• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于机器学习的列线图构建与验证:预测初治时高乙型肝炎表面抗原水平的乙型肝炎病毒相关肝细胞癌患者的预后:一项多中心研究。

Construction and validation of a machine learning-based nomogram to predict the prognosis of HBV associated hepatocellular carcinoma patients with high levels of hepatitis B surface antigen in primary local treatment: a multicenter study.

机构信息

Interventional Therapy Center for Oncology, Beijing You'an Hospital, Capital Medical University, Beijing, China.

Research Center for Biomedical Resources, Beijing You'an Hospital Capital Medical University, Beijing, China.

出版信息

Front Immunol. 2024 Mar 27;15:1357496. doi: 10.3389/fimmu.2024.1357496. eCollection 2024.

DOI:10.3389/fimmu.2024.1357496
PMID:38601167
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11004323/
Abstract

BACKGROUND

Hepatitis B surface antigen (HBsAg) clearance is associated with improved long-term outcomes and reduced risk of complications. The aim of our study was to identify the effects of levels of HBsAg in HCC patients undergoing TACE and sequential ablation. In addition, we created a nomogram to predict the prognosis of HCC patients with high levels of HBsAg (≥1000U/L) after local treatment.

METHOD

This study retrospectively evaluated 1008 HBV-HCC patients who underwent TACE combined with ablation at Beijing Youan Hospital and Beijing Ditan Hospital from January 2014 to December 2021, including 334 patients with low HBsAg levels and 674 patients with high HBsAg levels. The high HBsAg group was divided into the training cohort (N=385), internal validation cohort (N=168), and external validation cohort (N=121). The clinical and pathological features of patients were collected, and independent risk factors were identified using Lasso-Cox regression analysis for developing a nomogram. The performance of the nomogram was evaluated by C-index, receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves in the training and validation cohorts. Patients were classified into high-risk and low-risk groups based on the risk scores of the nomogram.

RESULT

After PSM, mRFS was 28.4 months (22.1-34.7 months) and 21.9 months (18.5-25.4 months) in the low HBsAg level and high HBsAg level groups (P<0.001). The content of the nomogram includes age, BCLC stage, tumor size, globulin, GGT, and bile acids. The C-index (0.682, 0.666, and 0.740) and 1-, 3-, and 5-year AUCs of the training, internal validation, and external validation cohorts proved good discrimination of the nomogram. Calibration curves and DCA curves suggested accuracy and net clinical benefit rates. The nomogram enabled to classification of patients with high HBsAg levels into low-risk and high-risk groups according to the risk of recurrence. There was a statistically significant difference in RFS between the two groups in the training, internal validation, and external validation cohorts (P<0.001).

CONCLUSION

High levels of HBsAg were associated with tumor progression. The nomogram developed and validated in the study had good predictive ability for patients with high HBsAg levels.

摘要

背景

乙肝表面抗原(HBsAg)清除与长期预后改善和并发症风险降低相关。本研究的目的是确定 HBsAg 水平对接受 TACE 序贯消融治疗的 HCC 患者的影响。此外,我们创建了一个列线图来预测局部治疗后 HBsAg 水平较高(≥1000U/L)的 HCC 患者的预后。

方法

本研究回顾性分析了 2014 年 1 月至 2021 年 12 月在北京佑安医院和北京地坛医院接受 TACE 联合消融治疗的 1008 例 HBV-HCC 患者,包括低 HBsAg 水平组 334 例和高 HBsAg 水平组 674 例。高 HBsAg 组分为训练队列(N=385)、内部验证队列(N=168)和外部验证队列(N=121)。收集患者的临床和病理特征,采用 Lasso-Cox 回归分析确定独立危险因素,建立列线图。在训练和验证队列中,通过 C 指数、受试者工作特征(ROC)曲线、校准曲线和决策曲线分析(DCA)曲线评估列线图的性能。根据列线图的风险评分将患者分为高危和低危组。

结果

PSM 后,低 HBsAg 水平组和高 HBsAg 水平组的 mRFS 分别为 28.4 个月(22.1-34.7 个月)和 21.9 个月(18.5-25.4 个月)(P<0.001)。列线图的内容包括年龄、BCLC 分期、肿瘤大小、球蛋白、GGT 和胆汁酸。训练、内部验证和外部验证队列的 C 指数(0.682、0.666 和 0.740)以及 1、3 和 5 年 AUC 证明了列线图的良好区分能力。校准曲线和 DCA 曲线表明了准确性和净临床获益率。该列线图能够根据复发风险将高 HBsAg 水平的患者分为低危和高危组。在训练、内部验证和外部验证队列中,两组间的 RFS 存在统计学差异(P<0.001)。

