scholarly journals Development of a system to support warfarin dose decisions using deep neural networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Heemoon Lee ◽  
Hyun Joo Kim ◽  
Hyoung Woo Chang ◽  
Dong Jung Kim ◽  
Jonghoon Mo ◽  
...  
Keyword(s):  
Neural Networks ◽  
Prediction Model ◽  
Learning Algorithm ◽  
Warfarin Dose ◽  
Repeated Administration ◽  
International Normalized Ratio ◽  
Prediction Algorithm ◽  
Dosing Algorithm ◽  
Warfarin Dosing ◽  
Warfarin Maintenance Dose

AbstractThe first aim of this study was to develop a prothrombin time international normalized ratio (PT INR) prediction model. The second aim was to develop a warfarin maintenance dose decision support system as a precise warfarin dosing platform. Data of 19,719 inpatients from three institutions was analyzed. The PT INR prediction algorithm included dense and recurrent neural networks, and was designed to predict the 5th-day PT INR from data of days 1–4. Data from patients in one hospital (n = 22,314) was used to train the algorithm which was tested with the datasets from the other two hospitals (n = 12,673). The performance of 5th-day PT INR prediction was compared with 2000 predictions made by 10 expert physicians. A generator of individualized warfarin dose-PT INR tables which simulated the repeated administration of varying doses of warfarin was developed based on the prediction model. The algorithm outperformed humans with accuracy terms of within ± 0.3 of the actual value (machine learning algorithm: 10,650/12,673 cases (84.0%), expert physicians: 1647/2000 cases (81.9%), P = 0.014). In the individualized warfarin dose-PT INR tables generated by the algorithm, the 8th-day PT INR predictions were within 0.3 of actual value in 450/842 cases (53.4%). An artificial intelligence-based warfarin dosing algorithm using a recurrent neural network outperformed expert physicians in predicting future PT INRs. An individualized warfarin dose-PT INR table generator which was constructed based on this algorithm was acceptable.

Evaluation of dosing and safety outcomes of low-dose prophylactic warfarin in children after cardiothoracic surgery

2020 ◽  
Vol 77 (13) ◽  
pp. 1018-1025
Author(s):  
Maura Harkin ◽  
Brittany Powers Shaddix ◽  
Stephen B Neely ◽  
Leigh A Peek ◽  
Katy Stephens ◽  
...  
Keyword(s):  
Low Dose ◽  
Warfarin Dose ◽  
International Normalized Ratio ◽  
Primary Objective ◽  
Cardiothoracic Surgery ◽  
Entire Study Period ◽  
Entire Study ◽  
Frequent Monitoring ◽  
Safety Outcomes ◽  
Warfarin Dosing

Abstract Purpose Prophylactic warfarin with an International Normalized Ratio (INR) goal of 1.5 to 2.0 is one antithrombotic therapy utilized in children after cardiothoracic surgery (CTS); published sources suggest a dose of 0.1 mg/kg per day to achieve this goal. However, few studies have evaluated dosing in this population. The purpose of this study was to evaluate dosing and safety outcomes in children receiving warfarin after CTS. Methods A descriptive, retrospective review was conducted to evaluate warfarin dosing and INR outcomes in patients 18 years of age or younger who underwent CTS and received prophylactic warfarin with an INR goal of 1.5 to 2.0 from January 2014 through December 2018. The primary objective was to determine the median initial warfarin dose. Secondary objectives included identifying the percentage of documented INR values that were outside the therapeutic range, the percentage of patients with therapeutic INRs at discharge, and the 30-day readmission rate. Results Twenty-six patients were included in the review. The median initial warfarin dosage was 0.07 mg/kg/d (interquartile range [IQR], 0.05-0.10 mg/kg/d). Of the total of 177 INR values collected during the entire study period, 67 (37.9%) were therapeutic, 64 (36.2%) were subtherapeutic, and 46 (26.0%) were supratherapeutic. Eighteen patients (69.2%) had at least 1 supratherapeutic INR at any point during the study period, most frequently on days 2 through 4 of therapy. At discharge, 11 patients (42.3%) had therapeutic INRs. Four patients (15.4%) were readmitted within 30 days, with bleeding documented in 2 patients during their readmission. Conclusion The majority of patients received an initial warfarin dose less than that specified in published recommendations but still had a supratherapeutic INR at least once during the study period. When initiating warfarin after CTS, a dosage of <0.1 mg/kg per day and frequent monitoring may be needed to achieve an INR goal of 1.5 to 2.0.

scholarly journals Preliminary outcomes of preemptive warfarin pharmacogenetic testing at a large rural healthcare center

