Risk prediction modelling is important to better understand the determinants of the course and outcome of PBC and to inform the risk across the disease continuum in PBC enabling risk-stratified follow-up care and personalised therapy. Current prognostic models in PBC are based on treatment response to ursodeoxycholic acid because of the well-established relationship between alkaline phosphatase on treatment and long-term outcome. In addition, serum alkaline phosphatase correlates with ductular reaction and biliary metaplasia, which are hallmark of biliary injury. Considering the waiting time for treatment failure in high-risk patients is not inconsequential, efforts are focused on bringing forward risk stratification at diagnosis by predicting treatment response at onset. There is a need for better prognostic variables that are central to the disease process. We should take an integrative approach that incorporates multiple layers of information including genetic and environmental influences, host characteristics, clinical data, and molecular alterations for risk assessments. Biomarker discovery has an accelerated pace taking advantage of the emergence of large-scale omics platforms (genomics, epigenomics, transcriptomics, proteomics, metabolomics, and others) and whole-genome sequencing. In the digital era, applications of artificial intelligence, such as machine learning, can support the computing power required to analyse the vast amount of data produced by omics. The information is then used for the development of personalised risk prediction models that through clinical trials and hopefully industry partnerships can guide risk management strategies. We are facing an unprecedented opportunity for the integration of molecular diagnostics into the clinic, which promotes progress toward the personalised management of patients with PBC.
Keywords: Alkaline phosphatase; Personalised medicine; Primary biliary cholangitis; Prognostic models; Risk prediction.
Copyright © 2018 Elsevier Ltd. All rights reserved.