Binary classification of users of electronic cigarettes and smokeless tobacco through biomarkers to assess similarity with current and former smokers: machine learning applied to the population assessment of tobacco and health study

Table 2 Demographic information and geometric mean of biomarkers for the potential harm classification model

Abbreviations: 8PGFT 8-isoprostane, CS cigarette smoker, CRE creatinine, dual-EPRODS current smoker and user of electronic cigarettes, dual-SMKLS current smoker and user of smokeless tobacco, ExSM former smoker, EPRODS user of electronic cigarettes, FIB fibrinogen, hsCRP high-sensitivity C-reactive protein, IL6 interleukin 6, sICAM soluble intercellular adhesion module, SD standard deviation, SMKLS user of smokeless tobacco, test-CS test dataset of current smokers, test-ExSM test dataset of former smokers
¹ Full data of all current smokers
² Random selection from data of all current smokers to match the number of former smokers for machine learning
³ Number of participants who answered “Yes” in the questionnaire
⁴ Number of participants who answered “Yes” in the relevant disease questionnaire
- In accordance with ICPSR data release rules, tables with cell sizes smaller than the threshold for the specific dataset will not be released

ISSN: 1471-2458