机器学习聚类区分双叶肝细胞癌特征与预后
基于多机构2000至2023年347例双叶肝细胞癌根治性肝切除患者,用k-means聚类识别出2种表型:大肿瘤高负荷非肝硬化型(cluster 1,n=95)和多发小结节型(cluster 2,n=252)。Cluster 1病理更侵袭、5年总生存34.9% vs 63.2%(P<.001)、早期复发53.7% vs 38.1%(P=.02);校正切缘和微血管侵犯后聚类仍独立关联总生存(HR 2.15,95%CI 1.48-3.13,P<.001)和无复发生存(HR 1.52,95%CI 1.11-2.06,P<.01)。
要点
- 双叶肝细胞癌可分两种表型,预后差异显著
- 高负荷大肿瘤非肝硬化型预后差,5年总生存34.9%
- 低负荷多发小结节型预后较好,5年总生存63.2%
核心结论
- 双叶肝细胞癌包含2种临床相关表型,肿瘤负荷、手术策略和结局不同。
- 基于术前临床和影像变量的表型分层可能有助于细化手术选择。
- 低负荷多发病灶预后较好,而主病灶伴卫星灶预后较差,支持该亚组采用多模式策略。
研究设计与样本
- 多机构数据库2000至2023年接受根治性肝切除的双叶肝细胞癌患者回顾性分析。
- 采用k-means聚类识别表型亚组,共纳入347例患者。
- 用Kaplan-Meier法和多因素Cox回归评估总生存和无复发生存。
主要发现
- Cluster 1(n=95)特征为大肿瘤、高肿瘤负荷、非肝硬化、常行大范围肝切除。
- Cluster 2(n=252)特征为多发较小病灶,更多使用微创手术和同期消融。
- Cluster 1病理特征更侵袭,5年总生存34.9% vs 63.2%(P<.001)。
- Cluster 1早期复发率53.7%(n=51)vs 38.1%(n=96),P=.02。
- 校正切缘状态和微血管侵犯后,聚类仍独立关联总生存(HR 2.15,95%CI 1.48-3.13,P<.001)和无复发生存(HR 1.52,95%CI 1.11-2.06,P<.01)。
关键数值与推荐
- 5年总生存:cluster 1为34.9%,cluster 2为63.2%(P<.001)。
- 早期复发:cluster 1为53.7%(n=51),cluster 2为38.1%(n=96)(P=.02)。
- 总生存独立关联:HR 2.15(95%CI 1.48-3.13,P<.001)。
- 无复发生存独立关联:HR 1.52(95%CI 1.11-2.06,P<.01)。
临床怎么用
- 可利用术前临床和影像变量对双叶肝细胞癌进行表型分层以辅助手术选择。
- 高负荷大肿瘤非肝硬化表型预后较差,应考虑多模式治疗策略。
- 低负荷多发小结节表型行微创手术和同期消融可获得较好生存。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Bilateral hepatocellular carcinoma represents a biologically heterogeneous disease with uncertain optimal surgical selection criteria. Although hepatic resection can provide survival benefit in selected patients, outcomes remain variable, and phenotypic determinants of prognosis have not been clearly defined. METHODS: Patients who underwent curative-intent hepatectomy for bilateral hepatocellular carcinoma from a multi-institutional database from 2000 to 2023 were reviewed. k-means clustering to identify phenotypic subgroups. Overall survival and recurrence-free survival were evaluated using Kaplan-Meier product-limit methods and multivariable Cox regression. RESULTS: Among 347 patients, unsupervised clustering identified 2 distinct phenotypes: cluster 1 (n = 95) characterized by larger tumors, higher tumor burden, non-cirrhotic livers, and frequent major hepatectomy; and cluster 2 (n = 252) characterized by multiple smaller lesions, treated with greater use of minimally invasive surgery and concomitant ablation. Cluster 1 demonstrated more aggressive pathologic features and worse survival (5-year overall survival 34.9 vs 63.2%; P < .001) and higher early recurrence (53.7 [n = 51] vs. 38.1% [n = 96]; P = .02). Cluster classification remained independently associated with overall survival (hazard ratio [HR], 2.15; 95% CI, 1.48-3.13; P < .001) and recurrence-free survival (HR 1.52; 95% CI, 1.11-2.06; P < .01) even after adjustment for margin status and microvascular invasion. CONCLUSIONS: Bilateral hepatocellular carcinoma encompasses 2 clinically relevant phenotypes with distinct tumor burden, operative strategies, and outcomes. Phenotype-based stratification using preoperative clinical and radiologic variables may help refine surgical selection. Low-burden multifocal disease achieved favorable survival, whereas dominant plus satellites disease had inferior prognosis, supporting multimodal strategies for this subgroup.
引用
- Endo Y, Kawashima J, Chatzipanagiotou O, et al. Machine learning-based clustering differentiates bilateral hepatocellular carcinoma characteristics and prognosis. Surgery. 2026. PMID: 41955886. doi:10.1016/j.surg.2026.110186
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。