Development and Validation of a Novel Risk Prediction Model Using Recursive Feature Elimination Algorithm for Acute-on-Chronic Liver Failure in Chronic Hepatitis B Patients With Severe Acute Exacerbation

Mingxue Yu; Xiangyong Li; Yaxin Lu; Yusheng Jie; Xinhua Li; Xietong Shi; Shaolong Zhong; Yuankai Wu; Wenli Xu; Zifeng Liu; Yutian Chong

doi:10.3389/fmed.2021.748915

Development and Validation of a Novel Risk Prediction Model Using Recursive Feature Elimination Algorithm for Acute-on-Chronic Liver Failure in Chronic Hepatitis B Patients With Severe Acute Exacerbation

Front Med (Lausanne). 2021 Nov 1:8:748915. doi: 10.3389/fmed.2021.748915. eCollection 2021.

Authors

Affiliations

¹ TheDepartment of Infectious Disease, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
² The Department of Clinical Data Center, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
³ The Department of Infectious Disease, Jieyang People's Hospital (Jieyang Affiliated Hospital of Sun Yat-sen University), Jieyang, China.

Abstract

Background: Patients with chronic hepatitis B (CHB) with severe acute exacerbation (SAE) are at a progression stage of acute-on-chronic liver failure (ACLF) but uniform models for predicting ACLF occurrence are lacking. We aimed to present a risk prediction model to early identify the patients at a high risk of ACLF and predict the survival of the patient. Methods: We selected the best variable combination using a novel recursive feature elimination algorithm to develop and validate a classification regression model and also an online application on a cloud server from the training cohort with a total of 342 patients with CHB with SAE and two external cohorts with a sample size of 96 and 65 patients, respectively. Findings: An excellent prediction model called the PATA model including four predictors, prothrombin time (PT), age, total bilirubin (Tbil), and alanine aminotransferase (ALT) could achieve an area under the receiver operating characteristic curve (AUC) of 0.959 (95% CI 0.941-0.977) in the development set, and AUC of 0.932 (95% CI 0.876-0.987) and 0.905 (95% CI 0.826-0.984) in the two external validation cohorts, respectively. The calibration curve for risk prediction probability of ACLF showed optimal agreement between prediction by PATA model and actual observation. After predictive stratification into different risk groups, the C-index of predictive 90-days mortality was 0.720 (0.675-0.765) for the PATA model, 0.549 (0.506-0.592) for the end-stage liver disease score model, and 0.648 (0.581-0.715) for Child-Turcotte-Pugh scoring system. Interpretation: The highlypredictive risk model and easy-to-use online application can accurately predict the risk of ACLF with a poor prognosis. They may facilitate risk communication and guidetherapeutic options.

Keywords: acute exacerbation; acute-on-chronic liver failure (ACLF); chronic hepatitis B; machine learning; prediction model; recursive feature elimination algorithm.