October 22nd – RL Based Disease Progression Model for Alzheimer’s Disease

This week, we have a presentation by Krishnakant Saboo – PhD Candidate in ECE under the advisement of Prof. Ravishankar Iyer.

Reinforcement Learning based Disease Progression Model for Alzheimer’s Disease

Early diagnosis of Alzheimer’s disease (AD) is crucial. However, long term longitudinal data spanning the entire duration of the disease is rarely available. In this talk, I present a model of AD progression that combines biologically motivated differential equations (DEs) and reinforcement learning (RL) with domain knowledge. The model requires limited data for training since it leverages DEs that provide relationships between some, but not all, factors relevant to AD, and utilizes RL to extract the missing relationships. The model predicted individualized 10-year future AD progression better than state-of-the-art learning-based models and provided insights into disease related processes. Finally, I discuss broader applicability of our framework that combines DEs with RL in modelling and understanding other neurological disorders.

Krishnakant Saboo is a PhD candidate in the ECE Department at the University of Illinois at Urbana-Champaign advised by Prof. Ravishankar Iyer. He received a Bachelor’s and Master’s degree in Electrical Engineering from the Indian Institute of Technology, Bombay in 2016. His research interests are at the intersection of machine learning, neurology, and neuroscience. For his PhD, he uses ML techniques to model the progression of Alzheimer’s disease and improve the diagnosis of epilepsy. Krishnakant’s work has been recognized by the Mayo/Illinois fellowship, Rambus fellowship, the Elsa and Floyd Dunn award, and the Mavis Future Faculty fellowship. Apart from work, he enjoys teaching, learning about science, and wondering about the meaning of life.