Retrospective AI-based measurement of NASH histology (AIM-NASH) analysis of biopsies from Phase 2 study of Resmetirom confirms significant treatment-induced changes in histologic features of non-alcoholic steatohepatitis

Harrison, Stephen A.; Iyer, Janani; Biddle-Snead, Charles; Hoffman, Sara; Le, Quang Bao; Mountain, Victoria; Resnick, Murray B.; Wack, Katy; Hennan, Jim; Taub, Rebecca

doi:10.1016/s0168-8278(22)01740-8

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This agreement was lower than has been observed between liver pathology experts, who had moderate-to-excellent agreement for the stage of fibrosis, steatosis, and hepatocyte ballooning, reflecting the consistency of assessment when performed by experienced pathologists 1,3,15,18 . The agreement in this analysis is also lower than the agreement measured for the same AI algorithms against pathologist consensus scoring in other clinical trial settings 19 . The higher variability between ML and pathologists in this study may be a result of multiple different factors, including the different analysis methods used by ML and pathologists to assess the histological features, and the quality of the slides impacting both ML and pathologist assessment.…”

Section: Discussioncontrasting

confidence: 67%

“… 1 , 3 , 15 , 18 The agreement in this analysis is also lower than the agreement measured for the same AI algorithms against pathologist consensus scoring in other clinical trial settings. 19 The higher variability between ML and pathologists in this study may be a result of multiple different factors, including the different analysis methods used by ML and pathologists to assess the histological features, and the quality of the slides impacting both ML and pathologist assessment. Generally, the ML-derived categorical assessment tended to assess the baseline fibrosis stage and the grades for steatosis, lobular inflammation, and hepatocyte ballooning higher than the pathologists’ scores at baseline.…”

Section: Discussionmentioning

confidence: 93%

See 1 more Smart Citation

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

Ratziu,

Francque,

Behling

et al. 2023

Hepatology

View full text Add to dashboard Cite

Background and Aims: Artificial intelligence-powered digital pathology offers the potential to quantify histologic findings in a reproducible way. This analysis compares the evaluation of histological features of non-alcoholic steatohepatitis (NASH) between pathologists and a machine learning (ML) pathology model. Approach and Results: This post hoc analysis included data from a subset of patients (N=251) with biopsy-confirmed NASH and fibrosis stage F1–F3 from a 72-week randomised placebo-controlled trial of once-daily subcutaneous semaglutide 0.1, 0.2, or 0.4 mg (NCT02970942). Biopsies at baseline and week 72 were read by two pathologists. Digitised biopsy slides were evaluated by PathAI’s NASH ML models to quantify changes in fibrosis, steatosis, inflammation, and hepatocyte ballooning using categorical assessments and continuous scores. Pathologist and ML-derived categorical assessments detected a significantly greater percentage of patients achieving the primary endpoint of NASH resolution without worsening of fibrosis with semaglutide 0.4 mg vs placebo (pathologist 58.5% vs 22.0%, p <0.0001; ML 36.9% vs 11.9%; p=0.0015). Both methods detected a higher but non-significant percentage of patients on semaglutide 0.4 mg vs placebo achieving the secondary endpoint of liver fibrosis improvement without NASH worsening. ML continuous scores detected significant treatment-induced responses in histologic features, including a quantitative reduction in fibrosis with semaglutide 0.4 mg vs placebo (p=0.0099) that could not be detected using pathologist or ML categorical assessment. Conclusions: ML categorical assessments reproduced pathologists’ results of histological improvement with semaglutide for steatosis and disease activity. ML-based continuous scores demonstrated an antifibrotic effect not measured by conventional histopathology.

show abstract

Section: Discussioncontrasting

confidence: 67%

Section: Discussionmentioning

confidence: 93%

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

Ratziu,

Francque,

Behling

et al. 2023

Hepatology

View full text Add to dashboard Cite

show abstract

“…In addition, the AIM-NASH algorithm alone has also demonstrated to either recapitulate or demonstrate that primary efficacy results were met across several trials and drug candidates (semaglutide, pegbelfermin, resmetirom [25][26][27][28]). In a phase 2b study for pegbelfermin AIM-NASH revealed a statistically significant difference in the proportion of primary endpoint responders in treatment vs. placebo groups, whereas the central pathologist scoring did not reveal a statistically significant difference [26].…”

Section: Discussionmentioning

confidence: 99%

“…In a phase 2b study for pegbelfermin AIM-NASH revealed a statistically significant difference in the proportion of primary endpoint responders in treatment vs. placebo groups, whereas the central pathologist scoring did not reveal a statistically significant difference [26]. In a phase 2b study for resmetirom, all endpoints met via both individual manual readers were also met by AIM-NASH [27]. In the phase 3 study for resmetirom, for both MASH resolution and fibrosis improvement endpoint, the percentage of patients that responded were comparable when assessed by AIM-NASH or manual pathology assessment [28].…”

Section: Discussionmentioning

confidence: 99%

Analytical and Clinical Validation of AIM-NASH: A Digital Pathology Tool for Artificial Intelligence-based Measurement of Nonalcoholic Steatohepatitis Histology

Pulaski,

Harrison,

Mehta

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Metabolic-dysfunction associated steatohepatitis (MASH) is a major cause of liver-related morbidity and mortality, yet treatment options are limited. Manual scoring of liver biopsies, currently the gold standard for clinical trial enrollment and endpoint assessment, suffers from high reader variability. This study represents the most comprehensive multi-site analytical and clinical validation of an AI-based pathology system, Artificial Intelligence-based Measurement of Nonalcoholic Steatohepatitis (AIM-NASH), to assist pathologists in MASH trial histology scoring. AIM-NASH demonstrated high repeatability and reproducibility compared to manual scoring. AIM-NASH-assisted reads by expert MASH pathologists were superior to unassisted reads in accurately assessing inflammation, ballooning, NAS >= 4 with >=1 in each score category, and MASH resolution, while maintaining non-inferiority in steatosis and fibrosis assessment. These findings suggest AIM-NASH could mitigate reader variability, providing a more reliable assessment of therapeutics in MASH clinical trials.

show abstract

Artificial intelligence-assisted digital pathology for non-alcoholic steatohepatitis: current status and future directions

Ratziu,

Hompesch,

Petitjean

et al. 2024

Journal of Hepatology

View full text Add to dashboard Cite

Retrospective AI-based measurement of NASH histology (AIM-NASH) analysis of biopsies from Phase 2 study of Resmetirom confirms significant treatment-induced changes in histologic features of non-alcoholic steatohepatitis

Cited by 4 publications

References 0 publications

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

Analytical and Clinical Validation of AIM-NASH: A Digital Pathology Tool for Artificial Intelligence-based Measurement of Nonalcoholic Steatohepatitis Histology

Artificial intelligence-assisted digital pathology for non-alcoholic steatohepatitis: current status and future directions

Contact Info

Product

Resources

About