High-dimensional counterfactual modelling of lesion-deficit relations in focal brain injury

Lead Research Organisation: University College London
Department Name: Institute of Health Informatics

Abstract

Stroke is arguably unique in medicine in combining substantial treatment effects,
large-scale, population-level impact, and high-dimensional non-linear causal
relations only complex modelling could adequately disentangle. This makes it an
ideal exemplar system for pioneering complex modelling, not only in the now
familiar predictive mode, but also prescriptively, seeking to quantify individual
treatment effects. An exquisitely time-sensitive condition, it benefits from clinical
and operational optimisation in equal measure, allowing early, demonstrable impact
to be drawn from operational deployment of complex models in advance of clinical
regulatory approval. The objective of this research is to build on proof-of-concept
work on prescriptive modelling in stroke-based on the largest published series of
stroke patients with anatomically registered imaging-to create and validate a
robust platform for quantifying individual treatment effects in focal brain injury
applied to stroke-clinically and operationally-and naturally extensible to kindred
conditions. This ambition is both aligned with the averred aims of the CDT and may
achieve tangible impact within its lifetime, maximising its reportable value.

Supervisors: Parashkev Nachev and Ashwani Jha

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S021612/1 01/04/2019 30/09/2027
2252409 Studentship EP/S021612/1 01/10/2019 30/09/2023 Dominic Matthew Giles