Table A1.

Data attributes.

Serial	Attributes	Description	Type
1	Id	Unique identifier	Identifier
2	Gender	“Male,” “Female” or “Other”	Nominal
3	Age	Age of the patient	Nominal (Quantitative)
4	Hypertension	0 = no hypertension, 1 = has hypertension	Categorical
5	Heart disease	0 = no heart disease, 1 = has heart disease	Categorical
6	Ever married	No or yes	Nominal
7	Work type	Children, government job, never worked, private, or self-employed	nominal
8	Residence type	Rural or urban	nominal
9	Average glucose level	Average glucose level in blood	Numerical
10	BMI	Body mass index	numerical
11	Smoking status	Formerly smoked, never smoked, smoke or unknown	Nominal
12	Stroke (target variable)	1 = had a stroke, 0 = no stroke	Categorical (Binary)

Unknown” in smoking status means that the information is unavailable for this patient.