PathAI Diagnostics, a leading laboratory services company, unveiled an AI-Assisted laboratory developed test (LDT) for the histologic scoring and staging of metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic dysfunction-associated steatohepatitis (MASH). 

This advancement was introduced at the American College of Gastroenterology 2023 (ACG2023) Meeting in Vancouver, Canada, from October 20-25.

MASLD and MASH are posing an escalating healthcare challenge, affecting millions of individuals worldwide. Recent estimates suggest that approximately 37.8% of the global adult population suffers from some form of MASLD, with 5-6% of the U.S. adult population at risk of progressing to MASH—a potential precursor to severe conditions such as cirrhosis and liver cancer.(1-3)

MASLD and MASH Diagnostics

While the gold standard for MASLD/MASH scoring is liver biopsy, the scoring provided by pathologists can exhibit variability.(4-5) In fact, there can be as much as a 30% disagreement in MASH diagnosis between pathologists, and intra-observer variability can reach up to 41% for the same case.(6) Accurate scoring and staging are paramount, as each fibrosis stage corresponds to approximately a two-fold increase in liver-related mortality.(7)

In order to better tackle this growing issue, PathAI Diagnostics developed AI.Dx MASH, an LDT, which provides AI-assisted histologic scoring that supports expert pathologists with enhanced insights for liver biopsy reporting. “We are excited to bring the world’s first AI-assisted Laboratory Developed Test for MASH to market,” says Jim Sweeney, president of PathAI Diagnostics. “The tool uses our deep expertise in AI-powered pathology coupled with our world-class diagnostics laboratory to improve patient outcomes through AI-assisted histologic scoring for MASH.”

This tool utilizes an AI algorithm that has been proven to significantly reduce inter- and intra-operator variability in CRN scoring. Moreover, AI.Dx MASH reports include image overlays and quantitation, offering a comprehensive view of steatosis, lobular inflammation, hepatocyte ballooning, and fibrosis, thus facilitating more accurate diagnosis and staging.(8-11)

Further reading: Normal Gastrointestinal Biopsy Not Protective Against Later IBD

“AI.Dx MASH provides a powerful tool for histologic MASH scoring by offering visual image overlays of key features to show how a score was reached,” says R. Shawn Kinsey, MD, gastrointestinal and hepatobiliary pathologist at PathAI Diagnostics. “This addresses one of the key challenges that leads to variability when assessing progression of the disease for a more accurate summary of a patient’s condition to inform future treatment and intervention.”

References:

  1. Riazi K, et al. The prevalence and incidence of NAFLD worldwide: a systematic review and meta-analysis. The Lancet. 2022;7(9):851-861.
  2. Estes C, et al. Modeling the epidemic of nonalcoholic fatty liver disease demonstrates an exponential increase in the burden of disease. Hepatology. 2018;67(1):123-133.
  3. Diehl AM, Day C. Cause, pathogenesis, and treatment of nonalcoholic steatohepatitis. N Engl J Med. 2017;377(21):2063-2072.
  4. Berger D, et al. Con: Liver Biopsy Remains the Gold Standard to Evaluate Fibrosis in Patients With Nonalcoholic Fatty Liver Disease. Clin Liver Dis (Hoboken). 2019 Apr;13(4):114–116.
  5. Arab JP, et al. The evolving role of liver biopsy in non-alcoholic fatty liver disease. Annals of Hepatology (2018);17(6):899-902.
  6. Davison B, et al. Suboptimal reliability of liver biopsy evaluation has implications for randomized clinical trials. J Hepatol (2020);73(6):1322-1332.
  7. Taylor RS, et al. Association Between Fibrosis Stage and Outcomes of Patients With Nonalcoholic Fatty Liver Disease: A Systematic Review and Meta-Analysis. Gastroenterology. 2020;158:1611-1625.
  8. Pokkala H, et al. Machine Learning Models Identify Novel Histologic Features Predictive of Clinical Disease Progression in Patients With Advanced Fibrosis Due to Nonalcoholic Steatohepatitis. EASL ILC 2020 Poster 2497.
  9. Carrasco-Zevallos O, et al. AI-based histologic measurement of NASH (AIM-NASH): A drug development tool for assessing clinical trial endpoints, EASL 2021 Abstract 1611.
  10. Harrison SA, et al. Analytical and Clinical Validation of AIM-NASH a Digital Pathology Tool for Artificial Intelligence-based Measurement of Nonalcoholic Steatohepatitis Histology. EASL 2023.
  11. Loomba R, et al. Comparison of the effects of semaglutide on liver histology in patients with non-alcoholic steatohepatitis cirrhosis between machine learning model assessment and pathologist evaluation. Poster AASID 2022.