Parameters associated with significant liver histological changes in patients with chronic hepatitis B

A machine learning-based model analysis for serum markers of liver fibrosis in chronic hepatitis B patients

Early assessment and accurate staging of liver fibrosis may be of great help for clinical diagnosis and treatment in patients with chronic hepatitis B (CHB). We aimed to identify serum markers and construct a machine learning (ML) model to reliably predict the stage of fibrosis in CHB patients. 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. In addition, a total of 571 patients from another hospital were used as an external validation cohort to verify the performance of the model. The DT model constructed based on five serological biomarkers included HBV-DNA, platelet, thrombin time, international normalized ratio and albumin, with the area under curve (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 cutoff value showed that the classification performance of the DT model in distinguishing hepatic fibrosis stages can be accurately matched with pathological diagnosis results. ML model of five serum markers allows for accurate diagnosis of hepatic fibrosis stages, and beneficial for the clinical monitoring and treatment of CHB patients.

A Noninvasive Score to Predict Liver Fibrosis in HBeAg-Positive Hepatitis B Patients with Normal or Minimally Elevated Alanine Aminotransferase Levels

Noninvasive fibrosis tests are highly needed but have not been well studied in chronic hepatitis B patients with normal or minimally elevated alanine aminotransferase (ALT) levels. This study is aimed at developing a noninvasive score system to predict liver fibrosis in these patients. HBeAg-positive chronic hepatitis B patients with ALT levels of <80 IU/l and liver histology (n = 290) were assigned to training (n = 203) or validation (n = 87) groups. Training group patients were divided into nonsignificant (F0–1) and significant fibrosis (F2–4) according to METAVIR stages. Logistic regression was performed to identify factors for liver fibrosis and develop a score system. The capacity of the score to identify the severity of fibrosis was displayed by receiver operating characteristic curve (ROC) and area under ROC (AUROC) values. Multivariate logistic regression showed that HBeAg (ratios of the sample to the cutoff values (S/CO)) and liver stiffness measurement (LSM; kilopascals (kPa)) were independent factors of liver fibrosis. A score system composed of HBeAg and LSM by assigning a point of 1, 2, or 3 to different HBeAg and LSM levels, respectively, was developed. The scores 2-3, 4, and 5-6 of the sum of HBeAg and LSM points indicated nonsignificant, indeterminate, and significant fibrosis, respectively. The score system had an AUROC of 0.880 and showed similar performance in validation group patients. The accuracy for identifying significant and nonsignificant fibrosis was 77.14% in validation group patients and 71.26% in the entire group of patients. It is suggested that this noninvasive score system can accurately predict hepatic fibrosis and may reduce the need for liver biopsy in HBeAg-positive patients with normal or minimally elevated ALT levels.

Noninvasive Biomarkers in Assessment of Liver Fibrosis in Patients with HBeAg Negative Chronic Hepatitis B

BACKGROUND

Liver biopsy for evaluation of liver fibrosis has several adverse effects, for which reason noninvasive tests have been developed.

AIM

To evaluate the usefulness of noninvasive biomarkers, qHBsAg and HBV DNA levels in predicting liver fibrosis in patients with hepatitis Be antigen (HBeAg) negative chronic hepatitis B (CHB).

MATERIAL AND METHODS

This prospective study included 50 patients with HBeAg negative CHB. All patients underwent laboratory and serology testing, quantification of HBV DNA and HBs antigen. The liver stiffness was measured with elastography. The patients were analysed for APRI and FIB-4, quantitative hepatitis Bs antigen and HBV DNA.

RESULTS

Logistic regression analysis showed that greatest significance in predicting liver fibrosis has FIB-4 (Wald = 3.24, P = 0.07), followed by HBV DNA ≥ 2 000 IU/ml ≤ 20 000 IU/ml (Wald = 2.86, P = 0.09), qHBsAg (Wald = 2.17, P = 0.14), HBV DNA > 20 000 IU/ml (Wald = 0.58, P = 0.45), APRI (Wald = 0.04, P = 0.84).

CONCLUSION

the FIB-4 index has the greatest value in predicting liver fibrosis while APRI has the lowest; the more advanced liver disease is associated with lower serum level of quantitative HBs antigen. Combination of noninvasive blood biomarkers and imaging tests can provide better diagnostic accuracy and exclude the need for liver biopsy.

Nomogram for cirrhosis in patients with chronic hepatitis B: A simple self-assessed scale for individual risk of cirrhosis

The aim of this retrospective study was to establish a simple self-assessed scale for individual risk of cirrhosis in patients with chronic hepatitis B. A total of 1808 consecutive patients were enrolled and analyzed. According to the results of multivariate logistic regression analysis, a simple nomogram was calculated for cirrhosis. The area under receiver operating characteristic curves (AUROCs) were calculated to compare the diagnostic accuracy of nomogram with aspartate aminotransferase to platelet ratio index (APRI), fibrosis index based on the four factors (FIB-4), and S index. The AUROCs of nomogram for cirrhosis were 0.807 (adjusted AUROC 0.876) in model group and 0.794 (adjusted AUROC0.866) in validation group. DeLong's test and Brier Score further demonstrated that nomogram was superior to APRI, FIB-4 and S index in both model group and validation group. The patients with nomogram <0.07 could be defined as low risk group with cirrhosis prevalence lower than 4.3% (17/397). The patients with nomogram >0.52 could be defined as high risk group with cirrhosis prevalence higher than 73.0% (119/163). In conclusion, as a self-assessed style, simple, non-invasive, economical, convenient, and repeatable scale, nomogram is suitable to serve as a massive health screening tool for cirrhosis in CHB patients and further external validation is needed.

