CHIMERA: Dr Andrey Kormilitzin, University of Oxford

26 May 2021, 3:00 pm–4:00 pm

Chimera Seminar Series

Unreasonable effectiveness of the path signature representations for electronic health records

Event Information

Open to





CHIMERA (Collaborative Healthcare Innovation through Mathematics, EngineeRing and AI)


Zoom webinar

Recent years have seen an explosion of computational methods to efficiently learn representations of complex longitudinal electronic health records for downstream analytical tasks. While deep representation learning is the method of choice in many scenario, it requires large amounts of data to achieve robust results. In this talk I will discuss the path signature method, that provides a succinct summary of sequential data and can be used as an effective and learnable feature set for describing sequentially ordered data, such as multidimensional physiological time-series or texts in clinical notes. I will introduce the fundamentals of the paths signature method and discuss their applications in two clinical use-cases: the winning solution to the PhysioNet 2019 Challenge on early prediction of sepsis in ICU and mortality risk prediction for patients diagnosed with Alzheimer's disease using their secondary care medical records.

About the Speaker

Prof Andrey Kormilitzin

at University of Oxford

Andrey Kormilitzin is a Senior Researcher at the Department of Psychiatry and a member of the Mathematical Institute at the University of Oxford. His research is centred around the development and translation of computational methods to make sense of complex multimodal biomedical data. He leads the Natural Language Processing research team working on information extraction, explainability and clinical decision support using the largest secondary care mental health electronic medical records in the UK. He holds PhD in Mathematical and Theoretical Physics.