Personalized Warfarin Dosing by Genomics and Computational Intelligence
This study will create a computer program that can be used to help dose a drug called warfarin for the prevention of blood clotting. The study will collected specific information about those patients receiving this drug and use that information to create a computer program that will predict the effects of the drug. With this prediction program in place, the investigators can perform a series of "what if I gave this amount of drug" simulations to determine the best dose of drug for that patient. Once the computer programs are developed, the investigators will test the program in patients that actually need this drug. They will also include genetic information into the prediction since it has been shown that this information can affect how well the drug works. Patients will have this genetic information determined during this study.
|Study Design:||Endpoint Classification: Efficacy Study
Intervention Model: Single Group Assignment
Masking: Open Label
Primary Purpose: Health Services Research
|Official Title:||Personalized Warfarin Dosing Using Genomics and Computational Intelligence|
- Patient Genomics [ Time Frame: Baseline ] [ Designated as safety issue: No ]During Aim 2, Determined Patient Genotypes: CYP2C9 and VKORC1.
|Study Start Date:||September 2008|
|Study Completion Date:||September 2011|
|Primary Completion Date:||September 2011 (Final data collection date for primary outcome measure)|
Active Comparator: Genomics
Aim 1: Collect historical data on warfarin dosing in subjects at the VA. Aim 2: Collect genotype information on up to 300 subjects receiving warfarin anticoagulation.
Aim 3: Develop a computer model incorporating the information from Aim 1 and 2. Aim 4: Conduct randomized clinical trial.
Model predictive control is a computer based algorithm that can be applied to drug dosing. This computer tool uses a model of how a patient will respond to a drug dose based on demographic and historical dosing information to predict a new drug response. A drug dose controller applies all possible doses to the response model and selects the one dose that best meets the stated goals of the drug therapy. In the case of warfarin, we will calculate an international normalized ratio (INR) value within a specific target range.
The objective of this project is to develop new techniques to incorporate genomic data into pharmacodynamic models to improve the dosing of chronically administered drugs. Specifically, the investigators look to improve warfarin therapy by decreasing the variability in the effect of this drug using information about the subjects genotype and computational intelligence. The investigators propose to achieve our objectives using a prospective, randomized, controlled clinical trial of a computer program that they will develop from both historical and prospective data. This computer program will be tested against a control group using standard warfarin dosing, and a group using standard dosing plus subject genotype. Warfarin dose and response data will be obtained from patients seen in the Louisville VA anticoagulation clinic. Following informed consent, subject genotype for cytochrome P450 allele 2C9 (2C9) and vitamin K epoxide reductase complex subunit 1 (VKORC1) will be determined. Other data routinely obtained to aid in warfarin dosing will also be recorded. Using this information, the investigators will develop many different models for warfarin dosing using incrementally more information. Each of these models will be tested using computer simulation until they have obtained the best model. This model will be used in a pilot study to test performance in real time. The results of the pilot study will then be used to power a final clinical trial of standard dosing, standard dosing and genetic information, computer dosing, and computer dosing plus genetic information.
The specific aims of this research are:
- Determine the structure and the type of neural network model for predictions from historically obtained data. (Computer Model)
- Prospectively develop an individualized neural network and nonlinear mixed effect modelling (NONMEM) model capable of predicting erythropoietin dosing for chronic in-center hemodialysis patients using adaptive techniques.
- Develop computer programs based on neural computing that can be used in a clinical setting. (Computer Model)
- Determine the utility of the computer programs prospectively in the clinical setting.
|United States, Kentucky|
|VA Medical Center, Louisville|
|Louisville, Kentucky, United States, 40206|
|Principal Investigator:||Michael E. Brier, PhD||VA Medical Center, Louisville|