Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers

<p>Abstract</p> <p>Background</p> <p>This article describes the data mining analysis of a clinical exposure study of 3585 adult smokers and 1077 nonsmokers. The analysis focused on developing models for four biomarkers of potential harm (BOPH): white blood cell count (W...

Full description

Bibliographic Details
Main Authors: Mendes Paul E, Sarkar Mohamadi, Liang Qiwei, Warner John H, Roethig Hans J
Format: Article
Language:English
Published: BMC 2010-03-01
Series:BMC Medical Research Methodology
Online Access:http://www.biomedcentral.com/1471-2288/10/19
id doaj-56a9fbffd26148daa210d32e674449f4
record_format Article
spelling doaj-56a9fbffd26148daa210d32e674449f42020-11-25T01:03:12ZengBMCBMC Medical Research Methodology1471-22882010-03-011011910.1186/1471-2288-10-19Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokersMendes Paul ESarkar MohamadiLiang QiweiWarner John HRoethig Hans J<p>Abstract</p> <p>Background</p> <p>This article describes the data mining analysis of a clinical exposure study of 3585 adult smokers and 1077 nonsmokers. The analysis focused on developing models for four biomarkers of potential harm (BOPH): white blood cell count (WBC), 24 h urine 8-epi-prostaglandin F<sub>2α </sub>(EPI8), 24 h urine 11-dehydro-thromboxane B<sub>2 </sub>(DEH11), and high-density lipoprotein cholesterol (HDL).</p> <p>Methods</p> <p>Random Forest was used for initial variable selection and Multivariate Adaptive Regression Spline was used for developing the final statistical models</p> <p>Results</p> <p>The analysis resulted in the generation of models that predict each of the BOPH as function of selected variables from the smokers and nonsmokers. The statistically significant variables in the models were: platelet count, hemoglobin, C-reactive protein, triglycerides, race and biomarkers of exposure to cigarette smoke for WBC (R-squared = 0.29); creatinine clearance, liver enzymes, weight, vitamin use and biomarkers of exposure for EPI8 (R-squared = 0.41); creatinine clearance, urine creatinine excretion, liver enzymes, use of Non-steroidal antiinflammatory drugs, vitamins and biomarkers of exposure for DEH11 (R-squared = 0.29); and triglycerides, weight, age, sex, alcohol consumption and biomarkers of exposure for HDL (R-squared = 0.39).</p> <p>Conclusions</p> <p>Levels of WBC, EPI8, DEH11 and HDL were statistically associated with biomarkers of exposure to cigarette smoking and demographics and life style factors. All of the predictors togather explain 29%-41% of the variability in the BOPH.</p> http://www.biomedcentral.com/1471-2288/10/19
collection DOAJ
language English
format Article
sources DOAJ
author Mendes Paul E
Sarkar Mohamadi
Liang Qiwei
Warner John H
Roethig Hans J
spellingShingle Mendes Paul E
Sarkar Mohamadi
Liang Qiwei
Warner John H
Roethig Hans J
Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers
BMC Medical Research Methodology
author_facet Mendes Paul E
Sarkar Mohamadi
Liang Qiwei
Warner John H
Roethig Hans J
author_sort Mendes Paul E
title Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers
title_short Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers
title_full Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers
title_fullStr Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers
title_full_unstemmed Adaptive regression modeling of biomarkers of potential harm in a population of U.S. adult cigarette smokers and nonsmokers
title_sort adaptive regression modeling of biomarkers of potential harm in a population of u.s. adult cigarette smokers and nonsmokers
publisher BMC
series BMC Medical Research Methodology
issn 1471-2288
publishDate 2010-03-01
description <p>Abstract</p> <p>Background</p> <p>This article describes the data mining analysis of a clinical exposure study of 3585 adult smokers and 1077 nonsmokers. The analysis focused on developing models for four biomarkers of potential harm (BOPH): white blood cell count (WBC), 24 h urine 8-epi-prostaglandin F<sub>2α </sub>(EPI8), 24 h urine 11-dehydro-thromboxane B<sub>2 </sub>(DEH11), and high-density lipoprotein cholesterol (HDL).</p> <p>Methods</p> <p>Random Forest was used for initial variable selection and Multivariate Adaptive Regression Spline was used for developing the final statistical models</p> <p>Results</p> <p>The analysis resulted in the generation of models that predict each of the BOPH as function of selected variables from the smokers and nonsmokers. The statistically significant variables in the models were: platelet count, hemoglobin, C-reactive protein, triglycerides, race and biomarkers of exposure to cigarette smoke for WBC (R-squared = 0.29); creatinine clearance, liver enzymes, weight, vitamin use and biomarkers of exposure for EPI8 (R-squared = 0.41); creatinine clearance, urine creatinine excretion, liver enzymes, use of Non-steroidal antiinflammatory drugs, vitamins and biomarkers of exposure for DEH11 (R-squared = 0.29); and triglycerides, weight, age, sex, alcohol consumption and biomarkers of exposure for HDL (R-squared = 0.39).</p> <p>Conclusions</p> <p>Levels of WBC, EPI8, DEH11 and HDL were statistically associated with biomarkers of exposure to cigarette smoking and demographics and life style factors. All of the predictors togather explain 29%-41% of the variability in the BOPH.</p>
url http://www.biomedcentral.com/1471-2288/10/19
work_keys_str_mv AT mendespaule adaptiveregressionmodelingofbiomarkersofpotentialharminapopulationofusadultcigarettesmokersandnonsmokers
AT sarkarmohamadi adaptiveregressionmodelingofbiomarkersofpotentialharminapopulationofusadultcigarettesmokersandnonsmokers
AT liangqiwei adaptiveregressionmodelingofbiomarkersofpotentialharminapopulationofusadultcigarettesmokersandnonsmokers
AT warnerjohnh adaptiveregressionmodelingofbiomarkersofpotentialharminapopulationofusadultcigarettesmokersandnonsmokers
AT roethighansj adaptiveregressionmodelingofbiomarkersofpotentialharminapopulationofusadultcigarettesmokersandnonsmokers
_version_ 1725201847605526528