The summaries are free for public
use. The Chronic Liver Disease
Foundation will continue to add and
archive summaries of articles deemed
relevant to CLDF by the Board of
Trustees and its Advisors.
Abstract Details
Artificial Intelligence in NASH Histology: Human Teaches a Machine for the Machine to help Humans
Hepatology. 2021 Feb 26. doi: 10.1002/hep.31777. Online ahead of print.
Mazen Noureddin1234
Author information
1Karsh Division of Gastroenterology and Hepatology, California, USA.
2Department of Medicine, Los Angeles, California, USA.
3Comprehensive Transplant Center, Los Angeles, California, USA.
4Cedars-Sinai Medical Center, Los Angeles, California, USA.
Abstract
With the high prevalence of non-alcoholic steatohepatitis (NASH) and its related morbidity, innovate and effective treatments for the disease have been needed. Fortunately, a plethora of clinical trials have been conducted, and many more are on the way (1). Nevertheless, the clinical trials pathway has been associated with limited success and many failures (1). Although non-invasive tests have shown promise and potential to replace liver biopsy, liver histology likely will remain the primary end point for phase 2b/3 trials and a key regulatory approval criterion for NASH drugs in the next few years (1). Unfortunately, histological evaluation of liver tissue has well-known limitations -- sample variability, lack of patient acceptance, low reproducibility among readers, and variable placebo effects -- that have been troublesome in NASH trials, although measures can be taken to reduce the shortcomings of this imperfect gold standard (2).