PO.BCS02.06 · 生物信息与计算
CAPTYN：一个预测阿替利珠单抗-贝伐珠单抗治疗肝细胞癌临床获益的六变量机器学习模型——在IMbrave150中的开发与外部验证
CAPTYN, a six-variable machine-learning model predicting clinical benefit of atezolizumab-bevacizumab in hepatocellular carcinoma: Development and external validation in IMbrave150
该海报暂无可下载的资料
AACR 官方页面
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
背景：目前用于阿替利珠单抗联合贝伐珠单抗（AB）治疗肝细胞癌（HCC）的预后模型依赖于有限的变量，且缺乏前瞻性验证。我们旨在开发并外部验证一个整合多个临床变量的机器学习模型，以预测一线AB治疗晚期HCC的临床获益。
方法与结果：这项多中心研究纳入了来自三家医院和一项III期前瞻性试验（IMbrave150）的637例不可切除HCC患者，分为四个AB队列。训练集包含来自CHA Bundang Medical Center（韩国，n=301）和Medical University of Vienna（奥地利，n=53）的患者，而外部验证使用了IMbrave150（n=99）和Severance Hospital（韩国，n=184）队列。临床获益（CB）定义为按RECIST v1.1达到CR、PR，或SD且PFS≥6个月；所有其他情况归类为非临床获益（NCB）。在14个候选变量中，有9个通过针对OS和PFS的单变量Cox回归被识别出来。一个最大化五折交叉验证AUC以进行NCB分类的递归剔除流程识别出六个最优预测因子——CRP、AFP、血小板、总胆红素、淋巴细胞和中性粒细胞——用于训练一个XGBoost分类器，命名为CAPTYN。在训练集中，CAPTYN取得了0.93的AUC。基于SHAP的解释显示，CRP、AFP和总胆红素升高以及淋巴细胞计数降低对NCB有贡献，而血小板和中性粒细胞计数呈现U形关联。在外部验证中，CAPTYN在IMbrave150队列中取得0.70的AUC（95% CI，0.59-0.81），在Severance队列中取得0.67（0.59-0.75），优于CRAFITY、ALBI和CRAPT-M（DeLong检验 p<0.05）。校准可接受（Brier评分分别为0.22和0.24），且CAPTYN显著分层了OS和PFS（IMbrave150队列：均p<0.001；Severance队列：OS p=0.012，PFS p=0.009），而对照模型未能对PFS进行判别。IMbrave150中跨人口统计学和疾病特征的亚组分析一致显示，CAPTYN预测为NCB的患者其OS和PFS的风险比更高（>1.5）。
结论：CAPTYN是一个预测AB治疗临床获益的六变量机器学习模型，已使用一项前瞻性试验和一个真实世界队列进行外部验证，可提供经校准的、可解释的概率，或可为个体化治疗决策提供依据。
查看英文原文 English abstract
Background: Current prognostic models for hepatocellular carcinoma (HCC) treated with atezolizumab plus bevacizumab (AB) rely on limited variables and lack prospective validation. We aimed to develop and externally validate a machine-learning model integrating multiple clinical variables to predict clinical benefit to first-line AB in advanced HCC.
Methods and Results: This multicenter study included 637 patients with unresectable HCC from three hospitals and one phase III prospective trial (IMbrave150), grouped into four AB cohorts. The training set comprised patients from CHA Bundang Medical Center (Korea, n=301) and the Medical University of Vienna (Austria, n=53), while external validation used IMbrave150 (n=99) and Severance Hospital (Korea, n=184) cohort. Clinical benefit (CB) was defined as CR, PR, or SD with PFS ≥6 months by RECIST v1.1; all other cases were classified as non-clinical benefit (NCB). Among 14 candidate variables, nine were identified by univariable Cox regression for OS and PFS. A recursive elimination procedure maximizing five-fold cross-validated AUC for NCB classification identified six optimal predictors-CRP, AFP, platelet, total bilirubin, lymphocyte, and neutrophil-which were used to train an XGBoost classifier, termed CAPTYN. In the training set, CAPTYN achieved an AUC of 0.93. SHAP-based interpretation showed that elevated CRP, AFP, and total bilirubin and reduced lymphocyte counts contributed to NCB, whereas platelet and neutrophil counts exhibited U-shaped associations. In external validation, CAPTYN achieved AUCs of 0.70 (95% CI, 0.59-0.81) in IMbrave150 cohort and 0.67 (0.59-0.75) in Severance cohort, outperforming CRAFITY, ALBI, and CRAPT-M (DeLong's test p<0.05). Calibration was acceptable (Brier score=0.22 and 0.24, respectively), and CAPTYN significantly stratified OS and PFS (IMbrave150 cohort: both p<0.001; Severance cohort: p=0.012 for OS, p=0.009 for PFS), whereas comparator models failed to discriminate PFS. Subgroup analyses across demographics and disease features in IMbrave150 consistently showed higher hazard ratios (>1.5) for OS and PFS in CAPTYN-predicted NCB patients.
Conclusion: CAPTYN, a six-variable machine-learning model predicting CB to AB, was externally validated using a prospective trial and a real-world cohort, providing calibrated, interpretable probabilities that may inform individualized treatment decisions.
利益披露 Disclosure
G. Jo, None..
S. Hwang, None..
B. Scheiner, None..
W. Lee, None..
B. Kang, None..
J. Kim, None..
H. Lim, None..
C. An, None..
D. Kim, None..
I. Kim, None..
D. Heo, None..
M. Pinter, None..
B. Kim, None..
C. Kim, None..
H. Chon, None.