PathAI to Present Recent Advances in Applying AI-Powered Pathology Towards Liver Disease at the American Association for the Study of Liver Diseases (AASLD) 2022 Liver Meeting

BOSTON–(BUSINESS WIRE)–#TLM22—PathAI, a global leader in artificial intelligence (AI)-powered technology for pathology, today announced that the organization’s recent research will be presented at the upcoming 2022 AASLD 2022 Liver Meeting*, which will be held in Washington, D.C. from November 4-8, 2022. At this year’s event PathAI will share a total of five presentations, four poster presentations and one oral presentation, four of which were developed in collaboration with pharmaceutical partners. Notably, new findings for nonalcoholic steatohepatitis (NASH) highlight how PathAI continues to address the need for a reproducible and accurate clinical research network (CRN) scoring tool to meet the standards of today’s NASH clinical trials, as well as the need for more robust quantitative measures.

“The latest research from our team aimed to explore the variabilities that exist in pathologist review of liver biopsies. Our findings indicate that integrating artificial intelligence solutions into this process can greatly enhance the consistency and accuracy of these assessments,” said Dr. Mike Montalto, Chief Scientific Officer at PathAI. “This approach will naturally extend to improving NASH drug development – which is critical to addressing a large unmet medical need for patients.”

In an oral presentation developed in partnership with Gilead Sciences, “Exploratory Analyses of NASH Histology Using CRN Scores Derived from a Multi-Stain Machine Learning Method,” PathAI will highlight a novel machine learning (ML)-based scoring model, which uses information combined from H&E- and Masson’s Trichrome-stained images to predict NASH CRN grades/stages. The current evaluation process of NASH biopsies is subject to high variability; this research shows how PathAI ML can combine histologic information from multiple whole-slide images to predict NASH CRN grades/stages on a continuous scale, potentially mitigating the variation between the tissue sample assessed for each stain. Furthermore, the continuous CRN feature scores that were extracted from these predictions were derived from the same input; as such, the PathAI model allows for a direct comparison between features associated with all four NASH histological features, revealing biologically meaningful correlations between model-derived scores and both non-invasive metrics of liver disease and gene expression patterns.

To further demonstrate the effectiveness of PathAI’s continuous ML scoring capabilities, PathAI will present data developed in partnership with Novo Nordisk that shows evaluation of liver histology was generally consistent between pathologists and ML assessment in patients with NASH cirrhosis. “Comparison of The Effects of Semaglutide on Liver Histology in Patients with Non-alcoholic Steatohepatitis Cirrhosis Between Machine Learning Model Assessment and Pathologist Evaluation,” highlights PathAI’s ML analysis detected significantly fewer placebo responders than pathologists scoring, supporting previously reported observations and providing further evidence that ML methods may more accurately capture treatment response in NASH clinical trials.

PathAI continues to drive NASH research forward to support the long-term need for more granular assessment of liver biopsies. By showcasing a new method in “Quantitative Multimodal Anisotropy Imaging Enables Machine Learning Prediction of NASH CRN Fibrosis Stage without Manual Annotation,” PathAI addresses variation in manual pathologist staging of fibrosis in NASHby using Quantitative Multimodel Anisotropy Imaging (QMAI) of fibrosis to provide unbiased annotations to train models to predict NASH CRN fibrosis stage in other tissue sections. Comparing model performance with pathologist scoring, these models predicted CRN fibrosis stage with an accuracy comparable to that of models trained via pathologist annotation of MT-stained tissue sections.

The full list of PathAI’s poster presentations is highlighted below. More information on each research abstract can be found here.

Title: Exploratory Analyses of NASH histology using CRN scores derived from a multi-stain machine learning method

Oral Presentation Date and Time: Monday, November 7, 2022, 2:00 – 3:00 PM ET

Poster: #76

Partner: Gilead Sciences

Title: Quantitative multimodal anisotropy Imaging enables machine learning prediction of NASH CRN fibrosis stage without manual annotation

Session Date and Time: Saturday, November 5, 2022, 1:00 PM – 2:00 PM ET

Poster: #2548

Title: Comparison of the effects of semaglutide on liver histology in patients with non-alcoholic steatohepatitis cirrhosis between machine learning model assessment and pathologist evaluation

Session Date and Time: Saturday, November 5, 2022, 1:00 PM – 2:00 PM ET

Poster: #2681

Partner: Novo Nordisk

Title: Association between improvement in machine learning-assessed steatosis area and magnetic resonance imaging-proton density fat fraction in patients with compensated non-alcoholic steatohepatitis cirrhosis

Session Date and Time: Saturday, November 5, 2022, 1:00 PM – 2:00 PM ET

Poster: #2682

Partner: Novo Nordisk

Title: Variability in liver biopsy assessment: Data from the pegozafermin Phase 1b/2a study in subjects with non-alcoholic steatohepatitis (NASH)

Session Date and Time: Saturday, November 5, 2022, 1:00 PM – 2:00 PM ET

Poster: #2683

Partner: 89Bio

*The Liver Meeting® and AASLD are registered trademarks of the American Association for the Study of Liver Diseases.

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.

Contacts

Media:
Rebecca Stella

[email protected]

Maggie Naples

[email protected]