The ability to understand causality from data is regarded as one of the major fundamental elements of human-level intelligence. CAIL lab studies causal inference, machine learning, and artificial intelligence methods with an interest in contributing to a deeper understanding of the cause and context in data-intensive healthcare and ubiquitous computing environments. We address new and fundamental challenges related to causal discovery, causal inferences, prior-knowledge infusion, predictive modeling, and associated uncertainty. Our work is collaborative and interdisciplinary in nature and focuses on societal impacts. Our research has applications in healthcare, pervasive computing, rehabilitation engineering, occupational science, social science, language, etc.
CKH: Causal Knowledge Hierarchy for Estimating Structural Causal Models from Data and Priors
Riddhiman Adib, Md Mobasshir Arshed Naved, Chih-Hao Fang, Md Osman Gani, Ananth Grama, Paul Griffin, Sheikh Iqbal Ahamed, Mohammad Adibuzzaman
Proceedings of Machine Learning Research XXX:1–25, 2022
Causal Discovery on the Effect of Antipsychotic Drugs on Delirium Patients in the ICU using Large EHR Dataset
Riddhiman Adib, Md Osman Gani, Sheikh Iqbal Ahamed, Mohammad Adibuzzaman
Proceedings of Machine Learning Research XXX:1–14, 2022