Modella AI, the 'ChatGPT of Pathology,' Partners with AstraZeneca and Files IPO Prospectus Following Nature-Published 89.5% Diagnostic Accuracy

Jul 04, 2025 18:34 CST Updated 18:34

Modella AI

Developer of Artificial Intelligence Technology in Biomedicine

AstraZeneca

Biopharmaceutical Manufacturer

Recently, AI medical startupsModella AIAnnounces Multi-Year Agreement with AstraZeneca

According to the agreement, Modella AI will provide AstraZeneca with access to its multimodal AI foundational model to accelerate the clinical development of AstraZeneca's global oncology portfolio.

Notably, the company isDerived from the Mahmood Lab at Harvard Medical School and Brigham and Women's Hospital, Massachusetts General Hospital.The multimodal generative AI model PathChat was once published in the prestigious international journal Nature.

Because when providing useful clinical contextAccuracy increased to 89.5%, once caused a stir in the industry and was calledThe ChatGPT of the pathology world, and this time withThe PathChat 2, which AstraZeneca collaborates on, is precisely the upgraded version of this model.

The World's FirstGranted FDA Breakthrough Device Designation

Modella AI was founded inIn 2024, committed toDevelop generative and agent-based AI to advance healthcare, with a particular focus on the field of AI pathology.

In terms of the team,President, Co-founder and Chief Executive Officer isOnce served as the leader in AI healthcarePaige AIPresident'sDr. Jill Stefanelli,

Product MatrixThe array mainly consists of two parts.First, there is PathChat mentioned above. The company's generative AI pathology diagnostic assistant, PathChat DX, has received the Breakthrough Device Designation from the US FDA.The World's First Generative AI-Based Human Pathology Diagnostic Assistance Tool。

In addition, there is another set named Judith.AI Agent, used for automating AI model development for biomedical image analysis and scientific discovery, with applications coveringFrom cell and tissue segmentation in gigapixel pathology images to biomarker discovery using the latest foundational models.

Recommended Reading