Predicting warfarin dosage from clinical data: A supervised learning approach

NCUIR > School of Management at National Central University > Department of Information Management > journal & Dissertation > Item 987654321/106955

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/106955

Title:	Predicting warfarin dosage from clinical data: A supervised learning approach
Authors:	胡雅涵;Hu, Ya-Han;Wu, Fan;Lo, Chia-Lun;Tai, Chun-Tien
Contributors:	管理學院資訊管理學系
Keywords:	Algorithms;Anticoagulants - administration & dosage;Anticoagulants - adverse effects;Classifier ensemble;Databases, Factual;Decision Support Techniques;Dosage prediction;Drug-Related Side Effects and Adverse Reactions;Humans;Internal Medicine;Model tree;Multilayer perceptron;Other;Support Vector Machine;Support vector regression;Taiwan;Warfarin;Warfarin - administration & dosage;Warfarin - adverse effects
Date:	2012-09-01
Issue Date:	2026-04-23 13:50:26 (UTC+8)
Publisher:	Elsevier;Netherlands: Elsevier B.V
Abstract:	摘要： Safety of anticoagulant administration has been a primary concern of the Joint Commission on Accreditation of Healthcare Organizations. Among all anticoagulants, warfarin has long been listed among the top ten drugs causing adverse drug events. Due to narrow therapeutic range and significant side effects, warfarin dosage determination becomes a challenging task in clinical practice. For superior clinical decision making, this study attempts to build a warfarin dosage prediction model utilizing a number of supervised learning techniques. The data consists of complete historical records of 587 Taiwan clinical cases who received warfarin treatment as well as warfarin dose adjustment. A number of supervised learning techniques were investigated, including multilayer perceptron, model tree, k nearest neighbors, and support vector regression (SVR). To achieve higher prediction accuracy, we further consider both homogeneous and heterogeneous ensembles (i.e., bagging and voting). For performance evaluation, the initial dose of warfarin prescribed by clinicians is established as the baseline. The mean absolute error (MAE) and standard deviation of errors (σ(E)) are considered as evaluation indicators. The overall evaluation results show that all of the learning based systems are significantly more accurate than the baseline (MAE=0.394, σ(E)=0.558). Among all prediction models, both Bagged Voting (MAE=0.210, σ(E)=0.357) with four classifiers and Bagged SVR (MAE=0.210, σ(E)=0.366) are suggested as the two most effective prediction models due to their lower MAE and σ(E). The investigated models can not only facilitate clinicians in dosage decision-making, but also help reduce patient risk from adverse drug events. 其他題名： Artif Intell Med 出版者： Netherlands: Elsevier B.V 出版日期： 2012-09-01 出處： Artificial intelligence in medicine, 2012-09, Vol.56 (1), p.27-34 版權： 2012 Elsevier B.V. 版權： Elsevier B.V. 版權： Copyright © 2012 Elsevier B.V. All rights reserved. 識別號： ISSN: 0933-3657 識別號： ISSN: 1873-2860 識別號： EISSN: 1873-2860 識別號： DOI: 10.1016/j.artmed.2012.04.001 識別號： PMID: 22537823
Appears in Collections:	[Department of Information Management] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	19	View/Open

社群 sharing

Loading...