The landscape of Metabolic Dysfunction-Associated Steatohepatitis (MASH) treatment is at a critical juncture. With only two approved drugs currently on the market and an ever-expanding patient population, the need for robust, efficient, and reliable clinical trials is more urgent than ever.
PathAI is meeting this challenge head-on, establishing itself as the premier, industry-leading MASH Center of Histology Excellence to streamline drug development and provide the high-quality data necessary to bring new therapies to patients.
The MASH Histology Challenge in Clinical Trials
Histologic assessment remains the gold standard for MASH clinical trial enrollment and primary endpoint assessment for accelerated approval by the FDA and conditional approval by EMA. As part of this process, pathologists evaluate liver biopsies for the severity of MASH cardinal CRN features – steatosis, hepatocellular ballooning, lobular inflammation, and fibrosis.
However, this process has led to challenges in the field:
Logistics: Manual reads of glass histology slides require the shipment of these samples between contract research laboratories and pathologists, slowing the evaluation process and introducing the risk of specimen damage or loss.
Reliability and Variability: Inter- and intra-reader variability for scoring cardinal MASH CRN features can introduce noise into the data, complicating clinical trials from enrollment through endpoint assessment:
- Screen failures: For trial enrollment, participants must have biopsy-confirmed fibrotic MASH (i.e. MASLD activity score >4, fibrosis stage >2). Manual scoring variability hinders the precise identification of eligible trial participants, contributing to reported screen failure rates of 69-87% [1-3]. This high rate of screen failures increases both the cost and time required for trial recruitment.
- Endpoint assessment: The conditional and accelerated approval processes of the European Medicines Agency and United States Food and Drug Administration, respectively, depend on meeting predefined histologic endpoints. The variability in manual histologic assessment of MASH specimens carries the risk that true histologic changes will be masked.
Together, these challenges complicate planning for clinical trials in MASH, including for cross-phase studies or designing monotherapy to combination therapy trials (e.g., Phase 3 planning).
PathAI’s Solution: End-to-End Excellence
PathAI delivers an integrated, validated, and efficient solution that addresses the MASH histology challenges from the point of sample preparation through AI-assisted or manual assessments and ultimately to regulatory submission (Figure 1). We provide everything needed in one place to support data integrity and efficiency.
Figure 1. End-to-end solutions for liver histology available through PathAI and our Biopharma laboratory.
Unparalleled Histology Expertise
PathAI's platform and team offer a comprehensive approach:
- End-to-End Histology Expertise: PathAI and our Biopharma laboratory [4] have complete oversight and deep domain knowledge across the entire histology workflow, from sample receipt and preparation through slide digitization and evaluation.
- MASH Pathology Expertise and Consensus Methods: Our team includes in-house MASH pathology experts and is powered by a network of experienced MASH pathologists, utilizing validated training and consensus methods to ensure the highest quality reads.
- Validated Platform for Reads: Our GCP/GCLP compliant 21 CFR Part 11 AISight Clinical Trials (CT)* image management system supports both manual pathologist evaluation and AI-powered histology assessments and has been specifically validated for MASH scoring. Use of this platform allows clinical trial specimens to be evaluated by expert pathologists regardless of location, streamlining and derisking the histologic evaluation process.
- Industry-leading turnaround times without compromise: We prioritize rapid 4-7 day turnaround times from the point of query resolution for histology reads from sample receipt to scoring, leading to efficient trial enrollment assessment and timely endpoint readouts, all while maintaining strict quality standards.
Driving Reliability and Insights with AI-powered digital pathology
The core of PathAI's excellence lies in the integration of AI-powered digital pathology tools (Figure 2) into the histologic evaluation process:
- Reliable and Validated AI-Based Scoring: The EMA- and FDA-qualified [5,6] AIM-MASH AI Assist# tool has been rigorously validated [7] for histology-based enrollment and primary endpoint assessment in Phase 2 and 3 clinical trials. This tool, which is integrated into the AISight CT platform, reduces trial inter- and intra-reader variability. Retrospective analysis of the WAYFIND clinical trial using AIM-MASH AI Assist demonstrated that the trial, which did not meet its primary endpoint by manual pathologist assessment, would have met this primary endpoint if the study design had incorporated the validated AIM-MASH AI Assist read workflow [6,8,9].
