Adjusted adaptive Lasso for covariate model-building in nonlinear mixed-effect pharmacokinetic models

Abstract

One important aim in population pharmacokinetics (PK) and pharmacodynamics is identification and quantification of the relationships between the parameters and covariates. Lasso has been suggested as a technique for simultaneous estimation and covariate selection. In linear regression, it has been shown that Lasso possesses no oracle properties, which means it asymptotically performs as though the true underlying model was given in advance. Adaptive Lasso (ALasso) with appropriate initial weights is claimed to possess oracle properties; however, it can lead to poor predictive performance when there is multicollinearity between covariates. This simulation study implemented a new version of ALasso, called adjusted ALasso (AALasso), to take into account the ratio of the standard error of the maximum likelihood (ML) estimator to the ML coefficient as the initial weight in ALasso to deal with multicollinearity in non-linear mixed-effect models. The performance of AALasso was compared with that of ALasso and Lasso. PK data was simulated in four set-ups from a one-compartment bolus input model. Covariates were created by sampling from a multivariate standard normal distribution with no, low (0.2), moderate (0.5) or high (0.7) correlation. The true covariates influenced only clearance at different magnitudes. AALasso, ALasso and Lasso were compared in terms of mean absolute prediction error and error of the estimated covariate coefficient. The results show that AALasso performed better in small data sets, even in those in which a high correlation existed between covariates. This makes AALasso a promising method for covariate selection in nonlinear mixed-effect models.

Population pharmacokinetics of levodopa/carbidopa microtablets in healthy subjects and Parkinson’s disease patients

“…For investigation of influential covariates, the AALASSO method was chosen since it has shown to perform better with small dataset and with highly correlated covariates [ 16 ], which was the circumstance in this case. The advantage of the method is that it tests all relationships simultaneously and does not rely on a user-specified p value; however it may, as in this case, add some covariates that only have a modest effect on the parameter values.…”

“…The significance of the relationships were investigated using the adjusted adaptive least absolute shrinkage and selection operator (AALASSO) [ 15 , 16 ], as implemented in PsN [ 17 ] (version 4.7.0; Department of Pharmaceutical Biosciences, Uppsala University). LASSO is a penalized regression method, here used for covariate selection.…”

A Bounded Integer Model for Rating and Composite Scale Data

“…The performance in external validation of the models was investigated through cross-validation (21–25), where the data was split into five equal-size sets. Model parameters were estimated on four-fifth (80%) of the sets, and the resulting parameters, without re-estimation, were used in evaluating the goodness of fit, using OFV as metric, to the fifth (20%), test data, set.…”

Identification of high‐dimensional omics‐derived predictors for tumor growth dynamics using machine learning and pharmacometric modeling

“…13 A commonly used ML method is the least absolute shrinkage and selection operator (LASSO), which is a linear regression method with 1 regularization that can be used for high-dimensional analysis, and results in variable selection. 14 Although ML approaches, such as sparse regression models using the LASSO, [15][16][17][18] have been implemented in pharmacometric modeling, they are computationally expensive due to the combination of nonlinearity and estimation of random effects, which often lead to convergence problems. The implementations of the LASSO involve alternating algorithms, which alternate between estimating the random effects and the LASSO optimization, so although LASSO is rather efficient, iterating through multiple random effect estimation steps can severely reduce computational efficiency.…”

“…The LASSO has been previously implemented in pharmacometric nonlinear mixed effect models. [16][17][18] These direct implementations have the advantage of informing the LASSO directly within the longitudinal modelling. Models with a very high number of variables, however, become computationally hard.…”