Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose

Warfarin dosing remains challenging due to narrow therapeutic index and highly individual variability. Incorrect warfarin dosing is associated with devastating adverse events. Remarkable efforts have been made to develop the machine learning based warfarin dosing algorithms incorporating clinical factors and genetic variants such as polymorphisms in CYP2C9 and VKORC1. The most widely validated pharmacogenetic algorithm is the IWPC algorithm based on multivariate linear regression (MLR). However, with only a single algorithm, the prediction performance may reach an upper limit even with optimal parameters. Here, we present novel algorithms using stacked generalization frameworks to estimate the warfarin dose, within which different types of machine learning algorithms function together through a meta-machine learning model to maximize the prediction accuracy. Compared to the IWPC-derived MLR algorithm, Stack 1 and 2 based on stacked generalization frameworks performed significantly better overall. Subgroup analysis revealed that the mean of the percentage of patients whose predicted dose of warfarin within 20% of the actual stable therapeutic dose (mean percentage within 20%) for Stack 1 was improved by 12.7% (from 42.47% to 47.86%) in Asians and by 13.5% (from 22.08% to 25.05%) in the low-dose group compared to that for MLR, respectively. These data suggest that our algorithms would especially benefit patients requiring low warfarin maintenance dose, as subtle changes in warfarin dose could lead to adverse clinical events (thrombosis or bleeding) in patients with low dose. Our study offers novel pharmacogenetic algorithms for clinical trials and practice.

[1]  Julie A. Johnson,et al.  Warfarin pharmacogenetics: a rising tide for its clinical value. , 2012, Circulation.

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

[3]  Hong-Hao Zhou,et al.  Comparison of Nine Statistical Model Based Warfarin Pharmacogenetic Dosing Algorithms Using the Racially Diverse International Warfarin Pharmacogenetic Consortium Cohort Database , 2015, PloS one.

[4]  Munir Pirmohamed,et al.  Warfarin pharmacogenetics: a single VKORC1 polymorphism is predictive of dose across 3 racial groups. , 2010, Blood.

[5]  Jeffrey L. Anderson,et al.  Effect of Genotype-Guided Warfarin Dosing on Clinical Events and Anticoagulation Control Among Patients Undergoing Hip or Knee Arthroplasty: The GIFT Randomized Clinical Trial , 2017, JAMA.

[6]  Ruobing Wang,et al.  Significantly Improving the Prediction of Molecular Atomization Energies by an Ensemble of Machine Learning Algorithms and Rescanning Input Space: A Stacked Generalization Approach , 2018 .

[7]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[8]  R. Desnick,et al.  Warfarin pharmacogenetics: CYP2C9 and VKORC1 genotypes predict different sensitivity and resistance frequencies in the Ashkenazi and Sephardi Jewish populations. , 2008, American journal of human genetics.

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

[10]  David Shaw,et al.  Using Machine Learning to Prescribe Warfarin , 2010, AIMSA.

[11]  Bin Jiang,et al.  Evolutionary Ensemble Learning Algorithm to Modeling of Warfarin Dose Prediction for Chinese , 2019, IEEE Journal of Biomedical and Health Informatics.

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

[13]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

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

[15]  M. Margaglione,et al.  A polymorphism in the VKORC1 gene is associated with an interindividual variability in the dose-anticoagulant effect of warfarin. , 2005, Blood.

[16]  Andreas Fregin,et al.  Mutations in VKORC1 cause warfarin resistance and multiple coagulation factor deficiency type 2 , 2004, Nature.

[17]  R L Berg,et al.  Integration of Genetic, Clinical, and INR Data to Refine Warfarin Dosing , 2010, Clinical pharmacology and therapeutics.

[18]  Jacques Turgeon,et al.  Clinical Practice Recommendations on Genetic Testing of CYP2C9 and VKORC1 Variants in Warfarin Therapy , 2015, Therapeutic drug monitoring.

[19]  Samuel Z Goldhaber,et al.  Warfarin dosing and cytochrome P450 2C9 polymorphisms , 2004, Thrombosis and Haemostasis.

[20]  Koroush Khalighi,et al.  Clinical Model for Predicting Warfarin Sensitivity , 2019, Scientific Reports.

[21]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.

[22]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[23]  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.

[24]  B. Horne,et al.  A Randomized and Clinical Effectiveness Trial Comparing Two Pharmacogenetic Algorithms and Standard Care for Individualizing Warfarin Dosing (CoumaGen-II) , 2012, Circulation.

[25]  Kuo-Chen Chou,et al.  Using stacked generalization to predict membrane protein types based on pseudo-amino acid composition. , 2006, Journal of theoretical biology.

[26]  Fan Wu,et al.  Predicting warfarin dosage from clinical data: A supervised learning approach , 2012, Artif. Intell. Medicine.

[27]  Tom Schalekamp,et al.  VKORC1 and CYP2C9 genotypes and acenocoumarol anticoagulation status: Interaction between both genotypes affects overanticoagulation , 2006, Clinical pharmacology and therapeutics.

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

[29]  Ian H. Witten,et al.  Stacked generalization: when does it work? , 1997, IJCAI 1997.