(W-023) Optimized Noncompartmental Half-Life Estimation with Tobit Regression

Objectives: When calculating half-life (t_1/2) in noncompartmental analysis, concentrations below the limit of quantification (BLQ) are typically omitted prior to estimating the elimination rate (k_el). The omission of BLQ concentrations removes information from the concentration-time profile as the fact that a concentration is BLQ indicates that it is censored below the limit of quantification.

Methods: Tobit regression is a method to estimate linear models with censored data;[1] it is equivalent to Beal's M3 method of handling BLQ concentrations with nonlinear mixed-effect modeling.[2] We describe a method for applying Tobit regression to estimate the half-life in data with or without BLQ concentrations, and using simulated pharmacokinetic (PK) data, we summarize the improvement of Tobit regression compared to least-squares regression.

Results: Via simulation-estimation using 1-, 2-, and 3-compartment simulated PK profiles, the method has been optimized such that it provides more accurate half-life estimates compared to the commonly-used curve-stripping linear regression method used by all software estimating noncompartmental half-lives.

Conclusions: Tobit regression provides an improved method for estimating noncompartmental half-life compared to current methods.

Citations: [1] Tobin J. Estimation of Relationships for Limited Dependent Variables. Econometrica. 1958;26(1):24-36. doi:10.2307/1907382
[2] Beal SL. Ways to Fit a PK Model with Some Data Below the Quantification Limit. J Pharmacokinet Pharmacodyn. 2001;28(5):481-504. doi:10.1023/A:1012299115260