Bai Xueting, Pu Chunwen, Zhen Wenchong, Huang Yushuang, Zhang Qian, Li Zihan, Zhang Yixin, Xu Rongxuan, Yao Zhihan, Wu Wei, Sun Mei, Li Xiaofeng
Department of Epidemiology and Health Statistics, Dalian Medical University, Dalian, China.
Dalian Public Health Clinical Center, Dalian, Liaoning province, China.
Ann Med. 2025 Dec;57(1):2477294. doi: 10.1080/07853890.2025.2477294. Epub 2025 Mar 19.
Chronic hepatitis B (CHB) is a common cause of liver cirrhosis (LC), a condition associated with an unfavourable prognosis. Therefore, timely diagnosis of LC in CHB patients is crucial.
This study aimed to enhance the diagnostic accuracy of LC in CHB patients by integrating liver stiffness measurement (LSM) with traditional indicators.
The study participants were randomly divided into training and internal validation sets. Employing the least absolute shrinkage and selection operator (LASSO) and random forest-recursive feature elimination (RF-RFE) for feature selection, we developed both traditional logistic regression and five machine learning models (k-nearest neighbors, random forest (RF), artificial neural network, support vector machine and eXtreme Gradient Boosting). Performance evaluation included receiver operating characteristic curves, calibration curves and decision curve analysis. Shapley additive explanations (SHAP) was employed to improve the interpretability of the optimal model.
We retrospectively included 1609 patients with CHB, among whom 470 were diagnosed with cirrhosis. Cirrhosis was diagnosed based on histological confirmation or clinical assessment, supported by characteristic findings on abdominal ultrasound and corroborative evidence such as thrombocytopenia, varices or imaging from CT/MRI. In the internal validation, the RF model achieved an accuracy above 0.80 and an AUC above 0.80, with outstanding calibration ability and clinical net benefit. Additionally, the model exhibited excellent predictive performance in an independent external validation set. The SHAP analysis indicated that LSM contributed the most to the model. The model still showed strong discriminative power when using only LSM or traditional indicators alone.
Machine learning models, especially the RF model, can effectively identify LC in CHB patients. Integrating LSM with traditional indicators can enhance diagnostic performance.
慢性乙型肝炎（CHB）是肝硬化（LC）的常见病因，肝硬化与不良预后相关。因此，及时诊断CHB患者的肝硬化至关重要。
本研究旨在通过将肝脏硬度测量（LSM）与传统指标相结合，提高CHB患者肝硬化的诊断准确性。
研究参与者被随机分为训练集和内部验证集。采用最小绝对收缩和选择算子（LASSO）和随机森林递归特征消除（RF-RFE）进行特征选择，我们开发了传统逻辑回归模型和五种机器学习模型（k近邻、随机森林（RF）、人工神经网络、支持向量机和极端梯度提升）。性能评估包括受试者工作特征曲线、校准曲线和决策曲线分析。采用Shapley加法解释（SHAP）来提高最优模型的可解释性。
我们回顾性纳入了1609例CHB患者，其中470例被诊断为肝硬化。肝硬化的诊断基于组织学证实或临床评估，并得到腹部超声特征性表现以及血小板减少、静脉曲张或CT/MRI成像等佐证证据的支持。在内部验证中，RF模型的准确率高于0.80，曲线下面积（AUC）高于0.80，具有出色的校准能力和临床净效益。此外，该模型在独立的外部验证集中表现出优异的预测性能。SHAP分析表明LSM对模型的贡献最大。仅使用LSM或传统指标时，该模型仍显示出较强的判别能力。
机器学习模型，尤其是RF模型，能够有效识别CHB患者的肝硬化。将LSM与传统指标相结合可提高诊断性能。
