BEGIN:VCALENDAR
VERSION:2.0
PRODID:talks.ox.ac.uk
BEGIN:VEVENT
SUMMARY:Interpretable artificial intelligence to identify brain aging traj
 ectories leading to Alzheimer's disease - Associate Professor Andrei Irimi
 a (University of Southern California)
DTSTART;VALUE=DATE-TIME:20241106T110000Z
DTEND;VALUE=DATE-TIME:20241106T120000Z
UID:https://talks.ox.ac.uk/talks/id/c997289d-2ab5-49ff-be2f-fe8f483c5291/
DESCRIPTION:Early estimation of disease risk from magnetic resonance image
 s (MRIs) can help to reduce the clinical burden of incurable neurological 
 disorders such as Alzheimer's disease and related dementias (ADRD). Tradit
 ionally\, researchers' attempts to identify early biomarkers of future ADR
 D have relied on neuroanatomic measures defined a priori\, including brain
  volume loss and cortical thinning. Such measures have limited utility due
  to their modest sensitivity and specificity for the prognostication of AD
 RD. Recent progress in explainable artificial intelligence (XAI) leverages
  the ability of deep neural networks to find complex patterns of abnormal 
 neuroanatomic aging that are not apparent to humans and that can better pr
 edict ADRD morbidity. Because brain aging is lifelong\, such abnormal agin
 g trajectories have the advantage of being detectable relatively early in 
 adulthood to mitigate ADRD risk. Our patient-tailored anatomic maps of bra
 in aging highlight differences in neurosenescence according to sex\, decad
 al age group\, biometrics\, demographics\, and cognitive status. These XAI
 -empowered findings identify\, for the first time\, the anatomic substrate
 s of complex endophenotypes whose structural bases were previously thought
  to be undetectable by MRI. In conclusion\, XAI holds considerable potenti
 al to assist translational neuroscience\, to advance basic studies of brai
 n structure/function\, and to develop early biomarkers of ADRD risk in agi
 ng adults with normal cognition.\n\nSPEAKER BIOGRAPHY\n\nAndrei Irimia\, P
 hD is a visiting associate professor at King's College London\, currently 
 on sabbatical from the Leonard Davis School of Gerontology at the Universi
 ty of Southern California. Dr. Irimia is a biogerontologist and computatio
 nal neurobiologist studying how (epi)genetic and environmental factors con
 strain brain aging in health and disease. In collaboration with the ENIGMA
  Consortium and with other researchers across the world\, his team uses ex
 plainable artificial intelligence (XAI)\, omics\, and neuroimaging to char
 acterize risk factors for Alzheimer's disease (AD). These methods are syne
 rgized with biometrics\, demographics and with large-scale research on pre
 -industrial populations to build XAI models that forecast AD conversion in
  aging adults. Such approaches relate AD risk to accelerated aging\, neuro
 vascular calcification\, industrialization\, urbanization\, lifestyle and 
 traumatic brain injury. \nSpeakers:\nAssociate Professor Andrei Irimia (Un
 iversity of Southern California)
LOCATION:Sherrington Library (Sherrington Building)\, off Parks Road OX1 3
 PT
TZID:Europe/London
URL:https://talks.ox.ac.uk/talks/id/c997289d-2ab5-49ff-be2f-fe8f483c5291/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Interpretable artificial intelligence to identify brain a
 ging trajectories leading to Alzheimer's disease - Associate Professor And
 rei Irimia (University of Southern California)
TRIGGER:-PT1H
END:VALARM
END:VEVENT
END:VCALENDAR