Individualized risk prediction of significant fibrosis in non‐alcoholic fatty liver disease using a novel nomogram

Zhou, Yujie; Ye, Fangzhou; Li, Yangyang; Pan, Xiaoyan; Chen, Yingxiao; Wu, Xixi; Xiong, Jie; Liu, Wen‐Yue; Xu, Shihao; Chen, Yongping; Zheng, Ming‐Hua

doi:10.1177/2050640619868352

Cited by 33 publications

(37 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, another meta-analysis indicated that APRI and FIB-4 had only moderate sensitivity and accuracy for diagnosis of liver fibrosis in chronic hepatitis B patients, which suggested they were not ideal substitutes for liver biopsy [ 39 ]. Regarding NAFLD, recent studies showed that APRI could better distinguish fibrosis stage F2-3 from F0-1 than FIB-4 [ 40 , 41 ]. The GPR developed by Lemoine et al was shown to be more accurate than the APRI and FIB-4 [ 42 ].…”

Section: Discussionmentioning

confidence: 99%

Nomogram for predicting advanced liver fibrosis and cirrhosis in patients with chronic liver disease

et al. 2021

View full text Add to dashboard Cite

Background We aimed to formulate a novel predictive nomogram to discriminate liver fibrosis stage in patients with chronic liver disease. Methods Nomograms were established based on the results of multivariate analysis. The predictive accuracy of the nomograms was assessed by ROC analysis and calibration. Decision curve analysis (DCA) was used to determine the clinical benefit of the nomograms. Results INR, platelets, and N-terminal propeptide type III collagen (PIIINP) were independent predictors for advanced liver fibrosis (≥ S3) and cirrhosis (S4) in patients with chronic liver disease in the training cohort. In the training set, the areas under the ROCs (AUROCs) of nomogram S3S4, APRI, FIB-4, and GPR for stage ≥ S3 were 0.83, 0.71, 0.68, and 0.74, respectively; the AUROCs of nomogram S4, APRI, FIB-4, and GPR for stage S4 were 0.88, 0.74, 0.78, and 0.79, respectively. The calibrations showed optimal agreement between the prediction by the established nomograms and actual observation. In the validation set, the AUROCs of nomogram S3S4, APRI, FIB-4, and GPR for stage ≥ S3 were 0.86, 0.79, 0.78, and 0.81, respectively; the AUROCs of nomogram S4, APRI, FIB-4, and GPR for stage S4 were 0.88, 0.77, 0.81, and 0.83, respectively. Furthermore, the decision curve analysis suggested that the nomograms represent better clinical benefits in both independent cohorts than APRI, FIB-4, and GPR. Conclusion The constructed nomograms could be a superior tool for discriminating advanced fibrosis and cirrhosis in chronic liver disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Nomogram for predicting advanced liver fibrosis and cirrhosis in patients with chronic liver disease

et al. 2021

View full text Add to dashboard Cite

show abstract

“…While the diagnostic performance of these non-invasive tests is satisfactory for ruling out advanced fibrosis, their performance is not adequate for diagnosing clinically significant liver fibrosis. 5,6 A recent meta-analysis showed that even low levels of liver fibrosis are associated with overall and liver-specific mortality, and these data are supported by the results of a large biopsy study with a mean of 20 years follow-up showing that advanced fibrosis was associated with liver-specific morbidity and overall mortality. 3 Additionally, distinguishing between NAFLD with or without significant fibrosis is clinically important for determining the clinical prognosis of these patients.…”

Section: Introductionmentioning

confidence: 89%

Machine learning algorithm outperforms fibrosis markers in predicting significant fibrosis in biopsy‐confirmed NAFLD

