An imaging-based artificial intelligence model for non-invasive grading of hepatic venous pressure gradient in cirrhotic portal hypertension

Cell Rep Med. 2022 Mar 15;3(3):100563. doi: 10.1016/j.xcrm.2022.100563.

Abstract

The hepatic venous pressure gradient (HVPG) is the gold standard for cirrhotic portal hypertension (PHT), but it is invasive and specialized. Alternative non-invasive techniques are needed to assess the hepatic venous pressure gradient (HVPG). Here, we develop an auto-machine-learning CT radiomics HVPG quantitative model (aHVPG), and then we validate the model in internal and external test datasets by the area under the receiver operating characteristic curves (AUCs) for HVPG stages (≥10, ≥12, ≥16, and ≥20 mm Hg) and compare the model with imaging- and serum-based tools. The final aHVPG model achieves AUCs over 0.80 and outperforms other non-invasive tools for assessing HVPG. The model shows performance improvement in identifying the severity of PHT, which may help non-invasive HVPG primary prophylaxis when transjugular HVPG measurements are not available.

Keywords: CHESS; CT; HVPG; cirrhosis; deep learning; machine learning; noninvasive tool; portal hypertension.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Artificial Intelligence*
  • Diagnostic Imaging
  • Humans
  • Hypertension, Portal* / diagnostic imaging
  • Liver Cirrhosis / complications
  • Portal Pressure