结论

高 HBsAg 水平与肿瘤进展相关。本研究中开发和验证的列线图对 HBsAg 水平较高的患者具有良好的预测能力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/480cb7cc6283/fimmu-15-1357496-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/138d23a1b665/fimmu-15-1357496-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/62aebca67c02/fimmu-15-1357496-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/60c908aa2176/fimmu-15-1357496-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/62d4983902e4/fimmu-15-1357496-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/9da4046acae5/fimmu-15-1357496-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/e7863871ae1b/fimmu-15-1357496-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/480cb7cc6283/fimmu-15-1357496-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/138d23a1b665/fimmu-15-1357496-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/62aebca67c02/fimmu-15-1357496-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/60c908aa2176/fimmu-15-1357496-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/62d4983902e4/fimmu-15-1357496-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/9da4046acae5/fimmu-15-1357496-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/e7863871ae1b/fimmu-15-1357496-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cc81/11004323/480cb7cc6283/fimmu-15-1357496-g007.jpg

相似文献

1
Construction and validation of a machine learning-based nomogram to predict the prognosis of HBV associated hepatocellular carcinoma patients with high levels of hepatitis B surface antigen in primary local treatment: a multicenter study.基于机器学习的列线图构建与验证:预测初治时高乙型肝炎表面抗原水平的乙型肝炎病毒相关肝细胞癌患者的预后:一项多中心研究。
Front Immunol. 2024 Mar 27;15:1357496. doi: 10.3389/fimmu.2024.1357496. eCollection 2024.
2
Prognostic model for predicting recurrence in hepatocellular carcinoma patients with high systemic immune-inflammation index based on machine learning in a multicenter study.基于多中心研究的机器学习构建高全身免疫炎症指数肝癌患者复发预测的预后模型。
Front Immunol. 2024 Sep 9;15:1459740. doi: 10.3389/fimmu.2024.1459740. eCollection 2024.
3
Incorporating Inflammatory Markers and Clinical Indicators into a Predictive Model of Single Small Hepatocellular Carcinoma Recurrence After Primary Locoregional Treatments.将炎症标志物和临床指标纳入原发性局部区域治疗后单发性小肝细胞癌复发的预测模型
J Hepatocell Carcinoma. 2024 Jun 13;11:1113-1125. doi: 10.2147/JHC.S465069. eCollection 2024.
4
Recurrence of Hepatocellular Carcinoma in Patients with Low Albumin-Bilirubin Grade in TACE Combined with Ablation: A Random Forest Cox Predictive Model.TACE联合消融治疗的低白蛋白-胆红素分级患者肝细胞癌的复发:随机森林Cox预测模型
J Hepatocell Carcinoma. 2024 Jul 8;11:1375-1388. doi: 10.2147/JHC.S465962. eCollection 2024.
5
Machine learning-based model for predicting tumor recurrence after interventional therapy in HBV-related hepatocellular carcinoma patients with low preoperative platelet-albumin-bilirubin score.基于机器学习的模型,用于预测术前血小板-白蛋白-胆红素评分低的 HBV 相关肝细胞癌患者介入治疗后肿瘤复发。
Front Immunol. 2024 May 28;15:1409443. doi: 10.3389/fimmu.2024.1409443. eCollection 2024.
6
Construction and validation of a nomogram for hepatocellular carcinoma patients based on HCC-GRIm score.基于 HCC-GRIm 评分构建和验证肝癌患者的列线图。
J Cancer Res Clin Oncol. 2023 Oct;149(13):12013-12024. doi: 10.1007/s00432-023-05037-x. Epub 2023 Jul 8.
7
Nomogram for predicting post-therapy recurrence in BCLC A/B hepatocellular carcinoma with Child-Pugh B cirrhosis.BCLC A/B 期合并 Child-Pugh B 级肝硬化肝癌患者经治疗后复发的预测列线图。
Front Immunol. 2024 May 10;15:1369988. doi: 10.3389/fimmu.2024.1369988. eCollection 2024.
8
Development and validation of a nomogram to predict the recurrence of hepatocellular carcinoma patients with dynamic changes in AFP undergoing locoregional treatments.用于预测接受局部区域治疗且甲胎蛋白动态变化的肝细胞癌患者复发的列线图的开发与验证。
Front Oncol. 2023 Aug 28;13:1206345. doi: 10.3389/fonc.2023.1206345. eCollection 2023.
9
Prognostic Nomogram for Hepatitis B Virus-related Hepatocellular Carcinoma With Adjuvant Transarterial Chemoembolization After Radical Resection.辅助性经动脉化疗栓塞术后乙型肝炎病毒相关肝细胞癌的预后列线图
Am J Clin Oncol. 2020 Jan;43(1):20-27. doi: 10.1097/COC.0000000000000619.
10
Nomogram for individualized prediction of recurrence after postoperative adjuvant TACE for hepatitis B virus-related hepatocellular carcinoma.用于个体化预测乙型肝炎病毒相关肝细胞癌术后辅助性经动脉化疗栓塞术复发的列线图
Medicine (Baltimore). 2017 Aug;96(32):e7390. doi: 10.1097/MD.0000000000007390.