2019 ◽  
Vol 76 (6) ◽  
pp. 387-397 ◽  
Author(s):  
Emili Leary ◽  
Murray Brilliant ◽  
Peggy Peissig ◽  
Sara Griesbach
Keyword(s):  
Care Service ◽  
Anticoagulation Therapy ◽  
Warfarin Dose ◽  
Standard Of Care ◽  
International Normalized Ratio ◽  
Preliminary Evaluation ◽  
Thromboembolic Events ◽  
Rural Healthcare ◽  
Pharmacogenetic Testing ◽  
Warfarin Dosing

Abstract Purpose As a preliminary evaluation of the outcomes of implementing pharmacogenetic testing within a large rural healthcare system, patients who received pre-emptive pharmacogenetic testing and warfarin dosing were monitored until June 2017. Summary Over a 20-month period, 749 patients were genotyped for VKORC1 and CYP2C9 as part of the electronic Medical Records and Genomics Pharmacogenetics (eMERGE PGx) study. Of these, 27 were prescribed warfarin and received an alert for pharmacogenetic testing pertinent to warfarin; 20 patients achieved their target international normalized ratio (INR) of 2.0–3.0, and 65% of these patients achieved target dosing within the recommended pharmacogenetic alert dose (± 0.5 mg/day). Of these, 10 patients had never been on warfarin prior to the alert and were further evaluated with regard to time to first stable target INR, bleeds and thromboembolic events, hospitalizations, and mortality. There was a general trend of faster time to first stable target INR when the patient was initiated at a warfarin dose within the alert recommendation versus a dose outside of the alert recommendation with a mean (± SD) of 34 (± 28) days versus 129 (± 117) days, respectively. No trends regarding bleeds, thromboembolic events, hospitalization, or mortality were identified with respect to the pharmacogenetic alert. The pharmacogenetic alert provided pharmacogenetic dosing information to prescribing clinicians and appeared to deploy appropriately with the correct recommendation based upon patient genotype. Conclusion Implementing pharmacogenetic testing as a standard of care service in anticoagulation monitoring programs may improve dosage regimens for patients on anticoagulation therapy.

Improved Artificial BP Neural Networks and Genetic Algorithm Used to Predict the Purity of the Artificial Synthetic Hydrotalcite

2007 ◽  
Vol 280-283 ◽  
pp. 495-498
Author(s):  
Qiang Luo ◽  
Qing Li Ren
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Prediction Model ◽  
Process Parameters ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Raw Material ◽  
Algorithm Analysis ◽  
Neural Net ◽  
Bp Neural Networks

A prediction model for purity of the artificial synthetic hydrotalcite under varied process parameters based on improved artificial back-propagation (BP) neural networks is developed. And the non-linear relationship between the hydrotalcite purity and the raw material adding amount of NaOH, MgCl2 and AlCl3 was established based on BP learning algorithm analysis and convergence improvement. The hydrotalcite purity can be predicted by means of the trained neural net. Thus, by virtue of the prediction model, the future hydrotalcite purity can be evaluated under random complicated raw material amounts. Moreover, the best processing technology is optimized using the genetic algorithm.

Effects of rare CYP2C9 alleles on stable warfarin doses in Chinese Han patients with atrial fibrillation

2020 ◽  
Vol 21 (14) ◽  
pp. 1021-1031
Author(s):  
Dongxu Wang ◽  
Da-Peng Dai ◽  
Hualan Wu ◽  
Jia Chong ◽  
You Lü ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Predictive Power ◽  
Warfarin Dose ◽  
Multivariate Regression Analysis ◽  
Chinese Patients ◽  
Chinese Han ◽  
Dosing Algorithm ◽  
Warfarin Dosing ◽  
Univariate Analyses

Aim: Gene polymorphisms are critical in warfarin dosing variation. Here, the role of rare CYP2C9 alleles on warfarin doses in Chinese Han patients was investigated. Methods: A retrospective study recruited 681 warfarin treated atrial fibrillation patients. The genetic and clinical data were collected. Dose-related variables were selected by univariate analyses and the warfarin-dosing algorithm was derived by multivariate regression analysis. Results: Three rare CYP2C9 alleles ( CYP2C9*13, *16 and *60) were associated with lower stable doses. Inclusion of the rare CYP2C9 alleles in the prediction model added an extra 3.7% warfarin dose predictive power. Conclusion: CYP2C9*13, *16 and *60 was associated with lower stable warfarin doses in Chinese patients. The algorithm including rare CYP2C9 alleles tends to more accurately predict stable warfarin doses.

