BIOM&S Seminar: by Joel Dubin "Some prediction problems in intensive care unit (ICU) studies"

SPEAKER:   Joel Dubin

(Dept. of Stats and Actuarial Science and School of Public Health and Health Systems, University of Waterloo)
 

ABSTRACT: 

A primary goal for ICU patients is treating them to achieve positive

patient outcomes (e.g., hospital discharge alive, improvement from

in-hospital ailments, extended survival).  A major analytical issue is the

preponderance of information available at ICU entry (e.g., age, sex,

co-morbidities, prescriptions, vital signs), and longitudinally (e.g.,

vital sign changes, dynamic renal function, in-ICU treatment).  I will

present a number of interesting analytic challenges In predictive modeling

that my collaborators and I have encountered from a large ICU database,

and discuss a few remedies that we have investigated, including

implementation of a patient similarity step in an effort to improve

predictive accuracy.