A novel noninvasive algorithm for the assessment of liver fibrosis in patients with chronic hepatitis B virus infection

Several noninvasive blood biomarkers have been established for the assessment of liver fibrosis in patients with chronic hepatitis B virus (HBV) infection, but their clinical performance remains inconclusive. Here, we compared the diagnostic performance of these biomarkers and developed a novel algorithm for assessing liver fibrosis. Six hundred and sixteen chronically HBV-infected and treatment-naïve patients who underwent liver biopsy were enrolled and randomly divided into training (N=410) and internal validation cohorts (N=206). One hundred and fifty-nine patients from another centre were recruited as an external validation cohort. Receiver operating characteristic (ROC) curves were used to analyse the performance of the gamma-glutamyltransferase-to-platelet ratio (GPR), red cell volume distribution width-to-platelet ratio (RPR), FIB-4 index, aspartate aminotransferase-to-platelet ratio index (APRI) and HBV DNA level against liver histology, and a novel algorithm was developed using the recursive partitioning and regression tree (RPART) method. In the training cohort, the area under the ROC curve of FIB-4 was significantly higher than that of APRI (P=.038) but was comparable to those of GPR, RPR and HBV DNA; however, the performance of the biomarkers was similar among the validation cohort. The established RPR-HBV DNA algorithm performed better in the training cohort than any individual blood biomarker, and the corresponding sensitivity, specificity, positive predictive value and negative predictive value were 63%, 90%, 72% and 80%, respectively. In the internal and external validation cohorts, the performance of the algorithm in assessing liver fibrosis was also superior to that of other biomarkers. These results suggest that the established RPR-HBV DNA algorithm might improve the diagnostic accuracy of liver fibrosis in treatment-naïve patients with chronic HBV infection, although additional studies are warranted to confirm these findings.

A novel non-invasive index using AFP and APTT is associated with liver fibrosis in patients with chronic hepatitis B infection: a retrospective cohort study

OBJECTIVE

A liver biopsy is the 'reference standard' for diagnosing and staging liver fibrosis but with many disadvantages. Therefore, developing a non-invasive index for predicting fibrosis is very valuable. We developed and validated a novel non-invasive index for predicting significant fibrosis in patients with chronic hepatitis B infection.

DESIGN

A retrospective cohort study.

SETTING

Chronic hepatitis B virus-infected patients were recruited in the Department of Infectious Disease in the First Affiliated Hospital of Zhejiang University.

PARTICIPANTS

A total of 506 patients were enrolled, and patients were randomly divided into estimation (n=253) and validation (n=253) cohorts.

PRIMARY AND SECONDARY OUTCOME MEASURES

Chronic hepatitis B virus-infected patients were studied retrospectively using routine parameters. A novel index was developed from an estimation cohort and validated in another cohort. Liver histology was assessed for fibrosis according to the Xi'an Meeting Scoring System. The novel index using α-fetal protein (AFP) and activated partial thromboplastin time (APTT; denoted AA index) was compared with 10 other indices using receiving operating characteristics curves. Multivariate forward stepwise regression analysis revealed that AFP and APTT were significantly associated with the Xi'an Meeting Scoring System, and were used to calculate the AA index (log index=-9.164+0.114×AFP+0.236×APTT).

RESULTS

The AA index predicted significant fibrosis with an area under the curve of 0.822, exhibited a significantly higher area compared with the other 10 indices in the estimation cohort, and was validated in the validation cohort.

CONCLUSIONS

The AA index can be used to predict significant fibrosis, and may decrease the need for liver biopsy in patients with chronic hepatitis B infection.

HBV DNA level could predict significant liver fibrosis in HBeAg negative chronic hepatitis B patients with biopsy indication

Background

Non-invasive models and methods to substitute liver biopsy in chronic hepatitis B (CHB) patients were investigated but their roles as predictors of significant liver histology for diagnosis of HBeAg-negative CHB patients who had indication for liver biopsy according to The American Association for the Study of Liver Diseases (AASLD) and The Asian Pacific Association for the Study of the Liver (APASL) guidelines are still unknown. This study was designed to identify predictors of significant liver necroinflammation as defined by a Histology Activity Index of necroinflammatory score ≥ 4 or Metavir necroinflammatory activity score ≥ 2 and significant liver fibrosis as defined by a Metavir fibrosis score ≥ 2 in HBeAg-negative CHB patients that had a hepatitis B virus (HBV) DNA level ≥ 2,000 IU/ml and age ≥ 40 years or elevated alanine aminotransferase level between 1–2 times the upper limit of normal.

Methods

Twenty-two patients were prospectively included and performed liver biopsies. Clinical and laboratory parameters including age, gender, underlying disease, family history of cirrhosis or hepatocellular carcinoma, body mass index (BMI), HBV DNA level, HBsAg level, liver function test, complete blood count, aspartate aminotransferase-to-platelet ratio index and transient elastography were collected and analyzed with liver histology profiles.

Results

Five patients (23%) had significant liver inflammation and 7 patients (32%) had significant liver fibrosis. Factors associated with significant liver inflammation were a lower BMI and higher alkaline phosphatase level while a factor associated with significant liver fibrosis was lower age. On multivariate analysis, only HBV DNA level > 5.5 log IU/ml could predict significant liver fibrosis (odds ratio 28.012, 95% CI, 1.631-481.240, p = 0.022) and its sensitivity, specificity, positive predictive value and negative predictive value were 71.4%, 93.3%, 83.3% and 87.5% respectively.

Conclusions

An HBV DNA level of > 5.5 log IU/ml was able to predict significant liver fibrosis for treatment of HBeAg-negative CHB patients that had indication for liver biopsy as recommended by AASLD and APASL guidelines.