Research Article: Supervised learning reveals circulating biomarker levels diagnostic of hepatocellular carcinoma in a clinically relevant model of non-alcoholic steatohepatitis; An OAD to NASH

Date Published: June 26, 2018

Publisher: Public Library of Science

Author(s): Anne Hwang, Christopher Shi, Edward Zhu, Farha Naaz, Ping Zhou, Zainab Rasheed, Michelle Liu, Lindsey S. Jung, Bin Duan, Jingsong Li, Kai Jiang, Latha Paka, Satishkumar V. Gadhiya, Dibyendu Dana, Quaisar Ali, Michael A. Yamin, Itzhak D. Goldberg, Prakash Narayan, Mahesh Narayan.


Although cirrhosis is a key risk factor for the development of hepatocellular carcinoma (HCC), mounting evidence indicates that in a subset of patients presenting with non-alcoholic steatohepatitis (NASH) HCC manifests in the absence of cirrhosis. Given the sheer size of the ongoing non-alcoholic fatty liver disease (NAFLD) epidemic and the dismal prognosis associated with late-stage primary liver cancer there is an urgent need for HCC surveillance in the NASH population. Using serum levels of HCC biomarkers as vectors and biopsy-proven HCC or no HCC as outputs / binary classifier, a supervised learning campaign was undertaken to develop a minimally invasive technique for making a diagnosis of HCC in a clinically relevant model of NASH. Adult mice randomized to control diet or a fast food diet (FFD) were followed for up to 14 mo and serum level of a panel of HCC-relevant biomarkers was compared with liver biopsies at 3 and 14 mo. Both NAFLD Activity Score (NAS) and hepatic hydroxyproline content were elevated at 3 and 14 mo on FFD. Picrosirius red staining of liver sections revealed a filigree pattern of fibrillar collagen deposition with no cirrhosis at 14 mo on FFD. Nevertheless, 46% of animals bore one or more tumors on their livers confirmed as HCC in hematoxylin-eosin-stained liver sections. In this training set, receiver operating characteristic (ROC) curves analysis for serum levels of the HCC biomarkers osteopontin (OPN), alpha-fetoprotein (AFP) and Dickkopf-1 (DKK1) returned concordance-statistic/area under ROC curve of ≥ 0.89. Serum levels of OPN (threshold, 218 ng/mL; sensitivity, 82%; specificity, 86%), AFP (136 ng/mL; 91%; 97%) and DKK1 (2.4 ng/mL; 82%; 81%) diagnostic for HCC were confirmed in a test set comprising mice on control diet or FFD and mice subjected to hepatic ischemia-reperfusion injury. These data suggest that levels of circulating OPN, AFP and DKK1 can be used to make a diagnosis of HCC in a clinically relevant model of NASH.

Partial Text

Given the diabetes, obesity and metabolic syndrome epidemics, non-alcoholic fatty liver disease (NAFLD) has reached epidemic proportions [1–3]. Left untreated, NAFLD, which starts as simple steatosis, can progress (Fig 1) to non-alcoholic steatohepatitis (NASH), NASH with increasing levels of fibrosis, cirrhosis and hepatocellular carcinoma, (HCC). Mounting evidence [4] suggests that NASH can also progress to HCC in the absence of cirrhosis (Fig 1). In fact, data from a number [4–9] of reports indicates that up to 50% of NASH patients presents with HCC without cirrhosis. Despite these emerging statistics and despite the fact that NASH patients routinely present for liver function tests, this cohort is not typically screened for HCC. Although liver biopsy followed by microscopic evaluation remains the gold standard for diagnosing HCC, ultrasonography with or without serum level of the HCC biomarker alpha-fetoprotein (AFP) is used to make a diagnosis [10, 11]. However, a major challenge associated with surveillance in patients with NASH is that obesity and visceral fat compromise the completeness of an ultrasound examination of the liver and conclusions from imaging data can be confounded by the presence of benign incidentelomas including hamartomas [8]. Use of a single biomarker such as AFP also carries the risk of misdiagnosis. Therapeutic strategy and prognosis with any cancer, especially HCC, is linked to early diagnosis; and accurate diagnosis is as important as early diagnosis.

In a murine model of FFD-induced NAFLD, animals developed NASH with increasing levels of fibrosis but not cirrhosis. By 14 mo on FFD, a large subset of animals exhibited HCC. Use of a supervised learning approach indicates that the serum HCC biomarkers OPN, AFP and DKK1 are excellent diagnostics for HCC in NASH with AUROCs of 0.97, 0.99 and 0.89, respectively, and thresholds of 136 ng/mL, 218 ng/mL and 2.4 ng/mL, respectively.

We have demonstrated for the first time a quantitative relationship between the levels of circulating biomarkers and HCC in a clinically relevant model of NASH without cirrhosis. Further development and clinical validation of this technology could potentially be used to facilitate early and accurate diagnosis of HCC in a burgeoning NASH population.




0 0 vote
Article Rating
Notify of
Inline Feedbacks
View all comments