BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Better Characterization of Sleep Stages for Detecting Dementia -
  Oscar Perez Romero
DTSTART:20260316T170000Z
DTEND:20260316T173000Z
UID:TALK245842@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:The prevention of neurodegenerative diseases is an emerging fi
 eld that relies on understanding the evolution of their symptoms such as c
 ognitive impairment. Although there are no standard indicators for detecti
 ng the early signs of dementia\, it is well-established that several memor
 y-related processes occur during sleep. Therefore\, recent works have stud
 ied sleep through brain activity\, focusing on the sleep stages defined by
  the American Academy of Sleep Medicine (AASM). In this thesis\, we demons
 trate that relying on AASM stages for detecting dementia provides suboptim
 al results and propose a new and more informative set of sleep stages disc
 overed naturally by a Gaussian Mixture (GM) model operating on electroence
 phalogram (EEG) features. The improved performance of our approach emerges
  from simple logistic regression classifiers trained on EEG‑derived desc
 riptors from healthy subjects\, as well as patients with mild cognitive im
 pairment and severe dementia\, highlighting the richer information content
  captured by our GM‑based stages. Moreover\, we show empirically that di
 fferences between levels of dementia reside primarily in patterns of brain
  activity rather than in the time spent in each sleep stage. These finding
 s indicate that more expressive characterizations of sleep exist beyond th
 e conventional AASM framework. In future work\, given the promising result
 s from this thesis\, it would be interesting to study other pathologies\, 
 as well as other techniques to extract information from sleep.
LOCATION:LT1
END:VEVENT
END:VCALENDAR