RBCDSAI Seminar - Sunandan Chakraborty

Watch Livesteam


Research articles published in medical journals often present findings from experiments to establish causality. We use this intuition to build a model that leverages causal relations expressed in the text to uncover causal links among medical events recorded independently in different data sources, which is expected to reduce the time between disease onset and diagnosis significantly. Symptoms of Sjögren’s syndrome is an auto-immune disease affecting up to 3.1 million people across the world. The uncommon nature of the disease, coupled with common symptoms with other autoimmune conditions, makes the timely diagnosis of this disease very hard. A centralized information system with easy access to common and uncommon factors related to Sjögren’s syndrome may alleviate the problem. We use automatically extracted causal relationships from text related to Sjögren’s syndrome collected from the medical literature to identify a set of factors, such as ``signs and symptoms'' and ``associated conditions'', related to this disease. We show that our approach is capable of retrieving such factors with high precision and recall values. Comparative experiments show that this approach leads to 25% improvement in retrieval F1-score compared to several state-of-the-art biomedical models, including BioBERT and Gram-CNN.


Sunandan Chakraborty is an assistant professor of data science at the Indiana University School of Informatics and Computing. His research focuses on data science for social good, building computational models that leverage vast data sets and applying them to a broad spectrum of problems in social and environmental science, agriculture, health, and other fields. He draws on diverse data sets (news, social media, time-series etc.) and uses tools such as machine learning, information extraction, and time series analysis to compile information and discover knowledge that can lead to solutions.
Before joining Indiana University, he worked with Dr. Jennifer Jacquet as a Moore-Sloan postdoctoral researcher at the NYU Center for Data Science. Their award-winning research explored the problem of illegal online wildlife trading, utilizing complex digital text analyses. He completed his PhD under the supervision of Dr. Lakshminarayanan Subramanian at the Courant Institute of Mathematical Sciences of New York University.