From: 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
Predicted by exposure classification model
Predicted by potential harm classification model
Current smoker
Former smoker
Cardiovascular disease
9.9%
6.4%
10.9%
6.3%
Respiratory diseases
19.4%
16.7%
22.2%
14.2%