BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260906T002811EDT-3148sO0jpI@132.216.98.100
DTSTAMP:20260906T042811Z
DESCRIPTION:Machine Learning To Identify Incipient Dementia.\n\nhttp://tnl.
 research.mcgill.ca/\n\n	Identifying individuals destined to develop Alzheim
 er's dementia within time frames acceptable for clinical trials constitute
 s an important challenge to design studies to test emerging disease-modify
 ing therapies. We developed a machine learning–based probabilistic method 
 designed to assess the progression to dementia within 24 months\, based on
  the regional information from a single amyloid positron emission tomograp
 hy scan. Importantly\, the proposed method was designed to overcome the in
 herent adverse imbalance proportions between stable and progressive mild c
 ognitive impairment individuals within a short observation period. The nov
 el algorithm obtained an accuracy of 84% and an area-under-the-receiver-op
 erating-characteristic-curve of 0.91\, outperforming the existing algorith
 ms using the same biomarker measures and previous studies using multiple b
 iomarker modalities. With its high accuracy\, this algorithm has immediate
  applications for population enrichment in clinical trials designed to tes
 t disease-modifying therapies aiming to mitigate the progression to Alzhei
 mer's disease dementia.\n
DTSTART:20171107T203000Z
DTEND:20171107T213000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Sulantha Mathotaarachchi\, MSc\, McGill
URL:https://www.mcgill.ca/mathstat/channels/event/sulantha-mathotaarachchi-
 msc-mcgill-282420
END:VEVENT
END:VCALENDAR