慢性肝炎
肝纤维化
医学
纤维化
内科学
胃肠病学
肿瘤科
病理
免疫学
病毒
作者
Zhenyu Shu,Shanshan Chen,Jiaxuan Peng,Yue-Yue Zhao,Xuan Dai,Jie Li,Xuehan Zou,Yuguo Wei,Jianhua Hu,Hai Huang
摘要
Background: Early assessment and accurate staging of liver fibrosis may be of great help in the clinical diagnosis and treatment of chronic hepatitis B (CHB) patients. We aimed to construct a machine learning (ML) model using serological biomarkers to accurately assessment of hepatic fibrosis stages for CHB patients.Methods: The clinical data of 618 CHB patients between February 2017 and September 2021 from Zhejiang Provincial People's Hospital were retrospectively analyzed, and these data as a training cohort to build the model. Six ML models were constructed based on logistic regression, support vector machine, Bayes, K-nearest neighbor, decision tree (DT) and random forest by using the maximum relevance minimum redundancy (mRMR) and gradient boosting decision tree (GBDT) dimensionality reduction selected features on the training cohort. Then, the resampling method was used to select the optimal ML model, and the receiver operating characteristic (ROC) curve was used to evaluate the performance of the model to further determine the cut-off value for the clinical diagnosis of hepatic fibrosis stages. In addition, a total of 571 patients from another hospital were used as an external validation cohort to verify the performance of the model.Results: The DT model constructed based on five serological biomarkers, with the AUC values of the DT model for assessment of liver fibrosis stages (F0-1, F2, F3 and F4) in the training cohort were 0.898, 0.891, 0.907 and 0.944, respectively. The AUC values of the DT model for assessment of liver fibrosis stages (F0-1, F2, F3 and F4) in the external validation cohort were 0.906, 0.876, 0.931 and 0.933, respectively. The simulated risk classification based on the cut-off value showed that the classification performance of the DT model in distinguishing hepatic fibrosis stages can be accurately matched with pathological diagnosis results.Conclusion: ML model of serum biomarkers allows for accurate diagnosis of hepatic fibrosis stages, and beneficial for the clinical monitoring and treatment of CHB patients.Funding: The study was supported by the Zhejiang Provincial Medicine and Health Science and Technology Project (No. 2019KY294).Declaration of Interests: The authors have no reported conflicts of interest to disclose for this study.Ethics Approval: This retrospective study was approved by the Ethics Committee of ZhejiangProvincial People’s Hospital, and the requirement for informed consent was waived.
科研通智能强力驱动
Strongly Powered by AbleSci AI