H&E-based MSI/MMR testing with AI in colorectal cancer: a multi-centred blinded evaluation

Bass, Cher, Ntelemis, Foivos, Schmidt, Julian, Wolf, Steffen, Geraldes, André, Mehrotra, Debapriya, Singhal, Shikha, Kumar, Narender, Marcia, Angelica, Bennett, Nicholas, Maiques, Oscar, Hyde, Mitchell, Mistry, Bejal, Rogerson, Grace, Cummings, Michele, Freer, Clare, Walsh, Elizabeth, Salto-Tellez, Manuel, Loughrey, Maurice, Um, In Hwa, Harrison, David J, Clarkson, Richard ORCID: https://orcid.org/0000-0001-7389-8673, Blackwood, James, Barrett, J Carl, Kather, Jakob Nikolas, Orsi, Nicolas M, Pandya, Pahini and Arslan, Salim 2025. H&E-based MSI/MMR testing with AI in colorectal cancer: a multi-centred blinded evaluation. npj Digital Medicine 10.1038/s41746-025-02218-5

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution. Download (44MB)

Abstract

Mismatch repair (MMR) deficiency occurs in 10-20% of colorectal cancer (CRC) cases, leading to microsatellite instability (MSI). Although MSI/MMR testing is critical for CRC management, high costs and long turnaround times limit testing rates and clinical utility, highlighting the need for more accessible, cost-effective alternatives. PANProfiler Colorectal (PPC) is an artificial intelligence (AI)-based biomarker test that determines MSI/MMR status directly from haematoxylin and eosin (H&E)-stained slides. We conducted a blinded, multi-centred validation to assess PPC's performance against standard testing. The study included 3,576 whole slide images from 1,243 CRC patients across three United Kingdom institutions. PPC produced definitive results for 86.55% of slides, achieving an overall agreement of 93.83%, positive agreement of 92.54%, and negative agreement of 94.02%. PPC accurately determined MSI/MMR status from routine H&E slides, offering a rapid, scalable alternative to conventional diagnostic methods.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Biosciences
Publisher:	Nature Research
Date of First Compliant Deposit:	8 January 2026
Date of Acceptance:	24 November 2025
Last Modified:	08 Jan 2026 12:00
URI:	https://orca.cardiff.ac.uk/id/eprint/183724

Actions (repository staff only)

Edit Item