scholarly journals Warfarin Interaction With Hepatic Cytochrome P-450 Enzyme-Inducing Anticonvulsants

2017 ◽  
Vol 24 (1) ◽  
pp. 172-178 ◽  
Author(s):  
Nathan P. Clark ◽  
Kim Hoang ◽  
Thomas Delate ◽  
John R. Horn ◽  
Daniel M. Witt
Keyword(s):  
Warfarin Therapy ◽  
Therapeutic Response ◽  
Warfarin Dose ◽  
Clinical Information ◽  
International Normalized Ratio ◽  
The Mean ◽  
Warfarin Dosing ◽  
Meaningful Interaction ◽  
Cytochrome P 450 ◽  
Hepatic Cytochrome

Initiation of cytochrome P-450 (CYP)-inducing anticonvulsant medications during warfarin therapy may decrease anticoagulant effect and necessitate frequent warfarin dose adjustments to maintain therapeutic response measured by the international normalized ratio (INR). Clinical information regarding interactions between warfarin and these medications is limited. This study investigated warfarin dose and INR response following CYP-inducing anticonvulsant initiation among chronic warfarin users. This retrospective, pre-post study included patients ≥18 years who were receiving chronic warfarin therapy and who initiated carbamazepine, oxcarbazepine, phenobarbital, or phenytoin between January 1, 2006, and December 31, 2013. Mean weekly warfarin dose/INR ratio and mean weekly warfarin dose were compared in the 90 days pre- and days post-anticonvulsant initiation periods. Of the 57 included patients, 34 (60%), 15 (26%), 6 (11%), and 2 (3%) patients purchased a prescription for carbamazepine, phenytoin, oxcarbazepine, and phenobarbital, respectively. Mean age was 70 years, 59% were female, and the majority were receiving chronic warfarin therapy for atrial fibrillation (39%) or venous thromboembolism (26%). The ratio of mean warfarin dose and INR increased significantly between the pre- and post-anticonvulsant initiation periods (from 13 mg/INR to 18 mg/INR, respectively, P ≤ .001) as did the mean weekly warfarin dose (from 33 mg to 37 mg, P = <.001). Warfarin dose and dose/INR ratio significantly increased after carbamazepine initiation (both P < .001), while oxcarbazepine, phenobarbital, and phenytoin initiation did not significantly affect warfarin dosing. Our results support the presence of a clinically meaningful interaction between warfarin and carbamazepine. Frequent INR monitoring and warfarin dose escalation are recommended in this setting.

scholarly journals Warfarin Dosing in a Patient withCYP2C9*3*3andVKORC1-1639 AAGenotypes

2014 ◽  
Vol 2014 ◽  
pp. 1-4
Author(s):  
Mark Johnson ◽  
Craig Richard ◽  
Renee Bogdan ◽  
Robert Kidd
Keyword(s):  
Vitamin K ◽  
Adverse Drug Events ◽  
Warfarin Dose ◽  
International Normalized Ratio ◽  
White Female ◽  
First Case ◽  
Increased Risk ◽  
Genes Encoding ◽  
Warfarin Dosing ◽  
Clinically Significant

Genetic factors most correlated with warfarin dose requirements are variations in the genes encoding the enzymes cytochrome P450 2C9 (CYP2C9) and vitamin K epoxide reductase (VKOR). Patients receiving warfarin who possess one or more genetic variations inCYP2C9andVKORC1are at increased risk of adverse drug events and require significant dose reductions to achieve a therapeutic international normalized ratio (INR). A 74-year-old white female with atrial fibrillation was initiated on a warfarin dose of 2 mg PO daily, which resulted in multiple elevated INR measurements and three clinically significant hemorrhagic events and four vitamin K antidote treatments over a period of less than two weeks. Genetic analysis later revealed that she had the homozygous variant genotypes ofCYP2C9*3*3andVKORC1-1639 AA. Warfarin dosing was subsequently restarted and stabilized at 0.5 mg PO daily with therapeutic INRs. This is the first case report of a white female with these genotypes stabilized on warfarin, and it highlights the value of pharmacogenetic testing prior to the initiation of warfarin therapy to maximize efficacy and minimize the risk of adverse drug events.

