US Adult Diabetes Risk Factors Survey

Columns

• Diabetes_012: Target variable indicating diabetes status (0 = no diabetes or only during pregnancy, 1 = prediabetes, 2 = diabetes).
• HighBP: Indicates high blood pressure (0 = no high BP, 1 = high BP).
• HighChol: Indicates high cholesterol (0 = no high cholesterol, 1 = high cholesterol).
• CholCheck: Denotes if cholesterol was checked in the past five years (0 = no check, 1 = yes check).
• BMI: Body Mass Index, a measure of body fat based on height and weight.
• Smoker: Identifies individuals who have smoked at least 100 cigarettes in their lifetime (0 = no, 1 = yes).
• Stroke: Indicates if the individual has ever been told they had a stroke (0 = no, 1 = yes).
• HeartDiseaseorAttack: Indicates a history of Coronary Heart Disease (CHD) or Myocardial Infarction (MI) (0 = no, 1 = yes).
• PhysActivity: Records physical activity in the past 30 days, excluding job-related activity (0 = no, 1 = yes).
• Fruits: Denotes if an individual consumes fruit one or more times per day (0 = no, 1 = yes).
• Veggies: Denotes if an individual consumes vegetables one or more times per day (0 = no, 1 = yes).
• HvyAlcoholConsump: Identifies heavy drinkers (adult men with more than 14 drinks/week, adult women with more than 7 drinks/week) (0 = no, 1 = yes).
• AnyHealthcare: Indicates if the individual has any kind of health care coverage (0 = no, 1 = yes).
• NoDocbcCost: Asks if there was a time in the past 12 months when a doctor was needed but not seen due to cost (0 = no, 1 = yes).
• GenHlth: Self-reported general health status on a scale of 1-5 (1 = excellent, 5 = poor).
• MentHlth: Number of days in the past 30 days when mental health was not good (scale 0-30).
• PhysHlth: Number of days in the past 30 days when physical health was not good (scale 0-30).
• DiffWalk: Indicates serious difficulty walking or climbing stairs (0 = no, 1 = yes).
• Sex: Gender of the respondent (0 = female, 1 = male).
• Age: 13-level age category (1 = 18-24, 13 = 80 or older).
• Education: Education level on a scale of 1-6 (1 = Never attended school or kindergarten, 6 = Graduate).
• Income: Income scale on a scale of 1-11 (1 = less than $10,000, 11 = $200,000 or more).

Distribution

• diabetes_012_health_indicators_BRFSS2021.csv: Contains 236,378 survey responses. The Diabetes_012 target variable has three classes (no diabetes/pregnancy, prediabetes, diabetes) and exhibits class imbalance.
• diabetes_binary_5050split_health_indicators_BRFSS2021.csv: Contains 67,136 survey responses. The Diabetes_binary target variable has two classes (no diabetes, prediabetes or diabetes) and is balanced with a 50-50 split.
• diabetes_binary_health_indicators_BRFSS2021.csv: Contains 236,378 survey responses. The Diabetes_binary target variable has two classes (no diabetes, prediabetes or diabetes) and is not balanced.

Usage

• Machine Learning Model Development: Building predictive models to identify individuals at risk of diabetes or to classify diabetes status based on health indicators.
• Public Health Research: Analysing the prevalence and contributing factors of diabetes in the U.S. adult population.
• Statistical Analysis: Investigating correlations between various health behaviours and indicators and diabetes outcomes.
• Data Visualisation: Creating visual representations of health trends and risk factors.

Coverage

License

Who Can Use It

• Data Scientists and Machine Learning Engineers for building and testing predictive models.
• Public Health Researchers and Epidemiologists for studying chronic disease prevalence and risk factors.
• Healthcare Analysts for understanding population health trends.
• Students and Academics for educational projects and research studies on health data.

Dataset Name Suggestions

• Diabetes Health Indicators BRFSS 2021
• US Adult Diabetes Risk Factors Survey
• BRFSS 2021 Health & Diabetes Data
• Chronic Disease Health Indicators (US)

Attributes