Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose (original) (raw)
Related papers
Pharmacogenetics: the science of predictive clinical pharmacology
2014
The study of pharmacogenetics has expanded from what were initially casual family-based clinical drug response observations, to a fully-fledged science with direct therapeutic applications, all within a time-span of less than 60 years. A wide spectrum of polymorphisms, located within several genes, are now recognised to influence pharmacokinetics and pharmacodynamics of the majority of drugs within our therapeutic armamentarium. This information forms the basis for the new development of pharmacogenetic genotyping tests, which can be used to predict the therapeutic and/or adverse effects of a specific drug in a particular patient. Pharmacogenetic-guided, patient targeted therapy has now become the developing fulcrum of personalized medicine, as it provides the best means to optimize benefit/risk ratio in pharmacological management.
Pharmacogenetics: From Bench to Byte— An Update of Guidelines
Clinical Pharmacology & Therapeutics, 2011
reports nature publishing group Currently, there are very few guidelines linking the results of pharmacogenetic tests to specific therapeutic recommendations. Therefore, the Royal Dutch Association for the Advancement of Pharmacy established the Pharmacogenetics Working Group with the objective of developing pharmacogenetics-based therapeutic (dose) recommendations. After systematic review of the literature, recommendations were developed for 53 drugs associated with genes coding for CYP2D6, CYP2C19, CYP2C9, thiopurine-S-methyltransferase (TPMT), dihydropyrimidine dehydrogenase (DPD), vitamin K epoxide reductase (VKORC1), uridine diphosphate glucuronosyltransferase 1A1 (UGT1A1), HLA-B44, HLA-B*5701, CYP3A5, and factor V Leiden (FVL).
Pharmacogenetics: From Bench to Byte
Clinical Pharmacology & Therapeutics, 2008
Despite initial enthusiasm, 1-3 the use of pharmacogenetics has remained limited to investigation in only a few clinical fields such as oncology and psychiatry. 4-8 The main reason is the paucity of scientific evidence to show that pharmacogenetic testing leads to improved clinical outcomes. 9,10 Moreover, for most pharmacogenetic tests (such as tests for genetic variants of cytochrome P450 enzymes) a detailed knowledge of pharmacology is a prerequisite for application in clinical practice, and both physicians and pharmacists might find it difficult to interpret the clinical value of pharmacogenetic test results. Guidelines that link the result of a pharmacogenetic test to therapeutic recommendations might help to overcome these problems, but such guidelines are only sparsely available. In 2001, an early step was taken to develop such guidelines for the therapeutic use of antidepressants, and these included CYP2D6-related dose recommendations drawn from pharmacokinetic study data. 11 However, the use of such recommendations in routine clinical practice remains difficult, because they are currently outside the ambit of the clinical environment and are not accessible during the decision-making process by physicians and pharmacists, namely the prescription and dispensing of drugs.
Genetics in Medicine, 2018
Biomedical databases combining electronic medical records and phenotypic and genomic data constitute a powerful resource for the personalization of treatment. To leverage the wealth of information provided, algorithms are required that systematically translate the contained information into treatment recommendations based on existing genotype-phenotype associations. Methods: We developed and tested algorithms for translation of preexisting genotype data of over 44,000 participants of the Estonian biobank into pharmacogenetic recommendations. We compared the results obtained by genome sequencing, exome sequencing, and genotyping using microarrays, and evaluated the impact of pharmacogenetic reporting based on drug prescription statistics in the Nordic countries and Estonia. Results: Our most striking result was that the performance of genotyping arrays is similar to that of genome sequencing, whereas exome sequencing is not suitable for pharmacogenetic predictions. Interestingly, 99.8% of all assessed individuals had a genotype associated with increased risks to at least one medication, and thereby the implementation of pharmacogenetic recommendations based on genotyping affects at least 50 daily drug doses per 1000 inhabitants. Conclusion: We find that microarrays are a cost-effective solution for creating preemptive pharmacogenetic reports, and with slight modifications, existing databases can be applied for automated pharmacogenetic decision support for clinicians.
