue. LIANG. Multivariate analysis and prediction model of mild cognitive impairment in patients with atrial fibrillation and diabetes mellitus [J]. The Journal of Practical Medicine, 2024, 40(16): 2236-2243.
[11]	ZHOU Yong, CHEN Hao, DOU Qian, LI Yue, LIU Wofeng.. An applied study on assessing the risk of nasopharyngeal carcinoma in Guangzhou population based on 5 kinds of EBV antibodies [J]. The Journal of Practical Medicine, 2023, 39(5): 602-612.
[12]	Hui HAN,Ping XU,Weidong. SONG. Construction of risk prediction model for acute exacerbation in near future of elderly COPD patients in stable stage [J]. The Journal of Practical Medicine, 2023, 39(22): 2984-2988.
[13]	Xiaoling FU,Xingdan ZHAO,Yazhou WANG,Xiang CAO,Linjing ZHANG,Fen. CHEN. Construction and verification of a risk predictive model for hyperbilirubinemia in ABO neonatal hemolysis disease by the level of umbilical blood bilirubin combined with high risk factors [J]. The Journal of Practical Medicine, 2023, 39(20): 2658-2663.
[14]	Xiuquan QI,Wei WANG,Xiaokang QIU,Ye. XU. Establishment of Nomogram prediction model for latent blood loss in patients with lumbar disc herniation after operation [J]. The Journal of Practical Medicine, 2023, 39(18): 2300-2305.
[15]	Mengxin XU,Wei WANG,Rongxiong. DAI. Construction of a column chart model for predicting postoperative delirium in patients with lumbar vertebral fractures based on novel inflammatory composite scoring [J]. The Journal of Practical Medicine, 2023, 39(18): 2306-2311.