Non-invasive fibrosis markers can distinguish between liver fibrosis stages in lieu of liver biopsy or imaging elastography.
Dr Samer El-Kamary and colleagues from Maryland, USA developed a sensitive, non-invasive, freely-available algorithm that differentiates between individual liver fibrosis stages in chronic hepatitis C virus patients.
Chronic HCV patients at Cairo University Hospital, Egypt, with liver biopsy to determine fibrosis stage, were tested for preselected fibrosis markers.
The researh team undertook a novel multistage stepwise fibrosis classification algorithm using random forest analysis for biomarker selection, and logistic regression for modelling.
FibroSteps predicted fibrosis stage using 4 steps.
|The final classification had accuracies of 95% for the training sets|
Step 1 distinguished no/mild fibrosis vs. moderate/severe fibrosis/cirrhosis; whereas Step 2a distinguished F0 vs. F1.
Step 2b distinguished F2 vs. F3/F4, and Step 3 distinguished F3 vs. F4.
FibroSteps was developed using a randomly-selected training set and evaluated using the remaining patients as a validation set.
Hyaluronic Acid, TGF-β1, α2-macroglobulin, MMP-2, Apolipoprotein-A1, Urea, MMP-1, alpha-fetoprotein, haptoglobin, RBCs, haemoglobin and TIMP-1 were selected into the models.
The final classification had accuracies of 95%, and 89% for the training and validation sets respectively.
The research team concluded, "FibroSteps, a freely available, non-invasive liver fibrosis classification, is accurate and can assist clinicians in making prognostic and therapeutic decisions."
"The statistical code for FibroSteps using R software is provided in the supplementary materials."