Warfarin Maintenance Dose Prediction for Patients Undergoing Heart Valve Replacement- a Hybrid Model with Genetic Algorithm and Back-Propagation Neural Network

Overview

Journal Sci Rep

Specialty Science

Date 2018 Jun 28

PMID 29946101

Citations 8

Authors

Qian Li

Huan Tao

Jing Wang

Qin Zhou

Jie Chen

Wen Zhe Qin

Li Dong

Bo Fu

Jiang Long Hou

Jin Chen

Wei-Hong Zhang

Affiliations

Soon will be listed here.

Abstract

Warfarin is the most recommended anticoagulant drug for patients undergoing heart valve replacement. However, due to the narrow therapeutic window and individual dose, the use of warfarin needs more advanced technology. We used the data collected from a multi-central registered clinical system all over China about the patients who have undergone heart valve replacement, subsequently divided into three groups (training group: 10673 cases; internal validation group: 3558 cases; external validation group: 1463 cases) in order to construct a hybrid model with genetic algorithm and Back-Propagation neural network (BP-GA), For testing the model's prediction accuracy, we used Mean absolute error (MAE), Root mean squared error (RMSE) and the ideal predicted percentage of total and dose subgroups. In results, whether in internal or in external validation group, the total ideal predicted percentage was over 58% while the intermediate dose subgroup manifested the best. Moreover, it showed higher prediction accuracy, lower MAE value and lower RMSE value in the external validation group than that in the internal validation group (p < 0.05). In conclusion, BP-GA model is promising to predict warfarin maintenance dose.

Citing Articles

Dose prediction for cervical cancer in radiotherapy based on the beam channel generative adversarial network.

Xie H, Tan T, Zhang H, Li Q Heliyon. 2024; 10(18):e37472.

PMID: 39309882 PMC: 11415707. DOI: 10.1016/j.heliyon.2024.e37472.

Optimizing warfarin dosing for patients with atrial fibrillation using machine learning.

Petch J, Nelson W, Wu M, Ghassemi M, Benz A, Fatemi M Sci Rep. 2024; 14(1):4516.

PMID: 38402362 PMC: 10894214. DOI: 10.1038/s41598-024-55110-9.

Evaluation of Machine Learning Approaches for Predicting Warfarin Discharge Dose in Cardiac Surgery Patients: Retrospective Algorithm Development and Validation Study.

Dryden L, Song J, Valenzano T, Yang Z, Debnath M, Lin R JMIR Cardio. 2023; 7:e47262.

PMID: 38055310 PMC: 10733832. DOI: 10.2196/47262.

Nonlinear Machine Learning in Warfarin Dose Prediction: Insights from Contemporary Modelling Studies.

Zhang F, Liu Y, Ma W, Zhao S, Chen J, Gu Z J Pers Med. 2022; 12(5).

PMID: 35629140 PMC: 9147332. DOI: 10.3390/jpm12050717.

Development of a system to support warfarin dose decisions using deep neural networks.

Lee H, Kim H, Chang H, Kim D, Mo J, Kim J Sci Rep. 2021; 11(1):14745.

PMID: 34285309 PMC: 8292496. DOI: 10.1038/s41598-021-94305-2.

References

Li X, Liu R, Luo Z, Yan H, Huang W, Yin J . Comparison of the predictive abilities of pharmacogenetics-based warfarin dosing algorithms using seven mathematical models in Chinese patients. Pharmacogenomics. 2015; 16(6):583-90. DOI: 10.2217/pgs.15.26. View

Ugrinowitsch C, Fellingham G, Ricard M . Limitations of ordinary least squares models in analyzing repeated measures data. Med Sci Sports Exerc. 2004; 36(12):2144-8. DOI: 10.1249/01.mss.0000147580.40591.75. View

Dong L, Shi Y, Tian Z . [The follow-up of 12 pregnant women with anticoagulation therapy after mechanical heart valve replacement]. Zhonghua Fu Chan Ke Za Zhi. 2002; 36(8):465-7. View

Scott R, Kersten B, Basior J, Nadler M . Evaluation of Fixed-Dose Four-Factor Prothrombin Complex Concentrate for Emergent Warfarin Reversal in Patients with Intracranial Hemorrhage. J Emerg Med. 2018; 54(6):861-866. DOI: 10.1016/j.jemermed.2018.01.030. View

Ageno W, Johnson J, Nowacki B, Turpie A . A computer generated induction system for hospitalized patients starting on oral anticoagulant therapy. Thromb Haemost. 2000; 83(6):849-52. View

Yu L, Song H, Zeng Z, Wang Q, Qiu H . [Validation and comparison of pharmacogenetics-based warfarin dosing algorithms in Han Chinese patients]. Zhonghua Xin Xue Guan Bing Za Zhi. 2012; 40(7):614-9. View

