AUGUST 29, 2024 – A digital pathology approach that can distinguish subtypes of rheumatoid arthritis (RA) using a machine-learning tool created by Hospital for Special Surgery (HSS) and Weill Cornell Medicine (WCM) investigators may help scientists find ways to improve care for this complex condition.

The study published August 29 in Nature Communications shows that artificial intelligence and machine learning technologies can effectively and efficiently subtype pathology samples from patients with RA.

For this study, Dr. Richard Bell, an Instructor in the HSS Research Institute and Arthritis and Tissue Degeneration Program, and Lionel B. Ivashkiv,  MD, Chief Scientific Officer at HSS teamed up with  Dr. Fei Wang, a professor of population health sciences and the founding director of the Institute of AI for Digital Health (AIDH) in the Department of Population Health Sciences at Weill Cornell Medicine.

“Our study addresses the analytical bottleneck of pathology research,” Dr. Bell said. “It is very time-consuming and tedious.” “Our tool automates the analysis of pathology slides, which may one day lead to more precise and efficient disease diagnosis and personalized treatment for RA,” said Dr. Wang. “It shows that machine learning can potentially transform pathological assessment of many diseases.”

There are several existing machine learning tools for automatic analysis of pathology slides in oncology. Dr. Wang and his colleagues have been working to expand the use of this technology in other clinical specialties.

Digital Pathology and Precision Medicine in RA

Distinguishing between the three subtypes of RA may help clinicians choose which therapy is most likely to be effective for a particular patient. This personalized medicine approach would represent a breakthrough in the care of patients with RA, and is a major goal of the Research Institute and Division of Rheumatology at HSS, which involves multiple laboratory and clinical investigators. “It’s the first step towards more personalized RA care,” Dr. Bell said. “If you can build an algorithm that identifies a patient’s subtype, you’ll be able to get patients the treatments they need more quickly.”

The technology may provide new insights into the disease by detecting unexpected tissue changes that humans might miss. By saving pathologists time on subtyping, the tool may also decrease the cost and increase the efficiency of clinical trials testing treatments for patients with different subtypes of RA. “This work represents an important advance in analyzing RA tissues that can be applied for the benefit of patients” Dr. Ivashkiv said.

Pathologists currently manually classify arthritis subtypes using a rubric to identify cell and tissue characteristics in biopsy samples from human patients—a slow process that adds to the cost of research and may lead to inconsistencies between pathologists.

The team first trained its algorithm on RA samples from one set of preclinical models, optimizing its ability to distinguish tissue and cell types in the sample and sort them by subtype. They validated the tool on a second set of samples. The tool also yielded new insights into treatment effects in the models, such as reduced cartilage degradation within six weeks of administering commonly used RA treatments.

Then, they deployed the tool on patient biopsy samples from the NIH-supported Accelerating Medicines Partnership Rheumatoid Arthritis research consortium, of which HSS is a major participating site in research led by Laura Donlin, PhD, scientist and co-director of the HSS Precision Medicine Program and rheumatologist Susan  M. Goodman, MD. The new digital pathology approach could effectively and efficiently type human clinical samples. The researchers are now validating the tool with additional patient samples and determining the best way to incorporate this new tool into pathologists’ workflows.

The team is working to develop similar tools for evaluating osteoarthritis, disc degeneration and tendinopathy.

The research reported in this story was supported in part by the National Institute of Arthritis and Musculoskeletal and Skin Diseases, the National Institute of Allergy and Infectious Diseases, the National Institute of General Medical Sciences, and the National Institute on Aging, all part of the National Institutes of Health, through grant numbers R21AR071670, R01AI175212, UH2AR067690, UC2AR081025, F30AG076326, T32GM007356, AR046713, AR050401, R01AR078268, UC2AR081025, UL1TR001866 and R01AR056702.