A comparative investigation of methods for longitudinal data with limits of detection through a case study

The statistical analysis of continuous longitudinal data may be complicated since quantitative levels of bioassay cannot always be determined. Values beyond the limits of detection (LOD) in the assays may not be observed and thus censored, rendering complexity to the analysis of such data. This article examines how both left-censoring and right censoring of HIV-1 plasma RNA measurements, collected for the study on AIDS-related Non-Hodgkin’s lymphoma (AR-NHL) in East Africa, affects the quantification of viral load and explores the natural history of viral load measurements over time in AR-NHL patients receiving anticancer chemotherapy. Data analyses using Monte Carlo EM algorithm (MCEM) are compared to analyses where the LOD or LOD/2 (left censoring) value is substituted for the censored observations, and also to other methods such as multiple imputation, and maximum likelihood estimation for censored data (generalized Tobit regression). Simulations are used to explore the sensitivity of the results to changes in the model parameters. In conclusion, the antiretroviral treatment was associated with a significant decrease in viral load after controlling the effects of other covariates. A simulation study with finite sample size shows MCEM is the least biased method and the estimates are least sensitive to the censoring mechanism.

[1]  J L Schafer,et al.  Multiple Imputation for Multivariate Missing-Data Problems: A Data Analyst's Perspective. , 1998, Multivariate behavioral research.

[2]  J. Klein,et al.  Survival Analysis: Techniques for Censored and Truncated Data , 1997 .

[3]  J. A. Breslaw.  Random Sampling from a Truncated Multivariate Normal Distribution , 1994 .

[4]  S. Remick,et al.  AIDS-associated cancer in developing nations , 2004, Current opinion in oncology.

[5]  D. Rubin,et al.  Maximum Likelihood for General Patterns of Missing Data: Introduction and Theory with Ignorable Nonresponse , 2014, Statistical Analysis with Missing Data, Third Edition.

[6]  J. Tobin.  Estimation of Relationships for Limited Dependent Variables , 1958 .

[7]  Robert W. Coombs,et al.  Longitudinal Analysis of Quantitative Virologic Measures in Human Immunodeficiency Virus-Infected Subjects with ⩾400 CD4 Lymphocytes: Implications for Applying Measurements to Individual Patients , 1997 .

[8]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[9]  P. Diggle,et al.  Analysis of Longitudinal Data , 2003 .

[10]  H. Chu,et al.  Correlating two continuous variables subject to detection limits in the context of mixture distributions , 2005 .

[11]  M. McElrath,et al.  Longitudinal analysis of quantitative virologic measures in human immunodeficiency virus-infected subjects with > or = 400 CD4 lymphocytes: implications for applying measurements to individual patients. National Institute of Allergy and Infectious Diseases AIDS Vaccine Evaluation Group. , 1997, The Journal of infectious diseases.

[12]  D. Firth.  Bias reduction of maximum likelihood estimates , 1993 .

[13]  John W. Mellors,et al.  Prognosis in HIV-1 Infection Predicted by the Quantity of Virus in Plasma , 1996, Science.

[14]  D. Rubin.  Multiple imputation for nonresponse in surveys , 1989 .

[15]  John L. Johnson,et al.  Dose-modified oral chemotherapy in the treatment of AIDS-related non-Hodgkin's lymphoma in East Africa. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[16]  D Commenges,et al.  Analysis of left-censored longitudinal data with application to viral load in HIV infection. , 2000, Biostatistics.

[17]  D.,et al.  Regression Models and Life-Tables , 2022 .

[18]  D. Rubin,et al.  Estimation in Covariance Components Models , 1981 .

[19]  Michael P Epstein,et al.  A tobit variance-component method for linkage analysis of censored trait data. , 2003, American journal of human genetics.

[20]  D B Rubin,et al.  Multiple Imputation for Multivariate Data with Missing and Below‐Threshold Measurements: Time‐Series Concentrations of Pollutants in the Arctic , 2001, Biometrics.

[21]  B. Coiffier,et al.  AIDS-related non-Hodgkin's lymphoma: Final analysis of 485 patients treated with risk-adapted intensive chemotherapy. , 2006 .

[22]  J. Hughes,et al.  Mixed Effects Models with Censored Data with Application to HIV RNA Levels , 1999, Biometrics.

[23]  H. Lynn,et al.  Maximum likelihood inference for left-censored HIV RNA data. , 2001, Statistics in medicine.

[24]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[25]  D. Bates,et al.  Approximations to the Log-Likelihood Function in the Nonlinear Mixed-Effects Model , 1995 .

[26]  Frank C Curriero,et al.  Mixture models for quantitative HIV RNA data , 2002, Statistical methods in medical research.

[27]  D. Helsel.  Nondetects and data analysis : statistics for censored environmental data , 2005 .

[28]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.