引用本文的文献

1
Development and validation of a machine learning-based nomogram for survival prediction of patients with hilar cholangiocarcinoma after curative-intent resection.基于机器学习的列线图用于肝门部胆管癌根治性切除术后患者生存预测的开发与验证
Sci Rep. 2025 Jul 12;15(1):25220. doi: 10.1038/s41598-025-10329-y.
2
Prediction Model and Decision Analysis for Early Recognition of SDNS/FRNS in Children.儿童类固醇耐药性肾病综合征/频繁复发肾病综合征早期识别的预测模型与决策分析
J Inflamm Res. 2024 Dec 7;17:10585-10598. doi: 10.2147/JIR.S494530. eCollection 2024.

本文引用的文献

1
Survival analysis and development of a prognostic nomogram for patients with hepatitis B virus-associated hepatocellular carcinoma.乙肝病毒相关肝细胞癌患者的生存分析及预后列线图的构建
Heliyon. 2023 Oct 10;9(10):e20850. doi: 10.1016/j.heliyon.2023.e20850. eCollection 2023 Oct.
2
Development and validation of a nomogram to predict the recurrence of hepatocellular carcinoma patients with dynamic changes in AFP undergoing locoregional treatments.用于预测接受局部区域治疗且甲胎蛋白动态变化的肝细胞癌患者复发的列线图的开发与验证。
Front Oncol. 2023 Aug 28;13:1206345. doi: 10.3389/fonc.2023.1206345. eCollection 2023.
3
Individual surveillance by competing risk model for patients with hepatocellular carcinoma occurrence in all-cause cirrhosis.
采用竞争风险模型对全因性肝硬化患者肝细胞癌发生情况进行个体监测。
J Cancer Res Clin Oncol. 2023 Nov;149(14):13403-13416. doi: 10.1007/s00432-023-04911-y. Epub 2023 Jul 26.
4
Past, present, and future of long-term treatment for hepatitis B virus.乙型肝炎病毒长期治疗的过去、现在和未来。
World J Gastroenterol. 2023 Jul 7;29(25):3964-3983. doi: 10.3748/wjg.v29.i25.3964.
5
Establishment and Validation of a Novel Risk Score for Hepatocellular Carcinoma Based on Bile Acid and Bile Salt Metabolism-Related Genes.基于胆汁酸和胆汁盐代谢相关基因的新型肝细胞癌风险评分的建立和验证。
Int J Mol Sci. 2023 May 11;24(10):8597. doi: 10.3390/ijms24108597.
6
Construction and validation of a nomogram for HBV-related hepatocellular carcinoma: A large, multicenter study.构建并验证乙型肝炎病毒相关肝细胞癌的列线图:一项大型多中心研究。
Ann Hepatol. 2023 Jul-Aug;28(4):101109. doi: 10.1016/j.aohep.2023.101109. Epub 2023 Apr 24.
7
Inversed albumin-to-globulin ratio and underlying liver disease severity as a prognostic factor for survival in hepatocellular carcinoma patients undergoing transarterial chemoembolization.反白蛋白-球蛋白比值与潜在的肝脏疾病严重程度作为经肝动脉化疗栓塞治疗肝细胞癌患者生存的预后因素。
Diagn Interv Radiol. 2023 May 31;29(3):520-528. doi: 10.5152/dir.2022.211166. Epub 2023 Jan 23.
8
Effect of HBsAg expression in liver tissue on prognosis of hepatocellular carcinoma after minimally invasive interventional therapy.肝组织中HBsAg表达对微创介入治疗后肝细胞癌预后的影响
Front Oncol. 2023 Mar 9;13:1106333. doi: 10.3389/fonc.2023.1106333. eCollection 2023.
9
Nomogram established on account of Lasso-Cox regression for predicting recurrence in patients with early-stage hepatocellular carcinoma.列线图基于 Lasso-Cox 回归建立,用于预测早期肝细胞癌患者的复发情况。
Front Immunol. 2022 Nov 23;13:1019638. doi: 10.3389/fimmu.2022.1019638. eCollection 2022.
10
Combinatory local ablation and immunotherapies for hepatocellular carcinoma: Rationale, efficacy, and perspective.联合局部消融与免疫治疗肝细胞癌:原理、疗效与展望。
Front Immunol. 2022 Nov 23;13:1033000. doi: 10.3389/fimmu.2022.1033000. eCollection 2022.