Model | The feature considered |
---|---|
Model 1: All variables in their original scales besides the history of drugs | Age, Sex, Smoking status, Education, Marital Status, Family History of Stroke, SBP, DBP, BMI, Waist, Hip, FBS, TG, HDL, Physical Activity, Lipid Drug, Anti-Hypertension Drug, Aspirin, Corticosteroid. |
Model 2: Transformed variables; the effect of changing the continuous to the discrete state of the features. | Age, Sex, Smoking status, Education, Marital Status, Family History of Stroke, Anti-Hypertension drug, BMI categories, Waist-to-Height Ratio, T2DM, high TG, low HDL, Physical Activity |
Model 3: Transformed variables; the effect of changing the continuous to the discrete state of the features. | Age, Sex, Smoking status, Education, Marital Status, Family History of Stroke, Anti-Hypertension Drug, BMI categories, Waist-to-Hip Ratio, T2DM, high TG, low HDL, and Physical Activity |
Model 4: Cardio-metabolic risk factors model; reducing the number of features. | Age, Sex, Smoking status, Education, Marital Status, Family History of Stroke, Cardio-metabolic risk factors* |