A conceptual illustration of Fatty liver cells in the shape of a liver
Credit: KATERYNA KON/SCIENCE PHOTO LIBRARY/Getty Images

Artificial intelligence (AI)-focused digital pathology company PathAI and GlaxoSmithKline (GSK) today announced the two companies will partner to leverage PathAI’s technology to aid in the research and development of therapeutics for oncology and non-alcoholic steatohepatitis (NASH).

“GSK’s world-leading AI/ML capability, including our dedicated in-house hub in London, is applying a predictive and data-driven approach to drug discovery and clinical trials with the aim of improving the success rates of new medicines,” said Kim Branson, senior VP global head of Artificial Intelligence and Machine Learning at GSK in a press release. “We look forward to leveraging both PathAI’s expertise and models to advance GSK’s proprietary AI models and focus on designing better models to deliver improved treatment options for patients with cancer and NASH.”

The multi-year partnership that will leverage PathAI’s AIM-NASH tool comes five months after PathAI released results of a retrospective study of liver biopsy specimens from Bristol Myers Squibb’s FALCON 1 study, a Phase IIb, randomized, multicenter, placebo-controlled study assessing the efficacy and safety of pegbelfermin (PGBF) as a treatment for non-alcoholic steatohepatitis (NASH).

In that study, PathAI showed that post-hoc evaluation of liver biopsies from patients in the FALCON 1 study by AI-based histologic measurement of by its NASH drug development tool (DDT) suggests that clinical trial endpoints may have been met and shows treatment-associated improvements in key liver tissue features not identified by manual assessment.

Other work with pharmaceutical companies supporting the power of PathAI’s tissue analysis tools include it use in analyzing tissue to measure response in a clinical trial of Novo Nordisk’s drug candidate semaglutide, which showed a reduction of fibrosis using and AI-assessed continuous fibrosis score.

At the AASLD Liver Meeting 2021, the company also presented data showing that PathAI’s NASH histology scoring was concordant with the scoring done by a panel of three board-certified, expert hepatopathologists (who underwent proficiency training for NASH Clinical Research Network (CRN) scoring).

“In alignment with a recent FDA regulatory proposal recommending scoring of NASH histological trial endpoints by two hepatopathologists and a third for discordant cases, this study shows that panel scoring can support the reproducibility of NASH scoring and reduce bias, as demonstrated in biopsies obtained in a Phase III clinical trial. PathAI has curated a network of board-certified pathologists that is central to model training and development and the validation of PathAI’s AI-based drug development tools,” the company noted upon release of the result from the pilot study.

Now, the company will further strengthen its position with big pharma leveraging its AI-based tools for drug trials and development, while continuing to strengthen the platform’s performance.

“Our partnership will combine GSK and PathAI’s AI and platform engineering teams to scale algorithm development and enable the discovery of new insights that can be rapidly integrated into clinical trials,” said Andrew Beck, CEO and co-founder of PathAI. “With our combined efforts, we aim to harness the power of machine learning to predict which patients will benefit from therapies in key high need areas.”

Also of Interest