Prediction of hepatic inflammation in chronic hepatitis B patients with a random forest-backward feature elimination algorithm

Abstract

BACKGROUND Persistent liver inflammatory damage is the main risk factor for developing liver fibrosis, cirrhosis, and even hepatocellular carcinoma in chronic hepatitis B (CHB) patients. Thus, accurate prediction of the degree of liver inflammation is a high priority and a growing medical need. AIM To build an effective and robust non-invasive model for predicting hepatitis B-related hepatic inflammation. METHODS A total of 650 treatment-naïve CHB (402 HBeAg-positive and 248 HBeAg-negative) patients who underwent liver biopsy were enrolled in this study. Histological inflammation grading was assessed by the Ishak scoring system. Serum quantitative hepatitis B core antibody (qAnti-HBc) levels and 21 immune-related inflammatory factors were measured quantitatively using a chemiluminescent microparticle immunoassay. A backward feature elimination (BFE) algorithm utilizing random forest (RF) was used to select optional features and construct a combined model. The diagnostic abilities of the model or variables were evaluated based on the estimated area under the receiver operating characteristics curve (AUROC) and compared using the DeLong test. RESULTS Four features were selected to predict moderate-to-severe inflammation in CHB patients using the RF-BFE method. These predictive features included qAnti-HBc, ALT, AST, and CXCL11. Spearman’s correlation analysis indicated that serum qAnti-HBc, ALT, AST, and CXCL11 levels were positively correlated with the histology activity index (HAI) score. These selected features were incorporated into the model to establish a novel model named I-3A index. The AUROC [0.822; 95% confidence interval (CI): 0.790-0.851] of the I-3A index was significantly increased compared with qAnti-HBc alone (0.760, 95%CI: 0.724-0.792, P < 0.0001) in all CHB patients. The use of an I-3A index cutoff value of 0.41 produced a sensitivity of 69.17%, specificity of 81.44%, and accuracy of 73.8%. Additionally, the I-3A index showed significantly improved diagnostic performance for predicting moderate-to-severe inflammation in HBeAg-positive and HBeAg-negative CHB patients (0.829, 95%CI: 0.789-0.865 and 0.810, 95%CI: 0.755-0.857, respectively). CONCLUSION The selected features of the I-3A index constructed using the RF-BFE algorithm can effectively predict moderate-to-severe liver inflammation in CHB patients.

Dose–response relationship between qAnti‐HBc and liver inflammation in chronic hepatitis B with normal or mildly elevated alanine transaminase based on liver biopsy

“…The exploration of subgroups/interactions analyses and control for confounding were extremely important for a scientific study, according to STROBE statement 22 . Unfortunately, besides the above two studies, the other three studies were also not involved 15,25,26 …”

“…22 Unfortunately, besides the above two studies, the other three studies were also not involved. 15,25,26 Besides the role mentioned above, there were numerous values of qAnti-HBc in the diagnosis and treatment monitoring of hepatitis B. These include the following values: identification of the natural history of hepatitis B (immune-tolerant phase was lower compared to immune-clearance phase) 12,27 ; positive correlation with liver fibrosis stage (used to help diagnose significant fibrosis) 28,29 ; positive correlation with HBeAg seroconversion after interferon 13,30 or T A B L E 4 Relationship between qAnti-HBc and Ishak score of HAI in patients receiving entecavir-based therapy followed to 78 weeks.…”

“…Thirty-nine studies were retrieved from the database as of the end of November 2021, but only 5 of them were related to our study. 15,[23][24][25][26] Although the results of Yao et al 23 and Chen et al 24 studies showed that anti-HBc was positively associated with liver inflammation, they used Abbott GmbH & Co. KG 's semi-quantitative kit (unit was S/CO) rather than quantification of anti-HBc (unit was IU/ml). Furthermore, none of them evaluated the relationship between anti-HBc and liver inflammation in patients after antiviral treatment.…”

“…We used the following search strategy: ((“liver inflammation” [Title/Abstract] OR “liver necroinflammation”[Title/Abstract] OR “liver biopsy”[Title/Abstract]) AND (“hepatitis b core antibody”[Title/Abstract] OR “anti‐HBc”[Title/Abstract] OR “HBcAb”[Title/Abstract])) AND (2010/1/1:2021/11/20[pdat]) to search the relationship between qAnti‐HBc and liver inflammation in PubMed database. Thirty‐nine studies were retrieved from the database as of the end of November 2021, but only 5 of them were related to our study 15,23–26 . Although the results of Yao et al 23 and Chen et al 24 studies showed that anti‐HBc was positively associated with liver inflammation, they used Abbott GmbH & Co. KG 's semi‐quantitative kit (unit was S/CO) rather than quantification of anti‐HBc (unit was IU/ml).…”

Clinical Utility of Quantitative HBV Core Antibodies for Solving Diagnostic Dilemmas

“…There is mounting evidence that qAnti-HBc level not only correlates positively with the severity of liver inflammation but also decreases with the improvement of inflammation severity in patients receiving therapy [ 19 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 ]. It was shown that serum qAnti-HBc level, ALT and liver inflammation activity were closely related [ 44 , 47 ]. The background of this association is the interplay between the virus and the host’s immune system.…”