Whitlock R, Sun J, Fremes S, Rubens F, Teoh K . Antithrombotic and thrombolytic therapy for valvular disease: Antithrombotic Therapy and Prevention of Thrombosis, 9th ed: American College of Chest Physicians Evidence-Based Clinical Practice Guidelines. Chest. 2012; 141(2 Suppl):e576S-e600S. PMC: 3278057. DOI: 10.1378/chest.11-2305. View

Wang S, Franklin J, Glynn R, Schneeweiss S, Eddings W, Gagne J . Prediction of rates of thromboembolic and major bleeding outcomes with dabigatran or warfarin among patients with atrial fibrillation: new initiator cohort study. BMJ. 2016; 353:i2607. PMC: 4878389. DOI: 10.1136/bmj.i2607. View

Mega J, Walker J, Ruff C, Vandell A, Nordio F, Deenadayalu N . Genetics and the clinical response to warfarin and edoxaban: findings from the randomised, double-blind ENGAGE AF-TIMI 48 trial. Lancet. 2015; 385(9984):2280-7. DOI: 10.1016/S0140-6736(14)61994-2. View

10.

Groszek B, Piszczek P . [Vitamin K antagonists overdose]. Przegl Lek. 2016; 72(9):468-71. View

11.

Li H, Lai L, Chen L, Lu C, Cai Q . The prediction in computer color matching of dentistry based on GA+BP neural network. Comput Math Methods Med. 2015; 2015:816719. PMC: 4385598. DOI: 10.1155/2015/816719. View

12.

Wei Z, Wang W, Bradfield J, Li J, Cardinale C, Frackelton E . Large sample size, wide variant spectrum, and advanced machine-learning technique boost risk prediction for inflammatory bowel disease. Am J Hum Genet. 2013; 92(6):1008-12. PMC: 3675261. DOI: 10.1016/j.ajhg.2013.05.002. View

13.

Levine M, Pizon A, Padilla-Jones A, Ruha A . Warfarin overdose: a 25-year experience. J Med Toxicol. 2014; 10(2):156-64. PMC: 4057544. DOI: 10.1007/s13181-013-0378-8. View

14.

Limdi N, Beasley T, Baird M, Goldstein J, McGwin G, Arnett D . Kidney function influences warfarin responsiveness and hemorrhagic complications. J Am Soc Nephrol. 2009; 20(4):912-21. PMC: 2663833. DOI: 10.1681/ASN.2008070802. View

15.

Lip G, Al-Saady N, Jin J, Sun M, Melino M, Winters S . Anticoagulation Control in Warfarin-Treated Patients Undergoing Cardioversion of Atrial Fibrillation (from the Edoxaban Versus Enoxaparin-Warfarin in Patients Undergoing Cardioversion of Atrial Fibrillation Trial). Am J Cardiol. 2017; 120(5):792-796. DOI: 10.1016/j.amjcard.2017.06.005. View

16.

Gu Q, Kong Y, Schneede J, Xiao Y, Chen L, Zhong Q . VKORC1-1639G>A, CYP2C9, EPHX1691A>G genotype, body weight, and age are important predictors for warfarin maintenance doses in patients with mechanical heart valve prostheses in southwest China. Eur J Clin Pharmacol. 2010; 66(12):1217-27. DOI: 10.1007/s00228-010-0863-9. View

17.

Kimura M, Wasaki Y, Ogawa H, Nakatsuka M, WAKEYAMA T, Iwami T . Effect of low-intensity warfarin therapy on left atrial thrombus resolution in patients with nonvalvular atrial fibrillation: a transesophageal echocardiographic study. Jpn Circ J. 2001; 65(4):271-4. DOI: 10.1253/jcj.65.271. View

18.

Sharabiani A, Bress A, Douzali E, Darabi H . Revisiting Warfarin Dosing Using Machine Learning Techniques. Comput Math Methods Med. 2015; 2015:560108. PMC: 4471424. DOI: 10.1155/2015/560108. View

19.

Anderson J, Horne B, Stevens S, Grove A, Barton S, Nicholas Z . Randomized trial of genotype-guided versus standard warfarin dosing in patients initiating oral anticoagulation. Circulation. 2007; 116(22):2563-70. DOI: 10.1161/CIRCULATIONAHA.107.737312. View

20.

Lopez J, Fernandez-Hidalgo N, Revilla A, Vilacosta I, Tornos P, Almirante B . Internal and external validation of a model to predict adverse outcomes in patients with left-sided infective endocarditis. Heart. 2011; 97(14):1138-42. DOI: 10.1136/hrt.2010.200295. View