Warfarin Dose Prediction Research Articles

Construction of warfarin population pharmacokinetics and pharmacodynamics model in Han population based on Bayesian method

The purpose of this paper is to study the genetic polymorphisms of related gene loci (CYP2C9*3, VKORC1-1639G > A) based on demographic and clinical factors, and use the maximum a posterior Bayesian method to construct a warfarin individualized dose prediction model in line with the Chinese Han population. Finally, the built model is compared and analyzed with the widely used models at home and abroad. In this study, a total of 5467 INR measurements are collected from 646 eligible subjects in our hospital, and the maximum a posterior Bayesian method is used to construct a warfarin dose prediction that conforms to the Chinese Han population on the basis of the Hamberg model. The model is verified and compared with foreign models. This study finds that body weight and concomitant use of amiodarone have a significant effect on the anticoagulant effect of warfarin. The model can provide an effective basis for individualized and rational dosing of warfarin in Han population more accurately. In the performance of comparison with different warfarin dose prediction models, the new model has the highest prediction accuracy, and the prediction percentage is as high as 72.56%. The dose predicted by the Huang model is the closest to the actual dose of warfarin. The population pharmacokinetics and pharmacodynamics model established in this study can better reflect the distribution characteristics of INR values after warfarin administration in the Han population, and performs better than the models reported in the literature.

Advances in warfarin's anticoagulation therapy in Chinese population after mechanical valve replacement

Warfarin is an irreplaceable oral anticoagulant for patients with mechanical heart valves, the stable pharmacogenetic-based warfarin dose prediction algorithms have improved the effectiveness and safety of warfarin anticoagulation therapy. Genetic factors are the main factors affecting the stable dose of warfarin. Single nucleotide polymorphisms such as VKORC1 and CYP2C9 affect the anticoagulation effect of warfarin through pharmacodynamic or pharmacokinetic pathways. Age, body surface area, combined use of drugs, and other nongenetic factors also affect the stable dose of warfarin. Previously published algorithms for warfarin dose prediction included mainly the white race, and most algorithms were constructed using traditional multiple linear regression. However, domestic studies have used machine learning methods to construct warfarin dose prediction algorithms based on the Chinese Han post-mechanical valve replacement population and have achieved better prediction efficiency. This article reviews the advances of warfarin anticoagulation influencing factors and the clinical application of stable dose prediction algorithms.

Improved stacking ensemble learning based on feature selection to accurately predict warfarin dose.

With the rapid development of artificial intelligence, prediction of warfarin dose via machine learning has received more and more attention. Since the dose prediction involve both linear and nonlinear problems, traditional machine learning algorithms are ineffective to solve such problems at one time. Based on the characteristics of clinical data of Chinese warfarin patients, an improved stacking ensemble learning can achieve higher prediction accuracy. Information of 641 patients from southern China who had reached a steady state on warfarin was collected, including demographic information, medical history, genotype, and co-medication status. The dataset was randomly divided into a training set (90%) and a test set (10%). The predictive capability is evaluated on a new test set generated by stacking ensemble learning. Additional factors associated with warfarin dose were discovered by feature selection methods. A newly proposed heuristic-stacking ensemble learning performs better than traditional-stacking ensemble learning in key metrics such as accuracy of ideal dose (73.44%, 71.88%), mean absolute errors (0.11 mg/day, 0.13 mg/day), root mean square errors (0.18 mg/day, 0.20 mg/day) and R2 (0.87, 0.82). The developed heuristic-stacking ensemble learning can satisfactorily predict warfarin dose with high accuracy. A relationship between hypertension, a history of severe preoperative embolism, and warfarin dose is found, which provides a useful reference for the warfarin dose administration in the future.

