Paper: Medical Risk Evaluation - Rankprop and Multitask Learning

[Shumeet Baluja]

Paper Available:
--------------------------
Using the Future to "Sort Out" the Present: Rankprop and 
Multitask Learning for Medical Risk Evaluation

Rich Caruana, Shumeet Baluja, and Tom Mitchell 



Abstract:
--------------------------
A patient visits the doctor; the doctor reviews the patient's history, asks
questions, makes basic measurements (blood pressure, ...), and prescribes
tests or treatment.  The prescribed course of action is based on an assessment
of patient risk---patients at higher risk are given more and faster attention.
It is also sequential---it is too expensive to immediately order all tests
which might later be of value.  This paper presents two methods that together
improve the accuracy of backprop nets on a pneumonia risk assessment problem
by 10-50\%.  {\em Rankprop} improves on backpropagation with sum of squares
error in ranking patients by risk.  {\em Multitask learning} takes advantage
of {\em future} lab tests available in the training set, but not available in
practice when predictions must be made.  Both methods are broadly applicable.




Retrieval Information
--------------------------
This paper will appear in NIPS 8.

Available via the web from:
 http://www.cs.cmu.edu/~baluja/techreps.html