Feng

Zheng

et al. 2021

J Hepato Biliary Pancreat

Self Cite

View full text Add to dashboard Cite

Background:The presence of significant liver fibrosis is a key determinant of longterm prognosis in non-alcoholic fatty liver disease (NAFLD). We aimed to develop a novel machine learning algorithm (MLA) to predict fibrosis severity in NAFLD and compared it with the most widely used non-invasive fibrosis biomarkers. Methods: We used a cohort of 553 adults with biopsy-proven NAFLD, who were randomly divided into a training cohort (n = 278) for the development of both logistic regression model (LRM) and MLA, and a validation cohort (n = 275). Significant fibrosis was defined as fibrosis stage F ≥ 2. MLA and LRM were derived from variables that were selected using a least absolute shrinkage and selection operator (LASSO) logistic regression algorithm. Results: In the training cohort, the variables selected by LASSO algorithm were body mass index, pro-collagen type III, collagen type IV, aspartate aminotransferase and albumin-to-globulin ratio. The diagnostic accuracy of MLA showed the highest values of area under the receiver operator characteristic curve (AUROC: 0.902, 95% CI 0.869-0.904) for identifying fibrosis F ≥ 2. The LRM AUROC was 0.764,

show abstract

“…This is an observational study of the well-characterized Prospective Epidemic Research Specifically Of NASH (PERSONS) cohort 12. Patients enrolled in this study fulfilled the following criteria: (1) age between 18–75 years; (2) presence of hepatic steatosis on liver ultrasound or other imaging techniques, and then confirmed by liver biopsy, in the absence of other competing causes of chronic liver diseases (as specified in the Results section); and (3) provided informed written consent prior to their inclusion in the study.…”

Section: Methodsmentioning

confidence: 99%

Combined and sequential non-invasive approach to diagnosing non-alcoholic steatohepatitis in patients with non-alcoholic fatty liver disease and persistently normal alanine aminotransferase levels

Zheng

Liu

Pan

et al. 2020

BMJ Open Diab Res Care

Self Cite

View full text Add to dashboard Cite

Background and aimImaging-confirmed non-alcoholic fatty liver disease (NAFLD) with normal alanine aminotransferase (nALT) levels is infrequently the subject for further evaluation. Early diagnosis of non-alcoholic steatohepatitis (NASH) is needed to prevent disease progression. Thus, we tested the clinical utility of serum Golgi protein 73 (GP73) levels and developed a new non-invasive score to diagnose NASH in patients with biopsy-confirmed NAFLD and persistent nALT levels.MethodsSerum GP73 and cytokeratin-18 M30 fragments (CK18-M30) levels were measured in 345 patients with biopsy-proven NAFLD. We developed a new score, named G-NASH model (by incorporating serum GP73), and combined it with serum CK18-M30 measurement in a sequential non-invasive approach to accurately identify NASH among patients with NAFLD and persistent nALT levels.Results105 (30.4%) patients had persistent nALT, 53 of whom had histologically confirmed NASH. Both serum GP73 and CK18-M30 levels alone had poor diagnostic accuracy in identifying NASH (55.2% and 51.6%, respectively) in these patients. Conversely, G-NASH model performed better than other established non-invasive scoring systems, and by using our proposed sequential non-invasive approach 82.9% of patients with NASH were correctly identified.ConclusionsNASH is highly prevalent in patients with NAFLD with persistent nALT levels. The G-NASH model accurately identifies NASH in this patient group.

show abstract

Individualized risk prediction of significant fibrosis in non‐alcoholic fatty liver disease using a novel nomogram

Cited by 33 publications

References 29 publications

Nomogram for predicting advanced liver fibrosis and cirrhosis in patients with chronic liver disease

Nomogram for predicting advanced liver fibrosis and cirrhosis in patients with chronic liver disease

Machine learning algorithm outperforms fibrosis markers in predicting significant fibrosis in biopsy‐confirmed NAFLD

Combined and sequential non-invasive approach to diagnosing non-alcoholic steatohepatitis in patients with non-alcoholic fatty liver disease and persistently normal alanine aminotransferase levels

Contact Info

Product

Resources

About