The impact of CYP2C9 and VKORC1 genetic polymorphism and patient characteristics upon warfarin dose requirements: proposal for a new dosing regimen

Blood ◽  
2005 ◽  
Vol 106 (7) ◽  
pp. 2329-2333 ◽  
Author(s):  
Elizabeth A. Sconce ◽  
Tayyaba I. Khan ◽  
Hilary A. Wynne ◽  
Peter Avery ◽  
Louise Monkhouse ◽  
...  
Keyword(s):  
Body Size ◽  
Warfarin Dose ◽  
Patient Characteristics ◽  
International Normalized Ratio ◽  
Dosing Regimen ◽  
Dose Requirement ◽  
Cyp2c9 Genotype ◽  
Daily Dose ◽  
Warfarin Dosing ◽  
The Impact

AbstractCurrent dosing algorithms do not account for genetic and environmental factors for warfarin dose determinations. This study investigated the contribution of age, CYP2C9 and VKORC1 genotype, and body size to warfarin-dose requirements. Studied were 297 patients with stable anticoagulation with a target international normalized ratio (INR) of 2.0 to 3.0. Genetic analyses for CYP2C9 (*2 and *3 alleles) and VKORC1 (-1639 polymorphism) were performed and venous INR and plasma R- and S-warfarin concentrations determined. The mean warfarin daily dose requirement was highest in CYP2C9 homozygous wild-type patients, compared with those with the variant *2 and *3 alleles (P &lt; .001) and highest in patients with the VKORC1 (position -1639) GG genotype compared with those with the GA genotype and the AA genotype (P &lt; .001). Mean warfarin daily dose requirements fell by 0.5 to 0.7 mg per decade between the ages of 20 to 90 years. Age, height, and CYP2C9 genotype significantly contributed to S-warfarin and total warfarin clearance, whereas only age and body size significantly contributed to R-warfarin clearance. The multivariate regression model including the variables of age, CYP2C9 and VKORC1 genotype, and height produced the best model for estimating warfarin dose (R2 = 55%). Based upon the data, a new warfarin dosing regimen has been developed. The validity of the dosing regimen was confirmed in a second cohort of patients on warfarin therapy.

scholarly journals Pharmacogenetic Warfarin Dosing Algorithm in the Russian Population

2019 ◽  
Vol 4 (3) ◽  
pp. 40-44
Author(s):  
T. A. Bairova ◽  
A. Yu. Sambyalova ◽  
L. V. Rychkova ◽  
E. A. Novikova ◽  
F. I. Belyalov ◽  
...  
Keyword(s):  
Ethnic Groups ◽  
Predictive Accuracy ◽  
Warfarin Dose ◽  
Absolute Error ◽  
International Normalized Ratio ◽  
Russian Population ◽  
Asian Patients ◽  
Performance Limitation ◽  
The Mean ◽  
Warfarin Dosing

Background. To date, there are many pharmacogenetic algorithms for selecting the dose of warfarin. However, there is very little information about the predictive accuracy of the algorithms. We decided to evaluate the predictive accuracy of the Gage algorithm, using a calculator, located on the web site (http://www.warfarindosing.org) in two ethnic groups (Caucasians and Asians), living in Russia.Aim. To compare the actual warfarin dose (AWD) to the calculated warfarin dose (CWD), using the algorithm in two ethnic groups taking warfarin.Materials and methods. We included 114 patients (66 Caucasians and 48 Asians): the mean age was60.91 ± 12.34 years; 61 (53.51 %) men, and 53 (46.49 %) women. The comparative characteristics of the algorithm were tested using the mean absolute error (MAE) between AWD and CWD, and percentage of patients, whose CWD fell within 20 % of AWD (percentage within 20 %). Genotyping for CYP2C9*2, CYP2C9*3, CYP4F*2 and VKORC1 was performed by real-time polymerase chain reaction (RT-PCR) method using Pharmacogenetics Warfarin reagent kits (DNA technology, Russia).Results. The Gage algorithm produced the predictive accuracy with MAE = 1.02 ± 0.16 mg/day and percentage within 20 % for Asian patients was 39.6 %. We obtained MAE = 1.33 ± 0.16 mg/day and percentage within 20 % for Caucasian patients was 40.9 %. In two ethnic groups (Caucasians and Asians) of the Russian population, overall performance of warfarin pharmacogenetic dosing by the Gage algorithm was similar.Conclusions. Despite the performance limitation of the current warfarin pharmacogenetic dosing Gage algorithm, constant international normalized ratio monitoring is important.

Current Models for Predicting Warfarin Maintenance Dose Do Not Work in an Ambulatory Venous Thromboembolism Patient Population.

