Tu Hai-Bin, Feng Si-Yi, Chen Li-Hong, Huang Yu-Jie, Zhang Ju-Zhen, Peng Su-Yu, Lin Ding-Luan, Ye Xiao-Jian
Department of Ultrasound, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350025, Fujian Province, China.
Department of Positron Emission Tomography, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350025, Fujian Province, China.
World J Gastrointest Oncol. 2025 May 15;17(5):105872. doi: 10.4251/wjgo.v17.i5.105872.
Hepatocellular carcinoma (HCC) is a major global contributor to cancer-related mortality, with advanced stages presenting substantial therapeutic challenges. Although targeted immunotherapy shows potential, many patients exhibit poor responses, underscoring the need for predictive tools to optimize treatment strategies. Emerging data indicate that ultrasound features (, tumor stiffness) and serum biomarkers may serve as predictors of treatment outcomes. However, an integrated model for these predictors remains unavailable. This paper introduces a machine learning-based approach that combines ultrasound and serological data to forecast immunotherapy efficacy in patients with advanced HCC.
To develop a non-invasive predictive model for targeted immunotherapy in advanced HCC, incorporating both internal and external validation.
Patients with advanced HCC who received targeted immunotherapy at two medical centers were enrolled and divided into internal training, internal validation, and external validation cohorts. Comprehensive clinical data were gathered. Initially, 13 machine learning algorithms were tested using the internal training cohort. The algorithm yielding the highest area under the curve (AUC) in the internal validation cohort was selected to construct a predictive model, termed the Target Immunotherapy Predictive Model (TIPM). TIPM performance was then compared with that of traditional tumor staging systems (tumor-node-metastasis, Barcelona Clinic Liver Cancer, China Liver Cancer, Hong Kong Liver Cancer, and C-reactive protein and alpha-fetoprotein in immunotherapy).
A total of 306 patients participated in the study, with 143 in the internal training cohort, 62 in the internal validation cohort, and 101 in the external validation cohort. In the internal validation cohort, the random forest model achieved the highest AUC (0.975, 95% confidence interval: 0.924-0.998). The key predictors for TIPM were tumor size, platelet count, tumor stiffness change, and white blood cell count. During external validation, TIPM outperformed conventional models, reaching an AUC of 0.899 (95% confidence interval: 0.840-0.957). Calibration curves demonstrated strong concordance with observed outcomes, while decision curve analysis confirmed TIPM's enhanced clinical value. Additional metrics, such as the net reclassification index and integrated discrimination improvement, further supported TIPM's superior predictive accuracy.
TIPM provides a robust tool for predicting targeted immunotherapy efficacy in advanced HCC, facilitating personalized treatment planning.
肝细胞癌（HCC）是全球癌症相关死亡的主要原因，晚期阶段面临重大治疗挑战。尽管靶向免疫疗法显示出潜力，但许多患者反应不佳，凸显了需要预测工具来优化治疗策略。新出现的数据表明，超声特征（如肿瘤硬度）和血清生物标志物可能作为治疗结果的预测指标。然而，这些预测指标的综合模型仍然不可用。本文介绍了一种基于机器学习的方法，该方法结合超声和血清学数据来预测晚期HCC患者的免疫治疗疗效。
建立一种用于晚期HCC靶向免疫治疗的非侵入性预测模型，并进行内部和外部验证。
纳入在两个医疗中心接受靶向免疫治疗的晚期HCC患者，并分为内部训练、内部验证和外部验证队列。收集全面的临床数据。最初，使用内部训练队列测试13种机器学习算法。选择在内部验证队列中曲线下面积（AUC）最高的算法来构建预测模型，称为靶向免疫治疗预测模型（TIPM）。然后将TIPM的性能与传统肿瘤分期系统（肿瘤-淋巴结-转移、巴塞罗那临床肝癌、中国肝癌、香港肝癌以及免疫治疗中的C反应蛋白和甲胎蛋白）的性能进行比较。
共有306例患者参与研究，其中143例在内部训练队列，62例在内部验证队列，101例在外部验证队列。在内部验证队列中，随机森林模型的AUC最高（0.975，95%置信区间：0.924-0.998）。TIPM的关键预测指标是肿瘤大小、血小板计数、肿瘤硬度变化和白细胞计数。在外部验证期间，TIPM的表现优于传统模型，AUC达到0.899（95%置信区间：0.840-0.957）。校准曲线显示与观察结果高度一致，而决策曲线分析证实了TIPM的临床价值增强。其他指标，如净重新分类指数和综合判别改善，进一步支持了TIPM的卓越预测准确性。
TIPM为预测晚期HCC靶向免疫治疗疗效提供了一个强大的工具，有助于个性化治疗规划。
