Revisiting Warfarin Dosing Using Machine Learning Techniques

Ashkan Sharabiani,Houshang Darabi,Elnaz Douzali,Adam Bress

doi:10.1155/2015/560108

Ashkan Sharabiani, Houshang Darabi + Show 2 more

Open Access

https://doi.org/10.1155/2015/560108

Copy DOI

Abstract

Determining the appropriate dosage of warfarin is an important yet challenging task. Several prediction models have been proposed to estimate a therapeutic dose for patients. The models are either clinical models which contain clinical and demographic variables or pharmacogenetic models which additionally contain the genetic variables. In this paper, a new methodology for warfarin dosing is proposed. The patients are initially classified into two classes. The first class contains patients who require doses of >30 mg/wk and the second class contains patients who require doses of ≤30 mg/wk. This phase is performed using relevance vector machines. In the second phase, the optimal dose for each patient is predicted by two clinical regression models that are customized for each class of patients. The prediction accuracy of the model was 11.6 in terms of root mean squared error (RMSE) and 8.4 in terms of mean absolute error (MAE). This was 15% and 5% lower than IWPC and Gage models (which are the most widely used models in practice), respectively, in terms of RMSE. In addition, the proposed model was compared with fixed-dose approach of 35 mg/wk, and the model proposed by Sharabiani et al. and its outperformance were proved in terms of both MAE and RMSE.

Highlights

A great deal of effort has been dedicated to determine the optimal initial dose for warfarin
Using the relevance vector machines (RVM) model, the data points in the testing set were classified to High required dose (HRD) and Low required dose (LRD) classes and two regression models were developed for each class separately
After classifying the points in the test set, 49% of the points were assigned to HRD class and 51% to LRD class

Summary

Introduction

A great deal of effort has been dedicated to determine the optimal initial dose for warfarin. The challenge in estimating the right dose of warfarin for each patient arises from the fact that there is wide interpatient variability in dosing [1]. Over the past decade or so, a number of research groups have focused on developing models to predict the warfarin maintenance dose. Accurate warfarin dosing is critically important because of the drug’s narrow therapeutic index, whereas there is an increased risk for thromboembolism or hemorrhage with sub- or supratherapeutic anticoagulation, respectively. Warfarin is the leading cause of drug-related hospitalizations among older adults in the United States of America [1]. The risks for bleeding or thrombosis with warfarin are greatest during the initial months of therapy [1]

Objectives

Methods

Results

Conclusion