Blood ◽  
2007 ◽  
Vol 110 (11) ◽  
pp. 302-302
Author(s):  
Philip Wells ◽  
Marc Rodger ◽  
Jennifer Fleming ◽  
Sarah Kassem
Keyword(s):  
Maintenance Dose ◽  
Patient Population ◽  
Pearson Correlation ◽  
Warfarin Dose ◽  
Correlation Coefficients ◽  
Therapeutic Index ◽  
P Value ◽  
Patient Response ◽  
Warfarin Dosing ◽  
Warfarin Maintenance Dose

Abstract Warfarin is the most widely used anticoagulant for the treatment of conditions such as deep vein thrombosis and pulmonary embolism. Warfarin has a narrow therapeutic index, and individual patient response to the drug is highly variable. Models to predict the maintenance dose have been published but not validated in independent populations (Kamali et al, Sconce et al, and Gage et al). Most of the prior data was derived in patients with atrial fibrillation and these may not be applicable to our predominantly ambulatory VTE population. The prior models incorporate a variety of factors that have been predicted to have an effect on warfarin dosing, such as age, height, and polymorphisms in the vitamin K epoxide reductase complex subunit 1 (VKORC1) and cytochrome P450 (CYP450) 2C9 enzyme. We enrolled 51 consecutive VTE patients on stable doses of warfarin as defined in the prior studies. As in those studies we excluded patients with known or suspected non-compliance, known liver disease and known congestive heart failure. All previously suggested predictive variables were collected. Mean warfarin dose, mean INRs, and gene polymorphisms were determined by previously described standard methods. In addition we are testing the recently identified coding VKORC1 Asp36Tyr polymorphism which predisposes to warfarin resistance. This study aimed to examine the accuracy of three previous models to predict individual warfarin dosing in pursuit of the development of a more accurate regression model. Preliminary results with the first 51 patients, through correlation analysis, indicate that none of the previous models provide an accurate prediction of warfarin maintenance dose. The mean maintenance dose of the patient population was 6.23mg. The doses predicted by the previous models were significantly lower at 4.4mg, 5.3mg, and 4.5mg for Kamali, Gage, and Sconce, respectively. The Pearson correlation coefficients were 0.047, 0.27, and 0.50, respectively. A preliminary model has been developed with a Pearson correlation coefficient of r=0.78, and a p-value <0.0001. The R2 value for the model was 61.5%. We have now recruited over 290 patients and are analysing the data. We will report more precise data on correlations with the other models and if a new model with a higher R2 can be determined it will be reported.

scholarly journals The Creating an Optimal Warfarin Nomogram (CROWN) Study

2012 ◽  
Vol 107 (01) ◽  
pp. 59-68 ◽  
Author(s):  
Todd S. Perlstein ◽  
Samuel Z. Goldhaber ◽  
Kerrie Nelson ◽  
Victoria Joshi ◽  
T. Morgan ◽  
...  
Keyword(s):  
Therapeutic Range ◽  
Significant Proportion ◽  
Warfarin Dose ◽  
Clinical Trial Registration ◽  
Therapeutic Anticoagulation ◽  
Dosing Algorithm ◽  
Epoxide Reductase ◽  
Secondary Endpoints ◽  
Warfarin Dosing ◽  
Dose Variability

SummaryA significant proportion of warfarin dose variability is explained by variation in the genotypes of the cytochrome P450 CYP2C9 and the vitamin K epoxide reductase complex, VKORC1, enzymes that influence warfarin metabolism and sensitivity, respectively. We sought to develop an optimal pharmacogenetic warfarin dosing algorithm that incorporated clinical and genetic information. We enroled patients initiating warfarin therapy. Genotyping was performed of the VKORC1, –1639G>A, the CYP2C9*2, 430C>T, and the CYP2C9*3, 1075C>A genotypes. The initial warfarin dosing algorithm (Algorithm A) was based upon established clinical practice and published warfarin pharmacogenetic information. Subsequent dosing algorithms (Algorithms B and Algorithm C) were derived from pharmacokinetic / pharmacodynamic (PK/PD) modelling of warfarin dose, international normalised ratio (INR), clinical and genetic factors from patients treated by the preceding algorithm(s). The primary outcome was the time in the therapeutic range, considered an INR of 1.8 to 3.2. A total of 344 subjects are included in the study analyses. The mean percentage time within the therapeutic range for each subject increased progressively from Algorithm A to Algorithm C from 58.9 (22.0), to 59.7 (23.0), to 65.8 (16.9) percent (p = 0.04). Improvement also occurred in most secondary endpoints, which included the per-patient percentage of INRs outside of the therapeutic range (p = 0.004), the time to the first therapeutic INR (p = 0.07), and the time to achieve stable therapeutic anticoagulation (p < 0.001). In conclusion, warfarin pharmacogenetic dosing can be optimised in real time utilising observed PK/PD information in an adaptive fashion.Clinical Trial Registration: ClinicalTrials.gov (NCT00401414)

Sign in / Sign up

Export Citation Format

Share Document