- Granular Histologic Insights: In addition to AIM-MASH AI Assist, PathAI offers two additional AI-powered digital pathology tools within the AISight CT platform to gain more nuanced insights into MASH specimens. AIM-MASH+* [10] and LiverExplore* [11-13] provide MASH CRN-based continuous histology scores and quantitative fibrosis and liver microarchitecture insights, respectively. Data from these models have strong potential to provide critical mechanism of action (MOA)-based evidence to support primary and secondary endpoints and accelerate biomarker discovery.
Figure 2: PathAI’s suite of AI-powered liver histology solutions.
Driving Reliability and Insights with AI-powered digital pathology
Beyond our histology and digital pathology expertise our team has been thoughtfully assembled to offer the crucial experience necessary to navigate the complex regulatory landscape:
- Clinical and Regulatory Experience: PathAI’s team has deep MASH clinical and regulatory experience, including successful interactions with both the FDA and EMA.
- Global Enrollment Solutions: PathAI provides integrated solutions for trial enrollment and histology endpoint assessment in patients from China, backed by direct experience with HGRAC submission.
By combining deep MASH pathology expertise with a thoroughly validated, EMA- and FDA-qualified tool such as AIM-MASH AI Assist, AI-powered exploratory insights, and comprehensive regulatory experience, PathAI is the trusted partner for sponsors seeking to de-risk their clinical trials and accelerate the development of life-changing MASH therapies.
To learn more about how PathAI can optimize the histology readouts in your MASH trial, visit our website.
*AISight CT, AIM-MASH+, and LiverExplore are For Research Use Only. Not for use in diagnostic procedures.
#AIM-MASH AI Assist is qualified as a tool in the EU and as a DDT in the US for use in MASH clinical trials. AIM-MASH AI Assist is not for use in diagnostic procedures.
- Newsome PN, Buchholtz K, Cusi K, Linder M, Okanoue T, Ratziu V, et al. A placebo-controlled trial of subcutaneous semaglutide in nonalcoholic steatohepatitis. N Engl J Med. 2020;384:1113–24.
- Francque SM, Bedossa P, Ratziu V, Anstee QM, Bugianesi E, Sanyal AJ, et al. A randomized, controlled trial of the pan-PPAR agonist lanifibranor in NASH. N Engl J Med. 2021;385:1547–58.
- Vuppalanchi R, Loomba R, Sanyal AJ, Nikooie A, Tang Y, Robins DA, et al. Randomised clinical trial: Design of the SYNERGY-NASH phase 2b trial to evaluate tirzepatide as a treatment for metabolic dysfunction-associated steatohepatitis and modification of screening strategy to reduce screen failures. Aliment Pharmacol Ther. 2024;60:17–32.
- Precision at Every Step: PathAI's End-to-End Workflow for Celiac Disease Clinical Trials
- European Medicines Agency (EMA). Qualification Opinion — Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology in Liver Biopsies to Determine Disease Activity in NASH/MASH Clinical Trials. EMA/CHMP; 2025.
- FDA Qualifies First AI Drug Development Tool, Will Be Used in 'MASH' Clinical Trials
- Pulaski H, Harrison SA, Mehta SS, Sanyal AJ, Vitali MC, Manigat LC, et al. Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis. Nature Medicine. 2025;31:315–322. doi:10.1038/s41591-024-03301-2.
- Alkhouri N, et al. A Randomized, Placebo-Controlled, Phase 2 Study of the Safety and Efficacy of Combination Treatment with Semaglutide, Cilofexor and Firsocostat in Patients With Compensated Cirrhosis Due to Metabolic Dysfunction-Associated Steatohepatitis (WAYFIND). Hepatology. 2025; 82(S1):S131-S133
- A New Path Forward: How PathAI's FDA-Qualified AIM-MASH AI Assist Can Redefine MASH Clinical Trials
- Iyer JS, Juyal D, Le Q, Shanis Z, et al. AI-based automation of enrollment criteria and endpoint assessment in clinical trials in liver diseases. Nature Medicine. 2024; 30:2914-2923.
- Stanford-Moore A, Patel N, Gerardin Y, et al. Comprehensive characterization of granular fibrotic and cellular features in liver tissue enabled by deep learning models. medRxiv. 2025; 2025.06.12.25328580.
- The Power of LiverExplore: Quantifying Fibrosis with Unprecedented Precision
- Realizing the Power of LiverExplore: Measuring therapeutic-driven fibrosis reductions in patients with MASH
Written by Jackie Brosnan-Cashman PhD Senior Scientific Writer and Christina Jayson PhD Director of AI Product and Translational Research at PathAI