Pharmacogenetics in warfarin therapy
2013
Warfarin is a challenging drug to dose accurately, especially during the initiation phase because of its narrow therapeutic range and large inter-individual variability. Therefore, the aim of this thesis was to investigate the use of pharmacogenetics and clinical data to improve warfarin therapy. Genetic variants in cytochrome P450 2C9 (CYP2C9) and vitamin K epoxide reductase (VKORC1) are known to influence warfarin dose. Therefore we developed a pharmacogenetic dosing algorithm to predict warfarin stable dose prospectively in a British population based on 456 patients who started warfarin in a hospital setting and validated it in 262 retrospectively recruited patients from a primary care setting. The pharmacogenetic algorithm which included CYP2C9*2, CYP2C9*3 and VKORC1-1693 together with body surface area, age and concomitant amiodarone use, explained 43% of warfarin dose variability. The mean absolute error of the dose predicted by the algorithm was 1.08 mg/day (95% CI 0.95-1.20)...
Pharmacogenetic application in drug development and clinical trials
Drug metabolism and disposition: the biological fate of chemicals, 2001
Pharmacogenetics examines the genetic characteristics of individuals to understand variations in response to therapeutics. This approach has the potential to significantly affect the development of new medicines. The application of pharmacogenetic principles could yield significant time and resource savings within the drug development process. In preclinical drug development, pharmacogenetics could be applied to compound screening and identifying potential side effects before entering full clinical testing. Subpopulations of patients with different drug responses and underlying genetic markers could be stratified in clinical trials by analyzing their genotype. These data can improve clinical trial design and offer the possibility of optimized drug prescription based on patient genotype. Pharmacogenetics can guide the development of therapeutic interventions by identifying nonresponder patient groups. Advances in high-throughput genotyping technologies have added potential by facilit...
Pharmacogenomics, 2011
medical practice . When planning this conference 2 years ago, we thought it would be interesting to synthesize some knowledge gained in the field of pharmacogenetics and pharmacogenomics in the last 50 years, in order to identify the current pharmacogenetic/ pharmaco genomic tests that could be used in routine medical practice. Our aim was to determine, through daily discussions involving all participants, which pharmaco genetic information might be useful for patient therapy. In addition, we wanted to attempt to make some recommendations on which pharmacogenetic tests should be performed in routine medicine and decide what advice we might give to physicians regarding some of these pharmacogenetic/pharmaco genomic tests. The conference could not cover the whole field of pharmaco genetics/pharmaco genomics. Therefore, we limited the program to examples that we considered the most clinically relevant in the field of oncology, cardio vascular diseases, adverse drug reactions (ADRs) and organ transplantation. This choice is naturally subjective, excluding large parts of pharmaco genetics/ pharmaco genomics such as neuropsychopharmacology, pain, addiction and rheumatology. We present herein our conclusions on pharmacogenetic information that might be useful in ten clinical situations: guidance recommendations on which tests to be performed, and advice to physicians concerning these tests.
2008
The genetic makeup affects drug responses to a greater extend. Personalized medicine deals with the prescription of specific therapeutic agent best suited for an individual based on the pharmacogenetic and pharmacogenomic information. By understanding the genetic variations in an individual, it becomes easy for a clinician to select the appropriate drug in an adequate dose. Genetic variations can influence drug action in many ways, the common ones being the drug metabolizing enzyme (CYP450), the site of drug action (receptors), and at the drug transporter levels (p-glycoprotein). Safety and efficacy of many commonly prescribed drugs like aspirin, isoniazid, omeprazole, warfarin, hydralazine etc are affected by the genetic makeup of individuals. Similarly, the pharmacotherapy of common diseases like asthma, hypertension, depression etc is also influenced by genetic variations. Pharmacogenomics can also offer benefits like proper determination of drug dosage, and production of better vaccines and can definitely reduce the healthcare costs and helps to enable drug safety by understanding the genetic profile of an individual. Integration of pharmacogenomic information into clinical practice will also require clinical trials to assess their clinical usefulness. The usefulness of pharmacogenomic data also depends upon the affordability, ease of application, and ease of interpreting the results etc.