Skip to main content

Advertisement

Table 1 Overview of variable group (and number of variables) that appear in the data mining data set

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

Group Variables
BOPH (4) DEH11, EPI8, HDL, WBC
Special interest variables: BOE (9): HPMA3, DHBMA, MHBMA, NICEQ, COTIN, OHP, TOTNN, ABP, COHB
Special interest variables: cumulative effects (2) "AGE", "SMKYRS" (years smoked, excluded from analysis of non-smokers)
Special interest variables: stratification (1) Smoking Status
Exposure variables (4) Measures of exposure to exhaust and chemicals, from questionnaire
Exposure variables (non-smokers, 8) Measures of exposure to secondary smoke, from questionnaire
Exposure variables (smokers, 19) Measures of exposure to tobacco, including number of cigarettes smoked, tar and nicotine content, presence of menthol, included only in the analysis for smokers
Demographics (13) Weight, gender, race, geographical location, income, etc.
Vital signs (5) Respiratory rate, temperature, blood pressure, pulse
Clinical measures (2) Measures of respiratory capacity, FVC, FEV1
General health (20) General health questions, from questionnaire
Lab values (22) Clinical chemistry laboratory values
Creatinine clearance (1) CRCL: 24 h urine creatinine/plasma creatinine
Lab value flags (6) Lab value flags
Medical history indicators (15) Medical history findings broken down into 15 categories
Concomitant medications (61) Concomitant medications broken down into 61 categories