Automated warfarin dose prediction for Asian, American, and Caucasian populations using a deep neural network

Existing warfarin dose prediction algorithms based on pharmacogenetics and clinical parameters have not been used clinically due to the absence of external validation, lack of assessment for clinical utility, and high risk of bias. Moreover, given the high degree of heterogeneity across different datasets used to develop these algorithms, it is unsurprising that prediction errors remain high, and dosing accuracy is dependent on specific ethnic populations. To circumvent these challenges, deep neural models are increasingly used to improve the precision and accuracy of warfarin dose predictions. Hence, this study sought to develop a deep learning-based model using a well-established curated dataset of over 6000 patients from the International Warfarin Pharmacogenomics Consortium (IWPC). Clinically-relevant input data such as physical attributes, medical conditions, concomitant medications, genotype status of functional warfarin genetic polymorphisms, and therapeutic INR were entered followed by applying a unique and robust training and validation method. The deep model yielded a low average mean absolute error (MAE) of 7.6 mg/week and a relatively low mean percentage of error of 40.9% in Asians, 14.2 mg/week MAE and 36.9% in African Americans, and 12.7 mg/week MAE and 45.4% mean percentage of error in White Caucasians. This model also resulted in 36.4% of all patients with a predicted dose within 20% of the administered dose. Hence, our proposed deep model provides an alternative to predicting warfarin dose in the clinical setting upon validation in ethnically-similar datasets.

Local Ancestry-Informed Candidate Pathway Analysis of Warfarin Stable Dose in Latino Populations.

Accuracy of warfarin dose prediction algorithms may be improved by including data from diverse populations in genetic studies of dose variability. Here, we surveyed single nucleotide polymorphisms in vitamin K-related genetic pathways for association with warfarin dose requirements in two admixed Latino populations in standard-principal component adjusted and contemporary-local ancestry adjusted regression models. A total of five variants from vitamin K-related genes/pathways were associated with warfarin dose in both cohorts (P < 0.0125) in standard models. Local ancestry-adjusted analysis unveiled 35 associated variants with absolute effects ranging from β=9.04 ( ±2.23) to 39.18 ( ±10.89) per ancestral allele in the discovery cohort and β=6.47 (± 2.02) to 17.82 (± 6.83) in the replication cohort. Importantly, we demonstrate the technical validity of the Tractor model in cohorts with admixed ancestry from three founder populations and bring attention to the technical hurdles obstructing the inclusion of diverse, especially admixed, populations in pharmacogenomic research.

Nonlinear Machine Learning in Warfarin Dose Prediction: Insights from Contemporary Modelling Studies.

Objective: This study aimed to systematically assess the characteristics and risk of bias of previous studies that have investigated nonlinear machine learning algorithms for warfarin dose prediction. Methods: We systematically searched PubMed, Embase, Cochrane Library, Chinese National Knowledge Infrastructure (CNKI), China Biology Medicine (CBM), China Science and Technology Journal Database (VIP), and Wanfang Database up to March 2022. We assessed the general characteristics of the included studies with respect to the participants, predictors, model development, and model evaluation. The methodological quality of the studies was determined, and the risk of bias was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). Results: From a total of 8996 studies, 23 were assessed in this study, of which 23 (100%) were retrospective, and 11 studies focused on the Asian population. The most common demographic and clinical predictors were age (21/23, 91%), weight (17/23, 74%), height (12/23, 52%), and amiodarone combination (11/23, 48%), while CYP2C9 (14/23, 61%), VKORC1 (14/23, 61%), and CYP4F2 (5/23, 22%) were the most common genetic predictors. Of the included studies, the MAE ranged from 1.47 to 10.86 mg/week in model development studies, from 2.42 to 5.18 mg/week in model development with external validation (same data) studies, from 12.07 to 17.59 mg/week in model development with external validation (another data) studies, and from 4.40 to 4.84 mg/week in model external validation studies. All studies were evaluated as having a high risk of bias. Factors contributing to the risk of bias include inappropriate exclusion of participants (10/23, 43%), small sample size (15/23, 65%), poor handling of missing data (20/23, 87%), and incorrect method of selecting predictors (8/23, 35%). Conclusions: Most studies on nonlinear-machine-learning-based warfarin prediction models show poor methodological quality and have a high risk of bias. The analysis domain is the major contributor to the overall high risk of bias. External validity and model reproducibility are lacking in most studies. Future studies should focus on external validity, diminish risk of bias, and enhance real-world clinical relevance.

