Proteomics data in real-world MASLD cohorts illuminates epidermal growth factor-like 7 as a novel biomarker that is associated with advanced fibrosis and mortality
Heather Collis, Clinical Pharmacology and Quantitative Pharmacology, Clinical Pharmacology & Safety Sciences, R&D, AstraZeneca, Gothenburg, Sweden
Heather is a fellow of the AstraZeneca Postdoc Programme. She joined AstraZeneca in January 2023, working from the Cambridge site in the UK before moving to the Gothenburg site in Sweden in June 2023. She obtained a PhD in Mathematics from the University of Nottingham where her work focused on understanding the dynamics of hormone transport in the vasculature of young plants. At AstraZeneca, her focus has shifted towards using machine learning in order to model disease progression of MASLD (metabolic dysfunction-associated steatotic liver disease).
Webinar Recording
Metabolic dysfunction-associated steatotic liver disease (MASLD) is a major cause of liver-related morbidity and mortality world-wide. MASLD is formally diagnosed with liver biopsy and disease progression is highly heterogenous and remains poorly understood. Currently, hepatic fibrosis stage is the best predictor for the development of liver-related outcomes and overall mortality. Liver biopsy is an invasive procedure that comes with high costs and risk of complications. As such, non-invasive assessment of fibrosis stage is a key step in the management of patients with MASLD. Here, we show that epidermal growth factor-like 7 (EGFL7) is a potential novel biomarker for advanced fibrosis and mortality in MASLD patients.
We studied a MASLD clinical cohort (87 patients) which included data for more than 1000 biomarkers. We developed a random forest pipeline aiming to reduce the number of biomarkers of interest in the dataset. The top ranked biomarker by Boruta features selection was EGFL7. We show that EGFL7 outperforms the FIB-4 score (the most used non-invasive test for assessing fibrosis) by achieving comparable accuracy results while leaving no patient unclassified (FIB-4 leaves 43% of patients in this cohort unclassified). Further, we explored EGFL7’s potential as a novel disease marker by assessing its prognostic capabilities in the UK Biobank. We show that elevated levels of plasma EGFL7 is predictive of all-cause mortality in a MASLD population. Our results highlight that EGFL7 can be a beneficial addition to existing patient risk stratification guidelines or clinical trial inclusion/exclusion criteria.