BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251121T060554EST-158651LFds@132.216.98.100
DTSTAMP:20251121T110554Z
DESCRIPTION:Scalable Joint Models for Reliable Event Prediction: Applicatio
 n to Monitoring Adverse Events using Electronic Health Record Data.\n\n\n	M
 any life-threatening adverse events such as sepsis and cardiac arrest are 
 treatable if detected early. Towards this\, one can leverage the vast numb
 er of longitudinal signals---e.g.\, repeated heart rate\, respiratory rate
 \, blood cell counts\, creatinine measurements---that are already recorded
  by clinicians to track an individual's health. Motivated by this problem\
 , we propose a reliable event prediction framework comprising two key inno
 vations. First\, we extend existing state-of-the-art in joint-modeling to 
 tackle settings with large-scale\, (potentially) correlated\, high-dimensi
 onal multivariate longitudinal data. For this\, we propose a flexible Baye
 sian nonparametric joint model along with scalable stochastic variational 
 inference techniques for estimation. Second\, we use a decision-theoretic 
 approach to derive an optimal detector that trades-off the cost of delayin
 g correct adverse-event detections against making incorrect assessments. O
 n a challenging clinical dataset on patients admitted to an Intensive Care
  Unit\, we see significant gains in early event-detection performance over
  state-of-the-art techniques.\n
DTSTART:20170207T203000Z
DTEND:20170207T213000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Suchi Saria - PhD\, Johns Hopkins University
URL:/mathstat/channels/event/suchi-saria-phd-johns-hop
 kins-university-265562
END:VEVENT
END:VCALENDAR