BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260729T023037EDT-53170SW2c4@132.216.98.100
DTSTAMP:20260729T063037Z
DESCRIPTION:Joon Lee\, PhD\n\nAssociate Professor of Health Data Science |
 \n	Depts of Cardiac Sciences and Community Health Sciences | Cumming School
  of Medicine | University of Calgary\n\nWHERE: Hybrid | 2001 McGill Colleg
 e\, Rm 1140 | Zoom\n\nNote: Joon Lee will be presenting from U of Calgary
 \n\n \n\nAbstract\n\nDelirium is common in the intensive care unit (ICU) a
 nd associated with longer ICU and hospital stays as well as worse patient 
 outcomes including long-term cognitive impairment. Early prediction of imp
 ending delirium can lead to efficient allocation of ICU resources and impr
 oved patient outcomes via preventive care. Based on rich clinical data fro
 m over 43\,000 ICU admissions in Alberta\, we developed deep learning-base
 d models capable of predicting delirium in the next two 12-hour windows\, 
 with new predictions generated every 12 hours. Our best model based on gat
 ed recurrent units resulted in areas under the receiver operating characte
 ristic curve around 0.9.\n\nLearning Objectives\n\nBy the end of this sess
 ion\, attendees will:\n\n\n	Understand delirium as a major clinical problem
  in the intensive care unit\;\n	Learn how recurrent deep learning can be ut
 ilized to predict impending delirium in the intensive care unit\;\n	Appreci
 ate the challenges surrounding feature engineering and hyperparameter tuni
 ng when granular electronic health record data are used.\n\n\nSpeaker Bio
 \n\nDr. Joon Lee is the Director of the Data Intelligence for Health Lab a
 nd an Associate Professor of Health Data Science in the Departments of Car
 diac Sciences and Community Health Sciences\, Cumming School of Medicine\,
  University of Calgary. He holds a PhD in Biomedical Engineering from the 
 University of Toronto and a BASc in Electrical Engineering from the Univer
 sity of Waterloo. He also completed a Postdoctoral Fellowship in Medical D
 ata Science at MIT. His research applies data science\, machine learning\,
  and artificial intelligence to a variety of problems in medicine and publ
 ic health including intensive care\, cardiology\, public health surveillan
 ce\, and food marketing.\n
DTSTART:20231106T210000Z
DTEND:20231106T220000Z
SUMMARY:Deep learning-based recurrent prediction of delirium in the intensi
 ve care unit
URL:https://www.mcgill.ca/epi-biostat-occh/channels/event/deep-learning-bas
 ed-recurrent-prediction-delirium-intensive-care-unit-351519
END:VEVENT
END:VCALENDAR