Assessment of the performance of haematological and non-invasive fibrotic indices for the monitoring of chronic HBV infection: a pilot study in a Ghanaian population

A New Assessment of Two Transferase-Based Liver Enzymes in Low- and High-Fibrosis Patients Chronically Infected with Hepatitis B Virus: A Meta-Analysis and Pilot Study

Background: The detection of fibrosis remains a necessity for the evaluation of hepatitis B virus (HBV)-infected patients, but the most accurate technique is invasive. Current studies aim to develop a novel noninvasive biomarker for fibrosis assessment, but no-one has found the ideal candidate. This study is a meta-analysis combined with a pilot study to investigate the connection between two transferase compounds and the levels of fibrosis. Methods: We studied data from PUBMED, Web of Science, and Scopus, retrieving 28,896 articles. Following PRISMA guidelines, we finally analyzed full-text articles written in English. The excluded items were duplicates, non-article entries, and irrelevant papers. We assessed the variations in alanine aminotransferase (ALT) and gamma-glutamyl transferase (GGT) levels between patients with high and low levels of fibrosis. Joanna Briggs Institute tools were used to assess article quality. We used R 4.2.2 for statistics. The pilot study included 14 randomly chosen patients with different fibrosis levels. Results: We found significant differences in ALT and GGT levels between patients with high and low fibrosis. The GGT/ALT ratio correlated with the levels of fibrosis and the fibrosis-4 (FIB-4) score. Conclusions: This meta-analysis assessed ALT and GGT levels in chronic HBV patients with fibrosis. The pilot study identified the first association between fibrosis and the GGT/ALT ratio in a Romanian cohort of chronic patients. This brings new ideas for future research.

Utility of four machine learning approaches for identifying ulcerative colitis and Crohn's disease

Objective

Peripheral blood routine parameters (PBRPs) are simple and easily acquired markers to identify ulcerative colitis (UC) and Crohn's disease (CD) and reveal the severity, whereas the diagnostic performance of individual PBRP is limited. We, therefore used four machine learning (ML) models to evaluate the diagnostic and predictive values of PBRPs for UC and CD.

Methods

A retrospective study was conducted by collecting the PBRPs of 414 inflammatory bowel disease (IBD) patients, 423 healthy controls (HCs), and 344 non-IBD intestinal diseases (non-IBD) patients. We used approximately 70 % of the PBRPs data from both patients and HCs for training, 30 % for testing, and another group for external verification. The area under the receiver operating characteristic curve (AUC) was used to evaluate the diagnosis and prediction performance of these four ML models.

Results

Multi-layer perceptron artificial neural network model (MLP-ANN) yielded the highest diagnostic performance than the other three models in six subgroups in the training set, which is helpful for discriminating IBD and HCs, UC and CD, active CD and remissive CD, active UC and remissive UC, non-IBD and HCs, and IBD and non-IBD with the AUC of 1.00, 0.988, 0.942, 1.00, 0.986, and 0.97 in the testing set, as well as the AUC of 1.00, 1.00, 0.773, 0.904, 1.00 and 0.992 in the external validation set.

Conclusion

PBRPs-based MLP-ANN model exhibited good performance in discriminating between UC and CD and revealing the disease activity; however, a larger sample size and more models need to be considered for further research.