BOSTON--(BUSINESS WIRE)--PathAI, a global leader in AI-powered pathology, today announced it will present three presentations at this year's International Liver Congress (ILC) in London. The abstracts detail a novel machine learning-enabled continuous scoring system for nonalcoholic steatohepatitis (NASH) that allows for both nuanced analysis of treatment efficacy and capabilities to predict disease progression in patients with advanced fibrosis due to NASH. Further, the research details a novel method to image fibrosis in liver biopsy slides, potentially eliminating the second set of trichrome stain slides that historically have been required.
“Until now, no one has a proven method for quantifying subtleties in fibrosis progression, nor a way to predict that progression reliably,” said Andy Beck, CEO and Co-founder of PathAI. “We are excited to discuss these findings at ILC and explore the implications for advancing the standard of care for fibrosis treatment.”
The first abstract demonstrates the utility of AI Measured (AIM)-NASH by PathAI, a tool for scoring NASH histology in a retrospective analysis of liver biopsies from the Phase 2 trial of resmetirom. All biopsy-based endpoints that were evaluated via manual histologic scoring were also analyzed by AIM-NASH. Standard histologic assessment of fibrosis labels patients with scores of 1 to 4, much like labels for the stages of cancer. PathAI developed a novel continuous scoring system to allow for more nuanced analysis of a given treatment’s efficacy, such as 3.6 or 2.4. Analysis of these continuous scores revealed a statistically significant increase in NASH resolution and a greater reduction in fibrosis in treated versus placebo subjects.
“Previously studies would score patients at the onset and culmination of a study using a standardized ordinal scale. However, such scoring misses nuanced improvements that our continuous scoring system brings to light,” said Dr. Mike Montalto, Chief Scientific Officer at PathAI. “For example, a patient may start at 3.8, but be a 3.2 by the end of the study, pointing to benefits of the treatment that traditional scoring would have missed by labeling the patient a 3 at both the start and endpoint.”
The second abstract accepted at ILC dovetails with the first abstract and details employing PathAI’s proprietary continuous scoring to predict disease progression in patients with NASH. By leveraging continuous scores, prediction of clinical disease progression in patients with NASH is possible. The results of this abstract support further investigation into the value of machine learning-based continuous histologic scoring methods for detecting small but clinically meaningful therapeutic effects in NASH clinical trials.
The final abstract presents PathAI’s novel method for imaging fibrosis in liver biopsies, potentially allowing for removal of trichrome stain slides that historically have been necessary. Eliminating the need for trichrome-stained slides may have several benefits, the most prominent of which could be improved accuracy. Liver biopsy segments taken from a given patient can have variations unrelated to disease activity but due to heterogeneity in liver tissue. Obtaining all necessary information to assess a patient's disease state from a single biopsy slide allows for a more consistent analysis of the patient’s disease and may improve accuracy on determining their risk for disease progression.
The International Liver Conference runs June 22-26, 2022. PathAI’s abstract details are highlighted below:
Title: Retrospective AI-based Measurement of NASH Histology (AIM-NASH) analysis of biopsies from Phase 2 study of Resmetirom confirms significant treatment-induced changes in histologic features of non-alcoholic steatohepatitis
Session Date and Time: June 25, 2022. 9:00 am -18:00 pm GMT
Abstract: #3625
Developed in partnership with Madrigal Pharmaceuticals
Title: Machine learning-enabled continuous scoring of histologic features facilitates prediction of clinical disease progression in patients with non-alcoholic steatohepatitis
Session Date and Time: June 25, 2022. 9:00 am -18:00 pm GMT
Abstract: #3788
Developed in partnership with Gilead Sciences
Title: Quantitative multimodal anisotropy imaging enables automated fibrosis assessment of H&E-stained tissue
Session Date and Time: June 25, 2022. 9:00 am -18:00 pm GMT
Abstract: #3370
About PathAI
PathAI is a leading provider of AI-powered research tools and services for pathology. PathAI’s platform promises substantial improvements to the accuracy of diagnosis and the efficacy of treatment of diseases like cancer, leveraging modern approaches in machine and deep learning. Based in Boston, PathAI works with leading life sciences companies and researchers to advance precision medicine. To learn more, visit pathai.com.
