BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:BSU Seminar: "Reclassification of multiple sclerosis using probabi
 listic machine learning" - Habib Ganjgahi\, Oxford Big Data Institute
DTSTART:20250318T140000Z
DTEND:20250318T150000Z
UID:TALK229561@talks.cam.ac.uk
CONTACT:Alison Quenault
DESCRIPTION:Multiple sclerosis (MS) affects 2.9 million people.  Tradition
 al classification of MS into distinct subtypes poorly aligns with its path
 obiology\, has limited value for prognostication of disease evolution and 
 treatment response\, and divergent views on disease classification hamper 
 drug discovery. We have developed a bespoke multivariate hierarchical Baye
 sian model (probabilistic latent variable followed by hidden Markov model 
 (HMM)) that can handle different data\n\nmodalities (binary\, count\, ord
 inal and continuous variables) and structured missingness.\n\n \n\nWe repo
 rt a new\, data-driven classification of MS disease evolution by analysing
  a large clinical trial database (~8000 patients with 118\,000 patient vis
 its\, >35\,000 MRI scans). Four dimensions define MS disease states: physi
 cal disability\, brain damage\, clinical relapses\, and subclinical diseas
 e activity. Early/mild/evolving (EME) MS and advanced MS represent two pol
 es of a disease severity spectrum. Transitions to advanced MS occur via ac
 cumulation of damage to the central nervous system through inflammatory st
 ates\, with or without accompanying symptoms. We validated these results i
 n pooled data from three independent clinical trials and in a real-world c
 ohort\, totalling >4000 patients with MS.
LOCATION:Large Seminar Room\, East Forvie Building\, Forvie Site Robinson 
 Way Cambridge CB2 0SR.
END:VEVENT
END:VCALENDAR