A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits
Abstract Background In patient-based studies, biomarker data are often subject to left censoring due to the detection limits, or to incomplete sample or data collection. In the context of longitudinal regression analysis, inappropriate handling of these issues could lead to biased parameter estimate...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-01-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12874-017-0463-9 |
| _version_ | 1818561903636512768 |
|---|---|
| author | MinJae Lee Mohammad H. Rahbar Matthew Brown Lianne Gensler Michael Weisman Laura Diekman John D. Reveille |
| author_facet | MinJae Lee Mohammad H. Rahbar Matthew Brown Lianne Gensler Michael Weisman Laura Diekman John D. Reveille |
| author_sort | MinJae Lee |
| collection | DOAJ |
| description | Abstract Background In patient-based studies, biomarker data are often subject to left censoring due to the detection limits, or to incomplete sample or data collection. In the context of longitudinal regression analysis, inappropriate handling of these issues could lead to biased parameter estimates. We developed a specific multiple imputation (MI) strategy based on weighted censored quantile regression (CQR) that not only accounts for censoring, but also missing data at early visits when longitudinal biomarker data are modeled as a covariate. Methods We assessed through simulation studies the performances of developed imputation approach by considering various scenarios of covariance structures of longitudinal data and levels of censoring. We also illustrated the application of the proposed method to the Prospective Study of Outcomes in Ankylosing spondylitis (AS) (PSOAS) data to address the issues of censored or missing C-reactive protein (CRP) level at early visits for a group of patients. Results Our findings from simulation studies indicated that the proposed method performs better than other MI methods by having a higher relative efficiency. We also found that our approach is not sensitive to the choice of covariance structure as compared to other methods that assume normality of biomarker data. The analysis results of PSOAS data from the imputed CRP levels based on our method suggested that higher CRP is significantly associated with radiographic damage, while those from other methods did not result in a significant association. Conclusion The MI based on weighted CQR offers a more valid statistical approach to evaluate a biomarker of disease in the presence of both issues with censoring and missing data in early visits. |
| first_indexed | 2024-12-14T00:56:48Z |
| format | Article |
| id | doaj.art-c0d15f81c6394bc2aa2dfa24b800bda6 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-12-14T00:56:48Z |
| publishDate | 2018-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-c0d15f81c6394bc2aa2dfa24b800bda62022-12-21T23:23:30ZengBMCBMC Medical Research Methodology1471-22882018-01-0118111210.1186/s12874-017-0463-9A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visitsMinJae Lee0Mohammad H. Rahbar1Matthew Brown2Lianne Gensler3Michael Weisman4Laura Diekman5John D. Reveille6Division of Clinical and Translational Sciences, Department of Internal Medicine, McGovern Medical School, The University of Texas Health Science Center at HoustonDivision of Clinical and Translational Sciences, Department of Internal Medicine, McGovern Medical School, The University of Texas Health Science Center at HoustonQueensland University of TechnologyUniversity of CaliforniaCedars-Sinai Medical Center in Los AngelesDivision of Rheumatology, Department of Internal Medicine, McGovern Medical School, The University of Texas Health Science Center at HoustonDivision of Rheumatology, Department of Internal Medicine, McGovern Medical School, The University of Texas Health Science Center at HoustonAbstract Background In patient-based studies, biomarker data are often subject to left censoring due to the detection limits, or to incomplete sample or data collection. In the context of longitudinal regression analysis, inappropriate handling of these issues could lead to biased parameter estimates. We developed a specific multiple imputation (MI) strategy based on weighted censored quantile regression (CQR) that not only accounts for censoring, but also missing data at early visits when longitudinal biomarker data are modeled as a covariate. Methods We assessed through simulation studies the performances of developed imputation approach by considering various scenarios of covariance structures of longitudinal data and levels of censoring. We also illustrated the application of the proposed method to the Prospective Study of Outcomes in Ankylosing spondylitis (AS) (PSOAS) data to address the issues of censored or missing C-reactive protein (CRP) level at early visits for a group of patients. Results Our findings from simulation studies indicated that the proposed method performs better than other MI methods by having a higher relative efficiency. We also found that our approach is not sensitive to the choice of covariance structure as compared to other methods that assume normality of biomarker data. The analysis results of PSOAS data from the imputed CRP levels based on our method suggested that higher CRP is significantly associated with radiographic damage, while those from other methods did not result in a significant association. Conclusion The MI based on weighted CQR offers a more valid statistical approach to evaluate a biomarker of disease in the presence of both issues with censoring and missing data in early visits.http://link.springer.com/article/10.1186/s12874-017-0463-9Limit of detectionLeft-censoringMissing early visitsQuantile regressionMultiple imputation |
| spellingShingle | MinJae Lee Mohammad H. Rahbar Matthew Brown Lianne Gensler Michael Weisman Laura Diekman John D. Reveille A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits BMC Medical Research Methodology Limit of detection Left-censoring Missing early visits Quantile regression Multiple imputation |
| title | A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits |
| title_full | A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits |
| title_fullStr | A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits |
| title_full_unstemmed | A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits |
| title_short | A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits |
| title_sort | multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits |
| topic | Limit of detection Left-censoring Missing early visits Quantile regression Multiple imputation |
| url | http://link.springer.com/article/10.1186/s12874-017-0463-9 |
| work_keys_str_mv | AT minjaelee amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT mohammadhrahbar amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT matthewbrown amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT liannegensler amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT michaelweisman amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT lauradiekman amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT johndreveille amultipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT minjaelee multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT mohammadhrahbar multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT matthewbrown multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT liannegensler multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT michaelweisman multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT lauradiekman multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits AT johndreveille multipleimputationmethodbasedonweightedquantileregressionmodelsforlongitudinalcensoredbiomarkerdatawithmissingvaluesatearlyvisits |