Using AI to fight rheumatoid arthritis

Using AI to fight rheumatoid arthritis

Fan Zhang, PhD, sees artificial intelligence as a way to find an effective way to combat an intractable enemy: rheumatoid arthritis.

Zhang is an assistant professor in the Division of Rheumatology at the University of Colorado Department of Medicine and is also affiliated with the Department of Biomedical Informatics at the Cu Anschutz Medical Campus. She recently received a highly competitive grant from the Arthritis Foundation to further her work in using AI to better predict the onset of rheumatoid arthritis (RA) in certain patients, and a new paper documents the latest steps in her work.

Zhang's research focus is on developing methods that incorporate computer machine learning - using algorithms from data and prediction - to study RA and other autoimmune diseases, relying on large-scale clinical and preclinical single-cell datasets. This work could advance targeted interventions that could prevent disease progression.

Significant research has been done on how to treat a patient after someone is diagnosed. However, there have been fewer studies to develop prevention strategies and to understand which healthy people are at risk of developing RA in the next few years. This is much more difficult. So we focus on improving disease prediction and ultimately enabling the prevention of the early diseases. “

Fan Zhang, PhD, assistant professor in the Division of Rheumatology at the University of Colorado Department of Medicine

Bridging data science with translational medicine

RA is a chronic autoimmune disease, meaning it is a disorder in which the body's immune system mistakenly attacks its own healthy tissues, causing inflammation. Although RA is often associated with swelling, pain, and stiffness in the joints, it can affect various parts of the body, including the heart and lungs.

It is estimated that around 18 million people live with RA worldwide, 1.5 million of whom live in the United States. Almost three times as many women have the disorder as men.

Available treatments can reduce inflammation and provide some relief, but there are no effective preventative treatments and no cures. The cause is uncertain, although RA has been linked to certain genes that can be triggered by a number of external factors.

Research has shown that many people who ultimately develop RA symptoms experience immunological abnormalities that can be detected even though blood tests appear years before the symptoms. However, the length of this symptom-free “preclinical” period can vary widely, and some people with these abnormalities never develop the full disease.

What's needed, says Zhang, are more precise ways to predict which people with preclinical abnormalities - or with a family history of RA - will progress to full-blown disease and how quickly.

Zhang describes her work as a “bridge” between data science and translational medicine.

“Our research is very interdisciplinary,” says Zhang. “We have large-scale data from patients with autoimmune diseases, so we can apply our AI tools to different cohorts of patients.”

Zhang's team analyzes data on genetics, genomics, epigenetics, protein and other factors of individual cells at different points in time over long periods of time - known as single-cell multi-modal sequencing. “By putting all of these things together, we can hope to more robustly identify new and more accurate markers for prediction, combined with clinical characteristics,” she says.

Pennant important immunological changes

The study presented in Zhang's new work - "Deep immunophenotyping reveals circulating activated lymphocytes in people at risk for rheumatoid arthritis" published March 17 in the Journal of Clinical Investigation - helped establish the foundation for its next phase of research, supported by a new grant from the Arthritis Foundation.

With this new funding, Zhang's lab will apply its advanced computational tools to complex data sets collected from a large preclinical trial called Stopra. This, says Zhang, will strengthen her collaboration with Cu rheumatologist Kevin Deane, MD, PhD, as they compare people who did it with those who didn't. The aim is to determine immune system changes associated with progression from preclinical Rau arthritis to symptoms.

In this paper, funded by a National Institutes of Health grant, Zhang and her colleagues analyzed RNA and protein expression in cells to compare people at risk of developing RA with symptoms and healthy people. They found “significant” differences in certain types of immune cells, particularly the expansion of specific T cell subtypes, in the at-risk group.

These cells "could be a promising marker" of RA onset, says Zhang, and could lead to improved prevention strategies. But she says it's "still a ways off" and requires even larger and more geographically diverse data sets to determine whether the results they're seeing hold up.

Zhang is the corresponding author of this paper; Her lab's postdoctoral fellow, Jun Inamo, MD, PhD, is the first author; and Deane and another rheumatology colleague, V. Michael Holers, MD, are among the co-senior authors.

Zhang, who was at Cu Anschutz for just over three years after a postdoctoral fellowship at Harvard Medical School, says the Aurora campus is suited to this type of collaboration, “with all the expertise and resources surrounding you.

Sources: