An AI-driven pre-screening test for colorectal cancer (CRC) treatment has taken a key step forward with a validation study, as reported in Nature Communications. Owkin’s MSIntuit test showed almost 99% sensitivity for detecting those patients most likely to respond to immunotherapy.
“Our solution represents the first step towards the development of an AI diagnostic that can identify actionable biomarkers from a single H&E [Hematoxylin and Eosin] slide used in clinical routine, pushing us closer to realizing a precision medicine future,” said Meriem Sefta, PhD, chief diagnostic officer at Owkin.
MSIntuit is Owkin’s CE-marked, AI-based, pre-screening tool for MSI detection from H&E stained slides. The test was developed as a pre-screening tool aimed at optimizing the precision of diagnosis and treatment of colorectal cancer.
With almost two million new cases and one million deaths worldwide in 2020, colorectal cancer is the third most common cancer globally and the second highest cause of cancer mortality.
Microsatellite Instability (MSI) is a key genomic biomarker in colorectal cancer and about 15% of the overall CRC population has this marker. Recent clinical trials have shown that MSI phenotype has both prognostic and therapeutic importance, especially with the recent approval of immune checkpoint inhibitor (ICI) therapies.
Patients whose tumors show MSI are considered more likely to respond to ICI therapy and are recommended for it. Conversely, ICI is not routinely recommended for those with tumors that are microsatellite stable (MSS). Many medical organizations such as the National Institute for Health and Care Excellence (NICE) and the National Comprehensive Cancer Network (NCCN), recommend universal screening for MSI status of all newly diagnosed CRC. Prescreening tools could streamline this process, reducing the pressure on laboratory staff and resources.
In this study, after training on samples from the Cancer Genome Atlas (TCGA), a blind validation was conducted on an independent dataset of 600 consecutive CRC patients, using two scanners. The test showed a sensitivity of 0.96–0.98m and specificity of 0.47–0.46.
“This new approach will have a direct impact on oncologist decision-making and help bring the best treatment to patients sooner,” stated Magali Svrcek, MD, PhD, an international expert in GI pathology, professor at Saint Antoine Hospital, Sorbonne Université, AP-HP, France, and a co-author of this publication. “It could also optimize costs and organization of MSI testing in pathology labs, especially for countries applying universal MSI screening.”
“With the increasing number of biomarkers to be routinely tested in clinical practice, the need for tools that can both ease bottleneck and resource pressures while ramping up biomarker testing is paramount,” said Sefta.
The company noted that a major strength of the study is the blind validation of the model on 600 consecutive CRC cases diagnosed across nine different pathology labs in the span of two years, thus reducing risk of selection bias, thanks to Medipath, the largest pathology lab network in France. This validation was also carried out across two different pathology slide scanners and performed consistently with a sensitivity of 96% and 98% respectively.