Dataset Information

Warfarin maintenance dose prediction for Chinese after heart valve replacement by a feedforward neural network with equal stratified sampling.

ABSTRACT: Patients requiring low-dose warfarin are more likely to suffer bleeding due to overdose. The goal of this work is to improve the feedforward neural network model's precision in predicting the low maintenance dose for Chinese in the aspect of training data construction. We built the model from a resampled dataset created by equal stratified sampling (maintaining the same sample number in three dose-groups with a total of 3639) and performed internal and external validations. Comparing to the model trained from the raw dataset of 19,060 eligible cases, we improved the low-dose group's ideal prediction percentage from 0.7 to 9.6% and maintained the overall performance (76.4% vs. 75.6%) in external validation. We further built neural network models on single-dose subsets to invest whether the subsets samples were sufficient and whether the selected factors were appropriate. The training set sizes were 1340 and 1478 for the low and high dose subsets; the corresponding ideal prediction percentages were 70.2% and 75.1%. The training set size for the intermediate dose varied and was 1553, 6214, and 12,429; the corresponding ideal prediction percentages were 95.6, 95.1%, and 95.3%. Our conclusion is that equal stratified sampling can be a considerable alternative approach in training data construction to build drug dosing models in the clinic.

SUBMITTER: Ma W

PROVIDER: S-EPMC8253817 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundWarfarin is the most recommended oral anticoagulant after artificial mechanical valve replacement therapy. However, the narrow therapeutic window and varying safety and efficacy in individuals make dose determination difficult. It may cause adverse events such as hemorrhage or thromboembolism. Therefore, advanced algorithms are urgently required for the use of warfarin.ObjectiveTo establish a warfarin dose model for patients after prosthetic mechanical valve replacement in southern China in combination with clinical and genetic variables, and to improve the accuracy and ideal prediction percentage of the model.MethodsClinical data of 476 patients were tracked and recorded in detail. The gene polymorphisms of VKORC1 (rs9923231, rs9934438, rs7196161, and rs7294), CYP2C9 (rs1057910), CYP1A2 (rs2069514), GGCX (rs699664), and UGT1A1 (rs887829) were determined using Sanger sequencing. Multiple linear regressions were used to analyze the gene polymorphisms and the contribution of clinical data variables; the variables that caused multicollinearity were screened stepwise and excluded to establish an algorithm model for predicting the daily maintenance dose of warfarin. The ideal predicted percentage was used to test clinical effectiveness.ResultsA total of 395 patients were included. Univariate linear regression analysis suggested that CYP1A2 (rs2069514) and UGT1A1 (rs887829) were not associated with the daily maintenance dose of warfarin. The new algorithm model established based on multiple linear regression was as follows: Y = 1.081 - 0.011 (age) + 1.532 (body surface area)-0.807 (rs9923231 AA) + 1.788 (rs9923231 GG) + 0.530 (rs1057910 AA)-1.061 (rs1057910 AG)-0.321 (rs699664 AA). The model accounted for 61.7% of individualized medication differences, with an ideal prediction percentage of 69%.ConclusionGGCX (rs699664) may be a potential predictor of warfarin dose, and our newly established model is expected to guide the individualized use of warfarin in clinical practice in southern China.

