In a peer-reviewed study published today Nature communicationFrench-American techbio Okin and a team of scientists from pathology labs in France present a blind validation of MSIntuit™ CRC, a first-in-class AI-powered digital pathology diagnostic developed by Okin, as a pre-screening tool that optimizes Aiming to improve the accuracy of diagnosis and treatment of colorectal cancer.
With nearly two million new cases and one million deaths worldwide in 2020, colorectal cancer is the third most common cancer worldwide and the second highest cause of cancer death.
Microsatellite instability (MSI) is a major genomic biomarker of colorectal cancer and represents 15% of the overall CRC population. Recent clinical trials have shown that the MSI phenotype has prognostic and therapeutic importance, particularly with the recent approval of immune checkpoint inhibitor (ICI) therapy. Patients whose tumors show MSI are thought to respond to ICI therapy and are recommended for it. Conversely, ICI is not routinely recommended for individuals with microsatellite stable (MSS) tumors. As a result, MSI testing is recommended by global consensus guidelines as a guide to optimal therapy.,,,
Prescreening tools that can eliminate the need to test all patients offer the opportunity to streamline the process and reduce pressure on laboratory personnel and resources.
Published in today’s study Nature communication revealed that MSIntuit CRC can correctly rule out approximately 50% of MSS patients, while correctly classifying more than 96% of MSI patients, equivalent to current gold standard methods (92–95%). Such new solutions pave the way for an optimized screening workflow to screen more patients faster.
“This new approach will have a direct impact on oncologist decision-making and help to quickly bring the best treatment to patients,” said Magali Savercek, international expert in GI pathology, professor at Saint Antoine Hospital, Sorbonne University, AP-HP, France and co-end of this publication. the writer “It could also optimize the cost and organization of MSI testing in pathology labs, especially for countries implementing universal MSI screening.”
Maryam Sefta, Chief Diagnostics Officer at OKIN, said,
“With increasing numbers of biomarkers routinely tested in clinical practice, the need for tools that can ease both the barriers and resource pressures when ramping up biomarker testing is paramount.”
“Our solution represents the first step toward developing an AI diagnostic that can identify actionable biomarkers from a single H&E slide used in clinical routine, pushing us closer to realizing a precision medicine future.”
A major strength of the study is the blind validation of the model of 600 consecutive CRC cases diagnosed in nine different pathology labs over a two-year period, thus reducing the risk of selection bias, thanks to Medipath, the largest pathology lab network in France. . This validation was also conducted across two different pathology slide scanners and performed consistently with sensitivities of 96% and 98%, respectively. These and other methodological approaches, such as emphasizing sensitivity and specificity as performance markers, demonstrate a commitment to the robustness of AI models, all with the intent of ensuring that diagnostics are appropriate for clinical settings and generalizable across labs and geographies.
The MSIntuit™ CRC diagnostic tool represents a pioneering achievement of OWKIN. It is driven by patient-derived data and is designed to benefit patients.
Sailard, C., etc (2023). Validation of MSIntuit as an AI-based pre-screening tool for detection of MSI from colorectal cancer histology slides. Nature communication. doi.org/10.1038/s41467-023-42453-6.