Motivation

Predicting warfarin dosage from clinical data:
A supervised learning approach
Presenter : CHANG, SHIH-JIE
Authors
: Ya-Han Hu, Fan Wu a, Chia-Lun Lo, Chun-Tien Tai b
2012.AIM.
Intelligent Database Systems Lab
Outlines
 Motivation
 Objectives
 Methodology
 Experiments
 Conclusions
 Comments
Intelligent Database Systems Lab
Motivation

Physicians use computerized dosing nomograms of
warfarin as reference .It merely consider age and INR values
not enough for dose adjustment.
Intelligent Database Systems Lab
Objectives
•
Build a warfarin dosage prediction model utilizing a
number of supervised learning techniques to help dose
adjustment.
Intelligent Database Systems Lab
Warfarin
Intelligent Database Systems Lab
Prediction model for warfarin dosing- Single classifiers
(1) KNN
(2) SVR
Given a set of training instances
xi : input vector
yi : actual output of xi
a regression function
regression hyperplane
ε-SVR can be formulated
Intelligent Database Systems Lab
Methodology - Single classifiers
(3) M5 (model-tree-based regression algorithm)
Tree-building :
use standard deviation reduction
standard deviation of the class values
of all instances in a child-node Nt,i,
specific node
Intelligent Database Systems Lab
Methodology - M5
tree-pruning
error term
Intelligent Database Systems Lab
Methodology – MLP
(4) MLP
Intelligent Database Systems Lab
Methodology – Classifier ensemble


Voting (weight)
Decide the estimated output
by combining the results
of different classifiers.

Bagged Voting method
Intelligent Database Systems Lab
Experiments – Data preparation
Collected 587 clinical cases (INR value 1~3)
Drug-to-drug interaction (DDI)
424
163
Use Bagging
496
Intelligent Database Systems Lab
Experiments – Performance measures
Intelligent Database Systems Lab
Experiments – Evaluation results
Experiments – The average of evaluation results
Intelligent Database Systems Lab
Conclusions
– The investigated models can not only facilitate
clinicians in dosage decision-making, but also
help reduce patient risk from adverse drug events.
Intelligent Database Systems Lab
Comments
• Advantages
– More accurate.
• Applications
– Warfarin dosage prediction.
Intelligent Database Systems Lab