Project description:WHAT IS ALREADY KNOWN ABOUT THIS SUBJECT * Genetic polymorphisms of VKORC1 and CYP2C9 are known to influence warfarin dosage. * Recent studies among Caucasians showed that polymorphisms of CYP4F2 also play a role in warfarin pharmacogenetics. * The contribution of CYP4F2 variants to the variability inwarfarin dose requirement in Chinese subjects remains to be investigated. WHAT THIS STUDY ADDS * This research was to study the effect of CYP4F2 variants on warfarin requirements in the Han Chinese population. * This study developed a multiple regression model including CYP2C9, VKORC1 3673G>A, CYP4F2 genotypes and age, weight, combination use of amiodarone which could explain 56.1% of the individual variability in warfarin dose CYP4F2 could explain 4% of the variance in warfarin dose. * We found that one novel genotypic polymorphism 5417G>T for Asp36Tyr, which was identified as an important marker of warfarin resistance, was absent in the Han Chinese population in our study. AIMS The objective of this study was to assess the effect of the CYP4F2 on the daily stable warfarin dose requirement in Han Chinese patients with mechanical heart valve replacement (MHVR). METHODS From March 2007 to November 2008, 222 Han Chinese MHVR patients were recruited in our study. VKORC1 3673G>A, 5417G>T, CYP2C9*3 and CYP4F2 rs2108622 were genotyped by using the polymerase chain reaction restriction fragment length polymorphism method (PCR-RFLP). Polymorphisms of VKORC1 9041G>A were detected by direct sequencing. Multiple linear regression analysis was used to investigate the contribution of CYP4F2. RESULTS The CYP4F2 rs2108622 CT/TT group took a significantly higher stable warfarin dose (3.2 mg day(-1)) than the CC group (2.9 mg day(-1), 95% CI 0.2, 1.0, P= 0.033). The multiple linear regression model included VKORC1 3673G>A, CYP2C9, CYP4F2 genotypes and clinical characteristics. The model could explain 56.1% of the variance in stable warfarin dose in Han Chinese patients with MHVR. CYP4F2 contributed about 4% to the variance in the warfarin dose. There was no variation in the SNPs of VKORC1 5417G>T. CONCLUSION CYP4F2 is a minor significant factor of individual variability in the stable warfarin dose in Han Chinese patients with MHVR. The effect of CYP2C9 and VKORC1 genotypes on variability in the stable warfarin dose had also been confirmed.

Project description:ObjectiveTo study the effect of cytochrome P-4504F2 ( CYP4 F2) gene polymorphism on the initial dose of warfarin in patients after mechanical heart valve replacement.MethodsWe collected 350 patients receiving warfarin after mechanical heart valve replacement from January 2013 to December 2015 in our hospital. According to the international standardized ratio (INR) ≥2 at the initial stage after surgery, the patients were divided into two groups: INR≥2 group and INR<2 group. We selected the blood samples of all the 350 patients with testing the CYP4 F2 gene type of each patient, and analyzed the effect of CYP4 F2 gene polymorphism on the initial dose of warfarin after mechanical heart valve replacement (the average daily dose during hospitalization of patients 5-10 days after mechanical heart valve replacement).ResultsThere was no statistical significance in the initial dose of warfarin among patients with different CYP4 F2 genotypes. However, warfarin dose was higher in CYP4 F2 TT genotype than in CYP4 F2 CC carriers ((3.37±0.68) mg vs. (2.94±0.74) mg, P<0.05) in INR≥2 group; In patients with the same genotype, the initial dose of warfarin in the CYP4 F2 CC ((4.02±0.58) mg vs. (2.94±0.74) mg) and CYP4 F2 CT genotypes ((4.15±0.88) mg vs. (3.18±0.82) mg) of INR<2 group was higher than that in INR≥2 group ( P<0.05). Gender, age, body mass index (BMI), comorbidities (hypertension, diabetes mellitus, coronary heart disease, atrial fibrillation), cytopigment P-450 2C9 ( CYP2 C9), CYP4 F2 and vitamin K peroxide-reductase complex 1 ( VKORC1) gene polymorphism and INR compliance were included in multiple linear regression analysis. The regression equation was as follows: warfarin initial dose (mg) =-8.634+0.352×BMI (kg/m 2) +1.102× CYP4 F2 genotype (CC or CT values 1, TT values 2) +2.147× VKORC1 (AA or AG values 1, GG values 2) +1.325×INR ( INR≥2 values 0, INR<2 values 1). The coefficient of determination ( R 2) of regression equation was 0.431 ( P<0.05).ConclusionCYP4 F2 gene polymorphism may affect the initial dose of warfarin in patients after heart valve replacement, and this effect is also affected by body characteristics and other factors.

Dataset Information

Warfarin maintenance dose prediction for Chinese after heart valve replacement by a feedforward neural network with equal stratified sampling.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets