Prediction of optimal warfarin maintenance dose using advanced artificial neural networks
Abstract
Background: In recent years, pharmacogenetic algorithms were developed for estimating the appropriate dose of vitamin K antagonists. Aim: To evaluate the performance of new generation artificial neural networks (ANNs) to predict the warfarin maintenance dose. Methods: Demographic, clinical and genetic data (CYP2C9 and VKORC1 polymorphisms) from 377 patients treated with warfarin were used. The final prediction model was based on 23 variables selected by TWIST® system within a bipartite division of the data set (training and testing) protocol. Results: The ANN algorithm reached high accuracy, with an average absolute error of 5.7 mg of the warfarin maintenance dose. In the subset of patients requiring ≤21 mg and 21–49 mg (45 and 51% of the cohort, respectively) the absolute error was 3.86 mg and 5.45 with a high percentage of subjects being correctly identified (71 and 73%, respectively). Conclusion: ANN appears to be a promising tool for vitamin K antagonist maintenance dose prediction.
References
- 1 Ansell JE. 9th National conference on anticoagulant therapy preface. J. Thromb. Thrombolysis25(1),1 (2008).
- 2 Hirsh J, Fuster V, Ansell J, Halperin JL, AHAACOC Foundation. American Heart Association/American College of Cardiology foundation guide to warfarin therapy. J. Am. Coll. Cardiol.41(9),1633–1652 (2003).
- 3 Loebstein R, Yonath H, Peleg D et al. Interindividual variability in sensitivity to warfarin–nature or nurture? Clin. Pharmacol. Ther.70(2),159–164 (2001).
- 4 Lubitz SA, Scott SA, Rothlauf EB et al. Comparative performance of gene-based warfarin dosing algorithms in a multiethnic population. J. Thromb. Haemost.8(5),1018–1026 (2010).
- 5 Takahashi H, Echizen H. Pharmacogenetics of warfarin elimination and its clinical implications. Clin. Pharmacokinet.40(8),587–603 (2001).
- 6 Margaglione M, Colaizzo D, D‘Andrea G et al. Genetic modulation of oral anticoagulation with warfarin. Thromb. Haemost.84(5),775–778 (2000).
- 7 Sanderson S, Emery J, Higgins J. CYP2C9 gene variants, drug dose, and bleeding risk in warfarin-treated patients: a HuGEnet systematic review and meta-analysis. Genet. Med.7(2),97–104 (2005).
- 8 Scordo MG, Aklillu E, Yasar U, Dahl ML, Spina E, Ingelman-Sundberg M. Genetic polymorphism of cytochrome P450 2C9 in a Caucasian and a black African population. Br. J. Clin. Pharmacol.52(4),447–450 (2001).
- 9 Sipeky C, Lakner L, Szabo M et al. Interethnic differences of CYP2C9 alleles in healthy Hungarian and Roma population samples: relationship to worldwide allelic frequencies. Blood Cells Mol. Dis.43(3),239–242 (2009).
- 10 Spreafico M, Lodigiani C, van Leeuwen Y et al. Effects of CYP2C9 and VKORC1 on INR variations and dose requirements during initial phase of anticoagulant therapy. Pharmacogenomics9(9),1237–1250 (2008).
- 11 Jorgensen AL, Fitzgerald RJ, Oyee J, Pirmohamed M, Williamson PR. Influence of CYP2C9 and VKORC1 on patient response to warfarin: a systematic review and meta-analysis. PLoS ONE7(8),e44064 (2012).
- 12 McClain MR, Palomaki GE, Piper M, Haddow JE. A rapid-ACCE review of CYP2C9 and VKORC1 alleles testing to inform warfarin dosing in adults at elevated risk for thrombotic events to avoid serious bleeding. Genet. Med.10(2),89–98 (2008).
- 13 Wadelius M, Chen LY, Lindh JD et al. The largest prospective warfarin-treated cohort supports genetic forecasting. Blood113(4),784–792 (2009).
- 14 Geisen C, Watzka M, Sittinger K et al.VKORC1 haplotypes and their impact on the inter-individual and inter-ethnical variability of oral anticoagulation. Thromb. Haemost.94(4),773–779 (2005).
- 15 Wysowski DK, Nourjah P, Swartz L. Bleeding complications with warfarin use: a prevalent adverse effect resulting in regulatory action. Arch. Intern. Med.167(13),1414–1419 (2007).
- 16 Budnitz DS, Shehab N, Kegler SR, Richards CL. Medication use leading to emergency department visits for adverse drug events in older adults. Ann. Intern. Med.147(11),755–765 (2007).
- 17 Cross SS, Harrison RF, Kennedy RL. Introduction to neural networks. Lancet346(8982),1075–1079 (1995).
- 18 Dayhoff JE, Deleo JM. Artificial neural networks: opening the black box. Cancer91(8 Suppl.),S1615–S1635 (2001).
- 19 Tabaton M, Odetti P, Cammarata S et al. Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment. J. Alzheimers Dis.19(3),1035–1040 (2010).
- 20 Ansari D, Nilsson J, Andersson R, Regner S, Tingstedt B, Andersson B. Artificial neural networks predict survival from pancreatic cancer after radical surgery. Am. J. Surg.205(1),1–7 (2013).
- 21 Rughani AI, Dumont TM, Lu Z et al. Use of an artificial neural network to predict head injury outcome. J. Neurosurg.113(3),585–590 (2010).