A Post-Hoc Interpretable Ensemble Model to Feature Effect Analysis in Warfarin Dose Prediction for Chinese Patients.

To interprete the importance of clinical features and genotypes for warfarin daily dose prediction, we developed a post-hoc interpretable framework based on an ensemble predictive model. This framework includes permutation importance for global interpretation and local interpretable model-agnostic explanation (LIME) and shapley additive explanations (SHAP) for local explanation. The permutation importance globally ranks the importance of features on the whole data set. This can guide us to build a predictive model with less variables and the complexity of final predictive model can be reduced. LIME and SHAP together explain how the predictive model give the predicted dosage for specific samples. This help clinicians prescribe accurate doses to patients using more effective clinical variables. Results showed that both the permutation importance and SHAP demonstrated that VKORC1, age, serum creatinine (SCr), left atrium (LA) size, CYP2C9 and weight were the most important features on the whole data set. In specific samples, both SHAP and LIME discovered that in Chinese patients, wild-type VKORC1-AA, mutant-type CYP2C9*3, age over 60, abnormal LA size, SCr within the normal range, and using amiodarone definitely required dosage reduction, whereas mutant-type VKORC1-AG/GG, small age, SCr out of normal range, normal LA size, diabetes and heavy weight required dosage enhancementt.

External Evaluation of a Bayesian Warfarin Dose Optimization Based on a Kinetic-Pharmacodynamic Model.

Warfarin is a representative anticoagulant with large interindividual variability. The published kinetic-pharmacodynamic (K-PD) model allows the prediction of warfarin dose requirement in Swedish patients; however, its applicability in Japanese patients is not known. We evaluated the model's predictive performance in Japanese patients with various backgrounds and relationships using Bayesian parameter estimation and sampling times. A single-center retrospective observational study was conducted at Tokyo Women's Medical University, Medical Center East. The study population consisted of adult patients aged >20 years who commenced warfarin with a prothrombin time-international normalized ratio (PT-INR) from June 2015 to June 2019. The published K-PD model modified by Wright and Duffull was assessed using prediction-corrected visual predictive checks, focusing on clinical characteristics, including age, renal function, and individual prediction error. The external dataset included 232 patients who received an initial warfarin daily dose of 3.2 ± 1.28 mg with 2278 PT-INR points (median [range] follow-up period of 23 d [7-28]). Prediction-corrected visual predictive checks carried a propensity for underprediction. Additionally, age >60 years, body mass index ≤25 kg/m2, and estimated glomerular filtration rate ≤60 mL/min/1.73 m2 had a pronounced tendency to underpredict PT-INR. However, Bayesian prediction using four prior observations reduced underprediction. To improve the prediction performance of these special populations, further studies are required to construct a model to predict warfarin dose requirements in Japanese patients.

Building and analyzing machine learning-based warfarin dose prediction models using scikit-learn.

For personalized drug dosing, prediction models may be utilized to overcome the inter-individual variability. Multiple linear regression has been used as a conventional method to model the relationship between patient features and optimal drug dose. However, linear regression cannot capture non-linear relationships and may be adversely affected by non-normal distribution and collinearity of data. To overcome this hurdle, machine learning models have been extensively adapted in drug dose prediction. In this tutorial, random forest and neural network models will be trained in tandem with a multiple linear regression model on the International Warfarin Pharmacogenetics Consortium dataset using the scikit-learn python library. Subsequent model analyses including performance comparison, permutation feature importance computation and partial dependence plotting will be demonstrated. The basic methods of model training and analysis discussed in this article may be implemented in drug dose-related studies.

Stable warfarin dose prediction in sub-Saharan African patients: A machine-learning approach and external validation of a clinical dose-initiation algorithm.

Warfarin remains the most widely prescribed oral anticoagulant in sub‐Saharan Africa. However, because of its narrow therapeutic index, dosing can be challenging. We have therefore (a) evaluated and compared the performance of 21 machine‐learning techniques in predicting stable warfarin dose in sub‐Saharan Black‐African patients and (b) externally validated a previously developed Warfarin Anticoagulation in Patients in Sub‐Saharan Africa (War‐PATH) clinical dose–initiation algorithm. The development cohort included 364 patients recruited from eight outpatient clinics and hospital departments in Uganda and South Africa (June 2018–July 2019). Validation was conducted using an external validation cohort (270 patients recruited from August 2019 to March 2020 in 12 outpatient clinics and hospital departments). Based on the mean absolute error (MAE; mean of absolute differences between the actual and predicted doses), random forest regression (12.07 mg/week; 95% confidence interval [CI], 10.39–13.76) was the best performing machine‐learning technique in the external validation cohort, whereas the worst performing technique was model trees (17.59 mg/week; 95% CI, 15.75–19.43). By comparison, the simple, commonly used regression technique (ordinary least squares) performed similarly to more complex supervised machine‐learning techniques and achieved an MAE of 13.01 mg/week (95% CI, 11.45–14.58). In summary, we have demonstrated that simpler regression techniques perform similarly to more complex supervised machine‐learning techniques. We have also externally validated our previously developed clinical dose–initiation algorithm, which is being prospectively tested for clinical utility.

Abstract 13467: Using Data Analytics Toward Precision Warfarin Dosing in Children With Heart Disease

Introduction: Warfarin is the most common anticoagulant used in children with heart disease. Multiple factors make initial warfarin dose selection and management subjective and variable in children. This variability increases hospital length of stay and impacts efficacy and safety. We sought to develop a data-driven tool to optimize time to warfarin goal dose in children with heart disease. Methods: We collected all demographic and clinical data for all patients &lt;18 years who received warfarin at our institution. We developed a warfarin sensitivity metric (Δ International Normalized Ratio (INR)/mg warfarin) to assess individual medication processing and characterize influential factors. Each inpatient interaction with warfarin was analyzed to assess the impact of concomitant medications, hepatic impairment, and procedure type on dosing, sensitivity, and resultant INR. A linear regression model was formulated to predict ending warfarin dose based on these influential factors. Results: A total of 714 patients were identified; 334 patients met inclusion criteria, and 447 unique encounters with warfarin were analyzed. Warfarin sensitivity was 94.3% higher in patients receiving major anticoagulation enhancing drugs and 13.6% higher in patients with minor liver injury. Patients undergoing a Fontan procedure had increased warfarin sensitivity compared to other procedures; 60% and 66% increase from ventricular assist device and valve replacement, respectively. A linear regression model was used to predict a patient’s warfarin ed dose based on age, baseline INR, other medications, liver injury, and Fontan procedure status. The Fontan binary indicator and age were the most impactful in predicting end dose with an adjusted R 2 of 0.1792. Conclusions: We have identified multiple factors that could affect individualized warfarin. Further analysis will refine our warfarin sensitivity metric and finalize and validate our tool to allow accurate and efficient warfarin dose prediction.

Machine Learning for Prediction of Stable Warfarin Dose in US Latinos and Latin Americans.

Populations used to create warfarin dose prediction algorithms largely lacked participants reporting Hispanic or Latino ethnicity. While previous research suggests nonlinear modeling improves warfarin dose prediction, this research has mainly focused on populations with primarily European ancestry. We compare the accuracy of stable warfarin dose prediction using linear and nonlinear machine learning models in a large cohort enriched for US Latinos and Latin Americans (ULLA). Each model was tested using the same variables as published by the International Warfarin Pharmacogenetics Consortium (IWPC) and using an expanded set of variables including ethnicity and warfarin indication. We utilized a multiple linear regression model and three nonlinear regression models: Bayesian Additive Regression Trees, Multivariate Adaptive Regression Splines, and Support Vector Regression. We compared each model’s ability to predict stable warfarin dose within 20% of actual stable dose, confirming trained models in a 30% testing dataset with 100 rounds of resampling. In all patients (n = 7,030), inclusion of additional predictor variables led to a small but significant improvement in prediction of dose relative to the IWPC algorithm (47.8 versus 46.7% in IWPC, p = 1.43 × 10−15). Nonlinear models using IWPC variables did not significantly improve prediction of dose over the linear IWPC algorithm. In ULLA patients alone (n = 1,734), IWPC performed similarly to all other linear and nonlinear pharmacogenetic algorithms. Our results reinforce the validity of IWPC in a large, ethnically diverse population and suggest that additional variables that capture warfarin dose variability may improve warfarin dose prediction algorithms.

Genotype-Guided vs Clinically-Guided Stable Warfarin Dose Prediction and Stable Dose Establishment In A Predominantly Non-European Ancestry Population

ABSTRACT Background Warfarin dosing varies due to individual genetic and clinical factors. The utility of genotype‐guided warfarin dosing to improve stable warfarin dose is not extensively studied in non-European populations. Research design and methods Retrospective cohort study of patients initiating warfarin receiving genotype (PGx)‐guided or clinically guided dosing. Primary outcomes included dose discordance between estimated dose at discharge and eventual stable dose. Results No significant difference in warfarin dose discordance was observed (PGx: 9.1 ± 8.8 mg/week difference vs. Clinical: 7.9 ± 8.9 mg/week difference; P = 0.446). PGx‐guided dosing did not reduce time to achieve stable dose (1.8 ± 2.5 months vs. 2.1 ± 2.6 months; P = 0.508). Vitamin K intake level did not alter prediction accuracy or time to stable dose (PGx‐predicted: dose difference P = 0.493, time to stable dose P = 0.336; Clinically predicted: dose difference P = 0.145, time to dose INR P = 0.095). Conclusions PGx‐guided warfarin dosing did not improve eventual stable dose discordance or reduce the time to achieve stable dose in this predominantly non‐European cohort. Dietary vitamin K intake level did not impact warfarin dose discordance or time to achieve stable warfarin dose. Additional study is needed to identify populations that best benefit from PGx‐guided warfarin dosing.

Performance Evaluation of Warfarin Dose Prediction Algorithms and Effects of Clinical Factors on Warfarin Dose in Chinese Patients.

The clinical utility of warfarin dose prediction algorithms remains controversial, our purpose is to evaluate the performance of warfarin dose prediction algorithms and the effects of clinical factors on warfarin dose in Chinese patients. Clinical data of 217 patients who received warfarin treatment were used to assess 6 warfarin dose prediction algorithms (OHNO, IWPC [International Warfarin Pharmacogenetics Consortium], HUANG, KIM, BRESS, and MIAO). The predicted dose (PD) was compared with the warfarin optimal dose (WOD, defined as the dose that maintains the international normalized ratio within the target range of 2.0-3.0). A multiple regression analysis with WOD as the dependent variable was performed to evaluate the effects of clinical factors on warfarin dose. The mean absolute error analysis ranked the predictive accuracies of the algorithms as OHNO > IWPC > HUANG > KIM > BRESS > MIAO. Stratified analysis indicated that HUANG most accurately predicted that patients required lower WODs (≤3 mg/d), whereas OHNO was the most effective in predicting medium WODs (3-5 mg/d). KIM was effective in predicting high WODs (>5 mg/d). Multiple linear regression analysis showed that VKORC1 (rs9923231) and body mass index were significantly positively correlated with WOD, whereas concurrent atrial fibrillation status, CYP2C9*3 (rs1057910), and sex were significantly negatively correlated with WOD. In Chinese patients, OHNO should be given priority during the prediction and selection of warfarin dose. When using OHNO to predict warfarin dose (≤3 mg/d or >5 mg/d), HUANG or KIM algorithms can provide precise predictions. At the same time, physicians should pay close attention to clinical factors, such as VKORC1 (rs9923231), concurrent atrial fibrillation status, CYP2C9*3 (rs1057910), body mass index, and sex, to improve warfarin dose adjustment strategies in Chinese patients.

Comparison of multivariate linear regression and a machine learning algorithm developed for prediction of precision warfarin dosing in a Korean population

BackgroundPersonalized warfarin dosing is influenced by various factors including genetic and non‐genetic factors. Multiple linear regression (LR) is known as a conventional method to develop predictive models. Recently, machine learning approaches have been extensively implemented for warfarin dosing due to the hypothesis of non‐linear association between covariates and stable warfarin dose. ObjectiveTo extend the multiple linear regression algorithm for personalized warfarin dosing in a Korean population and compare with a machine learning‐‐based algorithm. MethodFrom this cohort study, we collected information on 650 patients taking warfarin who achieved steady state including demographic information, indications, comorbidities, comedications, habits, and genetic factors. The dataset was randomly split into training set (90%) and test set (10%). The LR and machine learning (gradient boosting machine [GBM]) models were developed on the training set and were evaluated on the test set. ResultLR and GBM models were comparable in terms of accuracy of ideal dose (75.38% and 73.85%), correlation (0.77 and 0.73), mean absolute error (0.58 mg/day and 0.64 mg/day), and root mean square error (0.82 mg/day and 0.9 mg/day), respectively. VKORC1 genotype, CYP2C9 genotype, age, and weight were the highest contributors and could obtain 80% of maximum performance in both models. ConclusionThis study shows that our LR and GMB models are satisfactory to predict warfarin dose in our dataset. Both models showed similar performance and feature contribution characteristics. LR may be the appropriate model due to its simplicity and interpretability.

An Adapted Neural-Fuzzy Inference System Model Using Preprocessed Balance Data to Improve the Predictive Accuracy of Warfarin Maintenance Dosing in Patients After Heart Valve Replacement.

Tailoring warfarin use poses a challenge for physicians and pharmacists due to its narrow therapeutic window and substantial inter-individual variability. This study aimed to create an adapted neural-fuzzy inference system (ANFIS) model using preprocessed balance data to improve the predictive accuracy of warfarin maintenance dosing in Chinese patients undergoing heart valve replacement (HVR). This retrospective study enrolled patients who underwent HVR between June 1, 2012, and June 1, 2016, from 35 centers in China. The primary outcomes were the mean difference between predicted warfarin dose by ANFIS models and actual dose and the models' predictive accuracy, including the ideal predicted percentage, the mean absolute error (MAE), and the mean squared error (MSE). The eligible cases were divided into training, internal validation, and external validation groups. We explored input variables by univariate analysis of a general linear model and created two ANFIS models using imbalanced and balanced training sets. We finally compared the primary outcomes between the imbalanced and balanced ANFIS models in both internal and external validation sets. Stratified analyses were conducted across warfarin doses (low, medium, and high doses). A total of 15,108 patients were included and grouped as follows: 12,086 in the imbalanced training set; 2820 in the balanced training set; 1511 in the internal validation set; and 1511 in the external validation set. Eight variables were explored as predictors related to warfarin maintenance doses, and imbalanced and balanced ANFIS models with multi-fuzzy rules were developed. The results showed a low mean difference between predicted and actual doses (< 0.3 mg/d for each model) and an accurate prediction property in both the imbalanced model (ideal prediction percentage, 74.39-78.16%; MAE, 0.37 mg/daily; MSE, 0.39 mg/daily) and the balanced model (ideal prediction percentage, 73.46-75.31%; MAE, 0.42 mg/daily; MSE, 0.43 mg/daily). Compared to the imbalanced model, the balanced model had a significantly higher prediction accuracy in the low-dose (14.46% vs. 3.01%; P < 0.001) and the high-dose warfarin groups (34.71% vs. 23.14%; P = 0.047). The results from the external validation cohort confirmed this finding. The ANFIS model can accurately predict the warfarin maintenance dose in patients after HVR. Through data preprocessing, the balanced model contributed to improved prediction ability in the low- and high-dose warfarin groups.

An ensemble learning based framework to estimate warfarin maintenance dose with cross-over variables exploration on incomplete data set

MotivationWarfarin is a widely used oral anticoagulant, but it is challenging to select the optimal maintenance dose due to its narrow therapeutic window and complex individual factor relationships. In recent years, machine learning techniques have been widely applied for warfarin dose prediction. However, the model performance always meets the upper limit due to the ignoration of exploring the variable interactions sufficiently. More importantly, there is no efficient way to resolve missing values when predicting the optimal warfarin maintenance dose. MethodsUsing an observational cohort from the Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine, we propose a novel method for warfarin maintenance dose prediction, which is capable of assessing variable interactions and dealing with missing values naturally. Specifically, we examine single variables by univariate analysis initially, and only statistically significant variables are included. We then propose a novel feature engineering method on them to generate the cross-over variables automatically. Their impacts are evaluated by stepwise regression, and only the significant ones are selected. Lastly, we implement an ensemble learning based approach, LightGBM, to learn from incomplete data directly on the selected single and cross-over variables for dosing prediction. Results377 unique patients with eligible and time-independent 1173 warfarin order events are included in this study. Through the comprehensive experimental results in 5-fold cross-validation, our proposed method demonstrates the efficiency of exploring the variable interactions and modeling on incomplete data. The R2 can achieve 75.0% on average. Moreover, the subgroup analysis results reveal that our method performs much better than other baseline methods, especially in the medium-dose and high-dose subgroups. Lastly, the IWPC dosing prediction model is used for further comparison, and our approach outperforms it by a significant margin. ConclusionIn summary, our proposed method is capable of exploring the variable interactions and learning from incomplete data directly for warfarin maintenance dose prediction, which has a great premise and is worthy of further research.

Evolutionary synthetic oversampling technique and cocktail ensemble model for warfarin dose prediction with imbalanced data

To improve the accuracy of warfarin daily dose prediction, we develop an evolutionary synthetic oversampling technique (ESMOTE) with a cocktail ensemble model (CEM) called ESMOTE-CEM. Different from conventional oversampling methods, ESMOTE finds the near-optimal oversampling parameters by evolving the parameter representation based on the pre-predicted warfarin dose and then synthesizes new samples to balance the data. The CEM, which improves the performance of random forest (RF) and boosted regression tree (BRT) models using a hybrid mechanism in the regression calculation, estimates the daily dose of warfarin. We test the ESMOTE-CEM on a dataset of 733 samples collected from the First Affiliated Hospital of Soochow University and the International Warfarin Pharmacogenetics Consortium (IWPC). The results show that ESMOTE outperformed the other oversampling methods by at least 6.98% for R2 and 5.03% for the mean squared error (MSE). In terms of the percentage of patients whose predicted warfarin dose is within 20% of the actual stable therapeutic dose (20%-p value), the ESMOTE-CEM achieves a 20%-p value of 50%. Moreover, compared to RF, BRT and AdaBoost models, the CEM is the most suitable base predictive model for ESMOTE.

Plasma miRNA profiles associated with stable warfarin dosage in Chinese patients

BackgroundWe used bioinformatic analysis and quantitative reverse transcription polymerase chain reaction (RT-qPCR) assays to investigate the association between plasma microRNAs (miRNAs) and stable warfarin dosage in a Chinese Han population.MethodsBioinformatics analysis was used to screen out potential warfarin dose-associated miRNAs. Three plasma miRNAs were validated in 99 samples by RT-qPCR. Kruskal–Wallis test and multivariate logistic regression were used to compare differences in plasma miRNAs expression levels between three warfarin dosage groups.ResultsThere were significant between-group differences among the three dose groups for hsa-miR-133b expression (p = 0.005), but we observed an “n-shaped” dose-dependent curve rather than a linear relationship. Expression levels of hsa-miR-24-3p (p = 0.475) and hsa-miR-1276 (p = 0.558) were not significantly different in the multivariate logistic regression.ConclusionmiRNAs have received extensive attention as ideal biomarkers and possible therapeutic targets for various diseases. However, they are not yet widely used in precision medicine. Our results indicate that hsa-miR-133b may be a possible reference factor for the warfarin dosage algorithm. These findings emphasize the importance of a comprehensive evaluation of complex relationships in warfarin dose prediction models and provide new avenues for future pharmacogenomics studies.

