Dataset Information

Interactive modeling for ongoing utility of pharmacogenetic diagnostic testing: application for warfarin therapy.

ABSTRACT: BACKGROUND:The application of pharmacogenetic results requires demonstrable correlations between a test result and an indicated specific course of action. We developed a computational decision-support tool that combines patient-specific genotype and phenotype information to provide strategic dosage guidance. This tool, through estimating quantitative and temporal parameters associated with the metabolism- and concentration-dependent response to warfarin, provides the necessary patient-specific context for interpreting international normalized ratio (INR) measurements. METHODS:We analyzed clinical information, plasma S-warfarin concentration, and CYP2C9 (cytochrome P450, family 2, subfamily C, polypeptide 9) and VKORC1 (vitamin K epoxide reductase complex, subunit 1) genotypes for 137 patients with stable INRs. Plasma S-warfarin concentrations were evaluated by VKORC1 genotype (-1639G>A). The steady-state plasma S-warfarin concentration was calculated with CYP2C9 genotype-based clearance rates and compared with actual measurements. RESULTS:The plasma S-warfarin concentration required to yield the target INR response is significantly (P < 0.05) associated with VKORC1 -1639G>A genotype (GG, 0.68 mg/L; AG, 0.48 mg/L; AA, 0.27 mg/L). Modeling of the plasma S-warfarin concentration according to CYP2C9 genotype predicted 58% of the variation in measured S-warfarin concentration: Measured [S-warfarin] = 0.67(Estimated [S-warfarin]) + 0.16 mg/L. CONCLUSIONS:The target interval of plasma S-warfarin concentration required to yield a therapeutic INR can be predicted from the VKORC1 genotype (pharmacodynamics), and the progressive changes in S-warfarin concentration after repeated daily dosing can be predicted from the CYP2C9 genotype (pharmacokinetics). Combining the application of multivariate equations for estimating the maintenance dose with genotype-guided pharmacokinetics/pharmacodynamics modeling provides a powerful tool for maximizing the value of CYP2C9 and VKORC1 test results for ongoing application to patient care.

SUBMITTER: Linder MW

PROVIDER: S-EPMC3131846 | biostudies-literature | 2009 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interactive modeling for ongoing utility of pharmacogenetic diagnostic testing: application for warfarin therapy.

Linder Mark W MW Bon Homme Marjorie M Reynolds Kristen K KK Gage Brian F BF Eby Charles C Silvestrov Natalia N Valdes Roland R

Clinical chemistry 20090813 10

<h4>Background</h4>The application of pharmacogenetic results requires demonstrable correlations between a test result and an indicated specific course of action. We developed a computational decision-support tool that combines patient-specific genotype and phenotype information to provide strategic dosage guidance. This tool, through estimating quantitative and temporal parameters associated with the metabolism- and concentration-dependent response to warfarin, provides the necessary patient-sp ...[more]

PMID: 19679631

Similar Datasets

Project description:ObjectiveMultiple linear regression (MLR) and machine learning techniques in pharmacogenetic algorithm-based warfarin dosing have been reported. However, performances of these algorithms in racially diverse group have never been objectively evaluated and compared. In this literature-based study, we compared the performances of eight machine learning techniques with those of MLR in a large, racially-diverse cohort.MethodsMLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied in warfarin dose algorithms in a cohort from the International Warfarin Pharmacogenetics Consortium database. Covariates obtained by stepwise regression from 80% of randomly selected patients were used to develop algorithms. To compare the performances of these algorithms, the mean percentage of patients whose predicted dose fell within 20% of the actual dose (mean percentage within 20%) and the mean absolute error (MAE) were calculated in the remaining 20% of patients. The performances of these techniques in different races, as well as the dose ranges of therapeutic warfarin were compared. Robust results were obtained after 100 rounds of resampling.ResultsBART, MARS and SVR were statistically indistinguishable and significantly out performed all the other approaches in the whole cohort (MAE: 8.84-8.96 mg/week, mean percentage within 20%: 45.88%-46.35%). In the White population, MARS and BART showed higher mean percentage within 20% and lower mean MAE than those of MLR (all p values < 0.05). In the Asian population, SVR, BART, MARS and LAR performed the same as MLR. MLR and LAR optimally performed among the Black population. When patients were grouped in terms of warfarin dose range, all machine learning techniques except ANN and LAR showed significantly higher mean percentage within 20%, and lower MAE (all p values < 0.05) than MLR in the low- and high- dose ranges.ConclusionOverall, machine learning-based techniques, BART, MARS and SVR performed superior than MLR in warfarin pharmacogenetic dosing. Differences of algorithms' performances exist among the races. Moreover, machine learning-based algorithms tended to perform better in the low- and high- dose ranges than MLR.

Dataset Information

Interactive modeling for ongoing utility of pharmacogenetic diagnostic testing: application for warfarin therapy.

Publications

Interactive modeling for ongoing utility of pharmacogenetic diagnostic testing: application for warfarin therapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets