Searching the Resource Information Network
Are you sure you want to leave this community? Leaving the community will revoke any permissions you have been granted in this community.
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.
Pubmed ID: 30339708
Publication data is provided by the National Library of Medicine ® and PubMed ®. Data is retrieved from PubMed ® on a weekly schedule. For terms and conditions see the National Library of Medicine Terms and Conditions.
scikit-learn: machine learning in Python
View all literature mentionsDatabase and central repository for genetic, genomic, molecular and cellular phenotype data and clinical information about people who have participated in pharmacogenomics research studies. The data includes, but is not limited to, clinical and basic pharmacokinetic and pharmacogenomic research in the cardiovascular, pulmonary, cancer, pathways, metabolic and transporter domains. PharmGKB welcomes submissions of primary data from all research into genes and genetic variation and their effects on drug and disease phenotypes. PharmGKB collects, encodes, and disseminates knowledge about the impact of human genetic variations on drug response. They curate primary genotype and phenotype data, annotate gene variants and gene-drug-disease relationships via literature review, and summarize important PGx genes and drug pathways. PharmGKB is part of the NIH Pharmacogenomics Research Network (PGRN), a nationwide collaborative research consortium. Its aim is to aid researchers in understanding how genetic variation among individuals contributes to differences in reactions to drugs. A selected subset of data from PharmGKB is accessible via a SOAP interface. Downloaded data is available for individual research purposes only. Drugs with pharmacogenomic information in the context of FDA-approved drug labels are cataloged and drugs with mounting pharmacogenomic evidence are listed.
View all literature mentions