DBCSMOTE: a clustering-based oversampling technique for data-imbalanced warfarin dose prediction

BackgroundVitamin K antagonist (warfarin) is the most classical and widely used oral anticoagulant with assuring anticoagulant effect, wide clinical indications and low price. Warfarin dosage requirements of different patients vary largely. For warfarin daily dosage prediction, the data imbalance in dataset leads to inaccurate prediction on the patients of rare genotype, who usually have large stable dosage requirement. To balance the dataset of patients treated with warfarin and improve the predictive accuracy, an appropriate partition of majority and minority groups, together with an oversampling method, is required.MethodTo solve the data-imbalance problem mentioned above, we developed a clustering-based oversampling technique denoted as DBCSMOTE, which combines density-based spatial clustering of application with noise (DBCSCAN) and synthetic minority oversampling technique (SMOTE). DBCSMOTE automatically finds the minority groups by acquiring the association between samples in terms of the clinical features/genotypes and the warfarin dosage, and creates an extended dataset by adding the new synthetic samples of majority and minority groups. Meanwhile, two ensemble models, boosted regression tree (BRT) and random forest (RF), which are built on the extended dataset generateed by DBCSMOTE, accomplish the task of warfarin daily dosage prediction.ResultsDBCSMOTE and the comparison methods were tested on the datasets derived from our Hospital and International Warfarin Pharmacogenetics Consortium (IWPC). As the results, DBCSMOTE-BRT obtained the highest R-squared (R2) of 0.424 and the smallest mean squared error (mse) of 1.08. In terms of the percentage of patients whose predicted dose of warfarin is within 20% of the actual stable therapeutic dose (20%-p), DBCSMOTE-BRT can achieve the largest value of 47.8% among predictive models. The more important thing is that DBCSMOTE saved about 68% computational time to achieve the same or better performance than the Evolutionary SMOTE, which was the best oversampling method in warfarin dose prediction by far. Meanwhile, in warfarin dose prediction, it is discovered that DBCSMOTE is more effective in integrating BRT than RF for warfarin dose prediction.ConclusionOur finding is that the genotypes, CYP2C9 and VKORC1, no doubt contribute to the predictive accuracy. It was also discovered left atrium diameter, glutamic pyruvic transaminase and serum creatinine included in the model actually improved the predictive accuracy; When congestive heart failure, diabetes mellitus and valve replacement were absent in DBCSMOTE-BRT/RF, the predictive accuracy of DBCSMOTE-BRT/RF decreased. The oversampling ratio and number of minority clusters have a large impact on the effect of oversampling. According to our test, the predictive accuracy was high when the number of minority clusters was 6 ~ 8. The oversampling ratio for small minority clusters should be large (> 1.2) and for large minority clusters should be small (< 0.2). If the dataset becomes larger, the DBCSMOTE would be re-optimized and its BRT/RF model should be re-trained. DBCSMOTE-BRT/RF outperformed the current commonly-used tool called Warfarindosing. As compared to Evolutionary SMOTE-BRT and RF models, DBCSMOTE-BRT and RF models take only a small computational time to achieve the same or higher performance in many cases. In terms of predictive accuracy, RF is not as good as BRT. However, RF still has a powerful ability in generating a highly accurate model as the dataset increases; the software “WarfarinSeer v2.0” is a test version, which packed DBCSMOTE-BRT/RF. It could be a convenient tool for clinical application in warfarin treatment.