Detection of cell population dynamics in rheumatoid arthritis from flow cytometry data

Despite significant strides in comprehending and treating rheumatoid arthritis, the underlying biological mechanisms triggering relapses / flares, remain elusive due to their inherent unpredictability. If we were able to reliably predict the flares, it would open a path to designing targeted therapies that could significantly enhance the quality of life of people battling this chronic autoimmune disease. While traditional immunological data analysis, especially from flow cytometry, relies on manual procedures, there is a growing interest in using machine learning algorithms to extract more nuanced insights from the data.

In this talk, I will briefly describe the rheumatoid arthritis and explain why detection of different immune system cell populations is a key to a successful treatment. I will discuss the main drawbacks of current manual analysis process, and show my novel algorithm designed for flow cytometry biomarker data exploration. Finally, I will compare the algorithm performance with a machine learning approach.