Comparison of the predictive abilities of pharmacogenetics-based warfarin dosing algorithms using seven mathematical models in Chinese patients.

AIM This study is aimed to find the best predictive model for warfarin stable dosage. MATERIALS & METHODS Seven models, namely multiple linear regression (MLR), artificial neural network, regression tree, boosted regression tree, support vector regression, multivariate adaptive regression spines and random forest regression, as well as the genetic and clinical data of two Chinese samples were employed. RESULTS The average predicted achievement ratio and mean absolute error of the algorithms were ranging from 52.31 to 58.08% and 4.25 to 4.84 mg/week in validation samples, respectively. The algorithm based on MLR showed the highest predicted achievement ratio and the lowest mean absolute error. CONCLUSION At present, MLR may be still the best model for warfarin stable dosage prediction in Chinese population. Original submitted 10 November 2014; Revision submitted 18 February 2015.

[1]  Panos Deloukas,et al.  The largest prospective warfarin-treated cohort supports genetic forecasting. , 2009, Blood.

[2]  R. Califf,et al.  A pharmacogenetic versus a clinical algorithm for warfarin dosing. , 2013, The New England journal of medicine.

[3]  R. Altman,et al.  Estimation of the warfarin dose with clinical and pharmacogenetic data. , 2009, The New England journal of medicine.

[4]  A. Gallus,et al.  Standardised initial warfarin treatment: evaluation of initial treatment response and maintenance dose prediction by randomised trial, and risk factors for an excessive warfarin response. , 1991, Australian and New Zealand journal of medicine.

[5]  A. Israni,et al.  Dosing equation for tacrolimus using genetic variants and clinical factors. , 2011, British journal of clinical pharmacology.

[6]  F. Kamali,et al.  VKORC1 and CYP2C9 genotype and patient characteristics explain a large proportion of the variability in warfarin dose requirement among children. , 2012, Blood.

[7]  F. Kamali,et al.  Contribution of age, body size, and CYP2C9 genotype to anticoagulant response to warfarin , 2004, Clinical pharmacology and therapeutics.

[8]  H. Zhou,et al.  Development and comparison of a new personalized warfarin stable dose prediction algorithm in Chinese patients undergoing heart valve replacement. , 2012, Die Pharmazie.

[9]  Rita Barallon,et al.  A randomized trial of genotype-guided dosing of acenocoumarol and phenprocoumon. , 2013, The New England journal of medicine.

[10]  Deborah A Nickerson,et al.  Effect of VKORC1 haplotypes on transcriptional regulation and warfarin dose. , 2005, The New England journal of medicine.

[11]  Nicole Soranzo,et al.  A Genome-Wide Association Study Confirms VKORC1, CYP2C9, and CYP4F2 as Principal Genetic Determinants of Warfarin Dose , 2009, PLoS genetics.

[12]  Ann Daly,et al.  Sequence diversity in CYP3A promoters and characterization of the genetic basis of polymorphic CYP3A5 expression , 2001, Nature Genetics.

[13]  Jaekyu Shin,et al.  Comparison of warfarin pharmacogenetic dosing algorithms in a racially diverse large cohort. , 2011, Pharmacogenomics.

[14]  J. Hirsh,et al.  Interactions of Warfarin with Drugs and Food , 1994, Annals of Internal Medicine.

[15]  Christine W. Duarte,et al.  High-dimensional pharmacogenetic prediction of a continuous trait using machine learning techniques with application to warfarin dose prediction in African Americans , 2011, Bioinform..

[16]  K E Liu,et al.  Improvement of Adequate Use of Warfarin for the Elderly Using Decision Tree-based Approaches , 2013, Methods of Information in Medicine.

[17]  B. Horne,et al.  Randomized Trial of Genotype-Guided Versus Standard Warfarin Dosing in Patients Initiating Oral Anticoagulation , 2007, Circulation.

[18]  M. Rieder,et al.  Use of Pharmacogenetic and Clinical Factors to Predict the Therapeutic Dose of Warfarin , 2008, Clinical pharmacology and therapeutics.

[19]  D. Tregouet,et al.  Cytochrome P450 2C9 (CYP2C9) and vitamin K epoxide reductase (VKORC1) genotypes as determinants of acenocoumarol sensitivity. , 2005, Blood.

[20]  Massimo Buscema,et al.  Prediction of optimal warfarin maintenance dose using advanced artificial neural networks. , 2014, Pharmacogenomics.

[21]  Ling-Zhi Wang,et al.  A warfarin‐dosing model in Asians that uses single‐nucleotide polymorphisms in vitamin K epoxide reductase complex and cytochrome P450 2C9 , 2006, Clinical pharmacology and therapeutics.

[22]  S. le Cessie,et al.  Loading and maintenance dose algorithms for phenprocoumon and acenocoumarol using patient characteristics and pharmacogenetic data. , 2011, European heart journal.

[23]  P. Deloukas,et al.  Association of warfarin dose with genes involved in its action and metabolism , 2006, Human Genetics.

[24]  D. Wysowski,et al.  Bleeding complications with warfarin use: a prevalent adverse effect resulting in regulatory action. , 2007, Archives of internal medicine.

[25]  Wei Zhang,et al.  Effect of CYP2C9–VKORC1 interaction on warfarin stable dosage and its predictive algorithm , 2015, Journal of clinical pharmacology.

[26]  Eun-Young Kim,et al.  Effect of CYP2C9 and VKORC1 genotypes on early-phase and steady-state warfarin dosing in Korean patients with mechanical heart valve replacement , 2009, Pharmacogenetics and genomics.

[27]  Yusuke Nakamura,et al.  Genetic variants associated with warfarin dose in African-American individuals: a genome-wide association study , 2013, The Lancet.

[28]  N. Eriksson,et al.  A randomized trial of genotype-guided dosing of warfarin. , 2013, The New England journal of medicine.