News Article

PathAI and Bristol-Myers Squibb to Showcase Results From First AI-Powered Analysis of PD-L1 Expression Across Three Phase 3 Trials at SITC 2019

Boston, Massachusetts – PathAI, a global provider of artificial intelligence (AI)-powered technology for use in pathology research, today announced the results of a robust, retrospective analysis examining PD-L1 expression on tumor and immune cells from 1,079 patient samples across three randomized Phase 3 clinical trials evaluating Opdivo (nivolumab) in non-small cell lung cancer. The study found a strong correlation between AI-powered and manual quantification of PD-L1 across tumor cells, macrophages, lymphocytes and total immune cells. PathAI and Bristol-Myers Squibb will present these findings in an oral presentation at the 34th Annual Meeting & Pre-Conference Programs (SITC 2019) of the Society for Immunotherapy of Cancer from November 6–10 in National Harbor, Maryland.

In the study, after training a model with more than 250,000 pathologist-provided annotations using the PathAI research platform, algorithm analytic performance was assessed against a consensus of five pathologists. The AI-powered and manual approaches found similar associations between PD-L1 expression on tumor and immune cells and progression-free survival. The findings were based on the evaluation of three clinical trials (CheckMate -017 [n=167], CheckMate -026 [n=502], and CheckMate -057 [n=410]). Of note, composite PD-L1 expression on tumor cells plus macrophages did not show a stronger association with response compared with tumor cells alone. These results will be presented in Concurrent Session 307 on Saturday, November 9 at 4:45p ET (Presentation #O65).

“Together with partners like PathAI, Bristol-Myers Squibb’s translational scientists are tapping into the most advanced imaging, digital pathology and AI technologies available in order to accelerate research – at scale – that can help predict patient outcomes more quickly and accurately,” said Saurabh Saha, M.D., Ph.D., senior vice president, global head of translational medicine at Bristol-Myers Squibb. “The combination of our unique expertise and sophisticated capabilities enables us to explore biological insights in real-time and translate them into meaningful learnings that fuel our R&D organization.”

In a related analysis, PathAI and Bristol-Myers Squibb researchers retrospectively examined samples from 293 patients across two clinical trials of Opdivo in advanced urothelial cancer. The AI-powered PD-L1 assessment showed a significantly stronger correlation with the reference standard (consensus of five pathologist PD-L1 positivity scores) compared with the individual pathologist scores for quantifying PD-L1 expression in lymphocytes (r=0.744 vs 0.598) and macrophages (r= 0.68 vs 0.287). In assessing PD-L1 positivity on tumor cells, there was no difference between the PathAI platform and the individual pathologist scores versus the reference standard (r=0.837 vs 0.857), demonstrating the PathAI platform performed similar to or better than pathologist-based scoring in all cell types tested, and especially for immune cells where manual correlation is known to be low. These results will be reported in a poster presentation on Saturday, November 9 from 7a–8p (Presentation #P730).

“In both studies, we put our process up against a very rigorous and high-quality benchmark,” said Andy Beck, co-founder and CEO at PathAI and an author on both studies. “We’re pleased to see that the PathAI approach performed well, demonstrating performance at the level of board-certified pathologists exhaustively labeling cells by hand across the board.”

The results of these robust analyses show the predictive promise of AI and suggest a benefit from the reliable and reproducible nature of AI-powered pathology interpretation in immuno-oncology, as assessing PD-L1 expression on immune cells by traditional approaches can be challenging. “We hope to be able to offer results to every patient that reflect the rigor and reliability of a five-pathologist panel, delivering a level of quality that cannot yet be provided at scale today,” said Beck. “This research shows that such a future may not be so far off after all.”

About PathAI

Bristol-Myers Squibb is a global biopharmaceutical company whose mission is to discover, develop and deliver innovative medicines that help patients prevail over serious diseases. For more information about Bristol-Myers Squibb, visit us at or follow us on LinkedIn, Twitter, YouTube, Facebook, Instagram.