- 22 Manotti C, Moia M, Palareti G, Pengo V, Ria L, Dettori AG. Effect of computer-aided management on the quality of treatment in anticoagulated patients: a prospective, randomized, multicenter trial of APROAT (automated program for oral anticoagulant treatment). Haematologica86(10),1060–1070 (2001).
- 23 Ageno W, Turpie AG. A randomized comparison of a computer-based dosing program with a manual system to monitor oral anticoagulant therapy. Thromb. Res.91(5),237–240 (1998).
- 24 Poller L. International normalized ratios (INR): the first 20 years. J. Thromb. Haemost.2(6),849–860 (2004).
- 25 Greenland S, Schwartzbaum JA, Finkle WD. Problems due to small samples and sparse data in conditional logistic regression analysis. Am. J. Epidemiol.151(5),531–539 (2000).
- 26 Penco S, Buscema M, Patrosso MC, Marocchi A, Grossi E. New application of intelligent agents in sporadic amyotrophic lateral sclerosis identifies unexpected specific genetic background. BMC Bioinformatics9,254 (2008).
- 27 Buscema M, Grossi E, Intraligi M, Garbagna N, Andriulli A, Breda M. An optimized experimental protocol based on neuro-evolutionary algorithms application to the classification of dyspeptic patients and to the prediction of the effectiveness of their treatment. Artif. Intell. Med.34(3),279–305 (2005).
- 28 Buscema M, Grossi E, Snowdon D et al. Artificial neural networks and artificial organisms can predict Alzheimer pathology in individual patients only on the basis of cognitive and functional status. Neuroinformatics2(4),399–416 (2004).
- 29 Haykin S. Neural networks: a Comprehensive Foundation. Prentice Hall PTR, NJ, USA (1998).
- 30 Gong IY, Tirona RG, Schwarz UI et al. Prospective evaluation of a pharmacogenetics-guided warfarin loading and maintenance dose regimen for initiation of therapy. Blood118(11),3163–3171 (2011).
- 31 International Warfarin Pharmacogenetics Consortium, Klein TE, Altman RB et al. Estimation of the warfarin dose with clinical and pharmacogenetic data. N. Engl. J. Med.360(8),753–764 (2009).
- 32 Lenzini P, Wadelius M, Kimmel S et al. Integration of genetic, clinical, and INR data to refine warfarin dosing. Clin. Pharmacol. Ther.87(5),572–578 (2010).
- 33 Millican EA, Lenzini PA, Milligan PE et al. Genetic-based dosing in orthopedic patients beginning warfarin therapy. Blood110(5),1511–1515 (2007).
- 34 Sconce EA, Khan TI, Wynne HA et al. The impact of CYP2C9 and VKORC1 genetic polymorphism and patient characteristics upon warfarin dose requirements: proposal for a new dosing regimen. Blood106(7),2329–2333 (2005).
- 35 Voora D, Eby C, Linder MW et al. Prospective dosing of warfarin based on cytochrome P-450 2C9 genotype. Thromb. Haemost.93(4),700–705 (2005).
- 36 Caraco Y, Blotnick S, Muszkat M. CYP2C9 genotype-guided warfarin prescribing enhances the efficacy and safety of anticoagulation: a prospective randomized controlled study. Clin. Pharmacol. Ther.83(3),460–470 (2008).
- 37 Anderson JL, Horne BD, Stevens SM et al. Randomized trial of genotype-guided versus standard warfarin dosing in patients initiating oral anticoagulation. Circulation116(22),2563–2570 (2007).
- 38 Zambon CF, Pengo V, Padrini R et al.VKORC1, CYP2C9 and CYP4F2 genetic-based algorithm for warfarin dosing: an Italian retrospective study. Pharmacogenomics12(1),15–25 (2011).
- 39 Gage BF, Eby C, Johnson JA et al. Use of pharmacogenetic and clinical factors to predict the therapeutic dose of warfarin. Clin. Pharmacol. Ther.84(3),326–331 (2008).
- 40 Moreno L, Piñeiro JD, Sánchez JL et al. Brain maturation estimation using neural classifier. IEEE Trans. Biomed. Eng.42(4),428–432 (1995).
- 41 Buscema M. Artificial neural networks and complex social systems. I. theory. Subst. Use Misuse33(1),v–xvii, 1–220 (1998).
- 42 Rumelhart DE, McClelland JL. Parallel Distributed Processing. Explorations in the Microstructure of Cognition: Foundations. MIT Press, MA, USA, 1 (1986).
- 43 Bridle JS. Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. In: Neuro-Computing: Algorithms, Architectures. NATO ASI Series F68. Fogelman-Soulié F, Hérault J (Eds). Springer-Verlag, NY, USA (1989).
- 44 Buscema M, Sacco PL. Feedforward networks in financial predictions: the future that modifies the present. Expert Syst.17(3),149–170 (2000).
- 45 Eikelboom JW, Connolly SJ, Brueckmann M et al. Dabigatran versus warfarin in patients with mechanical heart valves. N. Engl. J. Med.369(13),1206–1214 (2013).
- 101 The Human Cytochrome P450 (CYP) Allele Nomenclature Database. www.cypalleles.ki.se
- 102 US FDA: Table of Pharmacogenomic Biomarkers in Drug Labels. www.fda.gov/Drugs/ScienceResearch/ResearchAreas/Pharmacogenetics/ucm083378.htm