Lifestyle and Biometrics Health Dataset
Public Health & Epidemiology
Related Searches
Trusted By




"No reviews yet"
Free
About
Unlock insights into health behaviors through body signals with this dataset from the National Health Insurance Service in Korea. Focused on analyzing the relationship between body metrics and health behaviors like smoking and drinking, this dataset is ideal for those seeking to explore the physiological indicators linked to these lifestyle habits. Each record includes comprehensive body measurements, blood test results, and lifestyle information, enabling in-depth analysis and predictive modeling.
Dataset Features
-
Demographic Information:
- Sex: Male or Female
- Age: Rounded up to the nearest 5 years
-
Body Measurements:
- Height: Rounded up to the nearest 5 cm (in cm)
- Weight: Weight in kilograms (kg)
- Waistline: Waist circumference in cm
-
Vision and Hearing:
- Sight Left / Sight Right: Eyesight measurements for each eye
- Hearing Left / Hearing Right: Hearing capability for each ear (1 = Normal, 2 = Abnormal)
-
Vital Signs:
- Systolic Blood Pressure (SBP): Measured in mmHg
- Diastolic Blood Pressure (DBP): Measured in mmHg
-
Blood Tests:
- Blood Glucose (BLDS): Fasting blood glucose levels (mg/dL)
- Total Cholesterol: Total cholesterol level (mg/dL)
- HDL Cholesterol: High-density lipoprotein level (mg/dL)
- LDL Cholesterol: Low-density lipoprotein level (mg/dL)
- Triglyceride: Triglyceride level (mg/dL)
- Hemoglobin: Hemoglobin concentration (g/dL)
- Serum Creatinine: Blood creatinine levels (mg/dL)
-
Liver Enzymes:
- SGOT/AST: Glutamate-oxaloacetate transaminase levels (IU/L)
- SGPT/ALT: Alanine transaminase levels (IU/L)
- Gamma-GTP: Gamma-glutamyl transferase levels (IU/L)
-
Urine Protein:
- Protein levels in urine (1 = -, 2 = ±, 3 = +1, 4 = +2, 5 = +3, 6 = +4)
-
Health Behaviors:
- Smoking Status: 1 = Never smoked, 2 = Quit smoking, 3 = Currently smoking
- Drinking Status: Y = Yes (drinker), N = No (non-drinker)
Usage
This dataset is ideal for:
- Health Risk Analysis: Investigate the impact of smoking and drinking on various body metrics such as blood pressure, liver enzymes, and cholesterol levels.
- Predictive Modeling: Develop models to predict smoking and drinking status based on physiological data and blood test results.
- Healthcare Research: Study the correlations between health behaviors and body signals, which can aid in developing preventive health programs.
License
- License: Restricted to non-commercial use
- Data Volume: Moderate size, suitable for machine learning and statistical analysis
Who can use it:
- Researchers and Data Scientists: For building classification models and conducting statistical analysis on health behavior impacts.
- Public Health Officials and Policymakers: To inform health interventions and campaigns aimed at reducing smoking and drinking rates.
- Healthcare Providers: To better understand body metrics associated with lifestyle risks and improve patient care.
How to Use This Dataset
- Classification Modeling: Create algorithms to classify individuals as smokers or drinkers based on their body metrics and blood test data.
- Trend Analysis: Explore patterns in body metrics across different age groups, sexes, and health behaviors.
- Health Program Evaluation: Assess health initiatives by understanding the physiological effects of lifestyle choices like smoking and drinking.
Leverage this dataset to explore the complex relationships between body signals and lifestyle choices, providing data-driven insights for research, policy, and health interventions.