This study compared multipleimputation (MI) algorithms in a one-compartment pharmacokinetic (PK) scenario with oral absorption. Four covariates (two continuous, two dichotomous) linked to PK parameters were randomly ...
详细信息
This study compared multipleimputation (MI) algorithms in a one-compartment pharmacokinetic (PK) scenario with oral absorption. Four covariates (two continuous, two dichotomous) linked to PK parameters were randomly removed under a missing completely at random (MCAR) mechanism. The aim was to identify which algorithm best preserves covariate distributions and PK parameter estimates. The original dataset included 100 individuals, each with five sampling occasions. Missing data were introduced at 5%, 20%, 50%, and 75% for the four covariates under the MCAR assumption. Five MI algorithms (Mice, Amelia, missForest, rMIDAS, XGBoost) were tested. Absolute and relative errors and concordance metrics were used to assess performance. Population and individual parameter estimates were compared across imputed and original datasets using Monolix2024R1 (R). MissForest (MF) and Amelia yielded lower errors for continuous covariates whereas dichotomous variables were poorly imputed. Based on objective function values, Mice perform best at 5% and MF at 20% of missingness. Increasing missingness decreased covariate effects and increased the estimated inter-individual variances. Individual parameter estimation accurately captured individual-level variability across all imputed datasets. MI methods appear effective for covariate imputation in PK modeling, offering reliable results up to 20% missingness under an MCAR mechanism. Future research should explore refined strategies, including advanced modeling frameworks and Bayesian approaches for imputation. Enhancing our understanding of missing data processes will be crucial for robust PK analyses across diverse clinical settings.
Missing data is a common cause of uncertainty in reservoir characterization, especially in core analysis of porosity and permeability. This is due to the high cost and time required to gather core samples while drilli...
详细信息
Missing data is a common cause of uncertainty in reservoir characterization, especially in core analysis of porosity and permeability. This is due to the high cost and time required to gather core samples while drilling through the entire reservoir thickness. Therefore, the ability to collect core samples and directly assess petrophysical parameters is restricted by the small proportion of the reservoir thickness that can be measured by the retrieved cores. As a result, the absence of data has the potential to lead to inconsistent and imprecise classification of reservoirs and geomodeling, thereby increasing reservoir uncertainty. Therefore, imputationalgorithms are needed to estimate petrophysical properties for incomplete intervals. This study comprehensively compares seven imputation techniques for predicting missing horizontal and vertical core permeability and core porosity data in a well drilled through a carbonate reservoir in a southern Iraqi gas field. The performance of each method was assessed using relative bias (RB) and reasonable descriptive statistical distributions (histogram, log view, and box plots of data ratios to compare the imputed and original data), and robustness to outliers (RtO). The results revealed that the random imputation of missing data (RIMD) technique is the most effective algorithm in addressing the 30.5% missing data (vertical permeability), resulting in the attainment of the RB value closest to zero (0.04076191) compared to other algorithms. Principal component analysis (PCA) and random forest (RF) yielded the most favorable results in terms of handling missing values and outliers for the 15% missing ratio dataset (core porosity and horizontal permeability). The advantages of these approaches are related to their capacity to independently and accurately impute the missing data without requiring extra information, such as well logging records. Additionally, the multipleimputation and machine learning algorithms fill missing val
暂无评论