Summary:
PathAI’s AIM-MASH AI Assist has become the first AI-assisted pathology tool qualified by the EMA CHMP for histology-based enrollment and endpoint assessment in MASH clinical trials.

Takeaways:

  1. EMA Qualification: AIM-MASH AI Assist is now approved for use in MASH clinical trials to help assess liver biopsies.
  2. Improved Accuracy: The tool demonstrated non-inferiority to individual pathologists in fibrosis and steatosis grading, with superior performance in inflammation and ballooning assessment.
  3. Impact on Drug Development: Its standardization and efficiency can accelerate MASH research and the development of new treatments.

PathAI, a global leader in AI-powered pathology, today announced that the European Medicines Agency (EMA) Committee for Medicinal Products for Human Use (CHMP) has granted full qualification for AIM-MASH AI Assist1, (previously AIM-NASH) This marks a significant milestone as AIM-MASH AI Assist becomes the first and only AI-assisted pathology assessment tool qualified by the EMA CHMP for histology enrollment and primary or secondary endpoint assessment in clinical trials.

Can Be Used for MASH Clinical Trials

The EMA CHMP has determined that the proposed Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology (AIM-MASH) tool can be used in metabolic dysfunction associated steatohepatitis (MASH) clinical trials. Specifically, it will serve as an aid to trial pathologists in scoring liver biopsies at enrollment and follow-up visits. The tool is designed to assist a single central pathologist in evaluating patients for inclusion in clinical phase 2 and phase 3 trials in MASH, as well as for assessing study outcomes based on histological evaluation. 

“A robust, automated and highly standardized method to assess liver histological lesions will be a great help for the industry and drug development.” says Vlad Ratziu, MD, PhD, a professor of hepatology at the Sorbonne Université and the Hôpital Pitié-Salpêtrière Medical School in Paris, France.

AIM-MASH AI Assist Compared to Individual Pathologist Reads

The EMA qualification was in part based on an extensive clinical validation study2 comparing AIM-MASH AI Assist to individual pathologist reads, which demonstrated non-inferiority for the features of fibrosis grading and steatosis grade and superiority for lobular inflammation and hepatocellular ballooning.

This qualification signifies a major advancement in the field of MASH clinical trials, offering a more efficient, standardized, and reproducible approach to evaluating liver biopsies. The solution has the potential to accelerate the development of new treatments for MASH by providing accurate and consistent assessments, ultimately benefiting patients.

“We are thrilled to receive EMA qualification for AIM-MASH AI Assist,” says Andy Beck, CEO. “This achievement underscores our commitment to leveraging AI to transform pathology and improve patient outcomes. We believe that AIM-MASH AI Assist will play a crucial role in advancing MASH research and bringing much-needed therapies to patients.”

Key Highlights of AIM-MASH AI Assist:

  • First and only AI-assisted pathology assessment tool qualified by the EMA for histology enrollment and endpoint assessment in MASH clinical trials.
  • Enables assessment of primary or secondary endpoints based on histological evaluation that can be submitted to the EMA for conditional approval
  • Aids a single central pathologist in scoring liver biopsies at enrollment and follow-up visits and can be used in lieu of the current gold standard consensus reads of multiple pathologists.
  • Supports evaluation of patients for inclusion in phase 2 and phase 3 MASH clinical trials.
  • AIM-MASH AI Assist has been fully validated, ensuring accuracy and reliability in its assessments.2
  • Deployed on the AISight Clinical Trials Platform, providing a secure and efficient environment for implementing the AIM-MASH algorithm.

Featured Image: AIM-MASH AI Assist provides a robust, automated and highly standardized method to assess liver histological lesions. Photo: PathAI

References

  1. AIM-MASH AI Assist is for Research Use Only. Not for use in diagnostic procedures
  2. Pulaski, H., Harrison, S.A., Mehta, S.S. et al. Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis. Nat Med 31, 315–322 (2025).