ACTG 315 Longitudinal Data for Missing Covariates in Nonlinear Mixed-Effects (NLME) Models

Data Set 1

Data Set 2

Data Set 3

1. The data were produced from AIDS Clinical Trials Group, ACTG 315 study, which is sponsored by NIAID/NIH. If you have any questions regarding the data, you may contact Dr. Hulin Wu by email: hwu@bst.rochester.edu.

2. The detailed biomedical findings from this study and more detailed description of the study design can be found from the primary and secondary publications of this study, Lederman et al (1998) and Connick et al. (2000) (see below for these references).

3. Data set 1 was used in the paper by Wu and Wu (2001, Statistics in Medicine) in which more details about the data can be found.

4. Data set 2 was used in the paper by Wu and Wu (2002, Statistics in Medicine) in which more details about the data can be found.

5. Data set 3 was used in the paper by Wu and Wu (2002, JRSS-C) in which more details about the data can be found.

6. Early viral dynamics of this study was modeled by

  • Wu, Kuritzkes and McClernon, et al (1999, J of Infect Dis)
  • Wu and Ding (1999, Biometrics)

Some further viral dynamic analyses for this study (including long-term viral dynamics and covariates analyses) can be found in other pages of our website.

7. We included 48 patients, out of 53 patients enrolled in this study, for analysis. Only viral load data before rebound were used to fit the NLME viral dynamic model. "NA" in the data sets indicates the missing data (if you use Matlab, NA should be replaced by NaN).

8. Data set 1 (Data file 1) includes the following variables: id = ID, lgcopy=log10(RNA), cd4coun=baseline CD4 count, Baseline values of CD4, CH50, TNF are covariates in the NLME model.

9 More baseline covariates data (in total of 31 covariates) are included in Data set 2 (Data file 2).

10. Time-varying covariates, CD4 cell counts and CD8 cell counts, are included in Data set 3 (Data file 3).

11. Please cite the following references if appropriate when you use the data in your paper:

REFERENCES:
----------
1) Connick E, Lederman MM, Kotzin BL, et al. (2000), "Immune reconstitution in the first year of potent antiretroviral therapy and its relationship to virologic response," Journal of Infectious Diseases, 181:358-63.

2) Lederman MM, Connick E, Landay A, et al. (1998), "Immunologic responses associated with 12 weeks of combination antiretroviral therapy consisting of zidovudine, lamivudine and ritonavir: results of AIDS Clinical Trials Group Protocol 315," Journal of Infectious Diseases, 178: 70-79.

3) Wu, H. and Ding, A. (1999), "Population HIV-1 Dynamics in Vivo: Applicable Models and Inferential Tools for Virological Data from AIDS Clinical Trials," Biometrics, 55, 410-418.

4) Wu, H., Kuritzkes, D.R., and McClernon, D.R. et al. (1999), "Characterization of Viral Dynamics in Human Immunodeficiency Virus Type 1-Infected Patients Treated with Combination Antiretroviral Therapy: Relationships to Host Factors, Cellular Restoration and Virological Endpoints," Journal of Infectious Diseases, 179(4):799-807.

5) Wu, H. and Wu, L. (2001), "A Multiple Imputation Method for Missing Covariates in Nonlinear Mixed-effect Models, with Application to HIV Dynamics," Statistics in Medicine, 20 (12), 1755-1769.

6) Wu, H. and Wu, L. (2002), "Identification of Significant Host Factors for HIV Dynamics Modeled by Nonlinear Mixed-Effect Models," Statistics in Medicine, 21, 753-771.

7) Wu, L. and Wu, H. (2002), "Nonlinear Mixed-Effect Models with Missing Time-Dependent Covariates, with Application to HIV Viral Dynamics," Journal of the Royal Statistical Society, Series C (Applied Statistics), 51, 297-318.