Dark Mode
Healthcare Obesity Levels Dataset
Public Health & Epidemiology
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset aims to estimate obesity levels by analysing lifestyle habits, family history, and physical condition. It includes both real and synthetically generated data from individuals across Mexico, Peru, and Colombia. The dataset is particularly useful for classification, regression, and clustering tasks, providing valuable insights for early intervention strategies, health recommendations, and various machine learning applications within the healthcare sector.
Columns
- Gender: Specifies the individual's gender as Male or Female.
- Age: Represents the person’s age in years.
- Height: Indicates the individual's height in metres.
- Weight: Shows the individual's weight in kilograms.
- family_history_with_overweight: A binary indicator (yes/no) showing if the person has a family history of being overweight.
- FAVC: A binary indicator (yes/no) detailing if the person frequently consumes high-calorie foods.
- FCVC: Describes the frequency of vegetable consumption on a scale from 1 to 3.
- NCP: Denotes the number of main meals consumed per day.
- CAEC: Specifies the frequency of consuming food between meals, categorised as Never, Sometimes, Frequently, or Always.
- SMOKE: A binary indicator (yes/no) showing whether the person smokes.
- CH2O: Represents daily water intake on a scale from 1 to 3.
- SCC: A binary indicator (yes/no) showing if the person monitors their calorie intake.
- FAF: Describes physical activity frequency on a scale from 0 to 3.
- TUE: Indicates the time spent using technology on a scale from 0 to 3.
- CALC: Specifies the frequency of alcohol consumption, categorised as Never, Sometimes, Frequently, or Always.
- MTRANS: Represents the main mode of transportation used, such as Automobile, Bike, Motorbike, Public Transportation, or Walking.
- NObeyesdad: The target variable, classifying obesity levels into categories like Insufficient Weight, Normal Weight, Overweight Level I, Overweight Level II, Obesity Type I, Obesity Type II, and Obesity Type III.
Distribution
The dataset is provided in CSV format and contains 2111 records with 17 distinct columns. Its file size is approximately 243.31 kB. It is structured with 16 lifestyle and health-related features, culminating in one target variable that classifies obesity levels. The dataset is not expected to be updated.
Usage
This dataset is ideal for developing predictive models to estimate obesity levels and for identifying key lifestyle factors contributing to obesity. It is highly suitable for various machine learning tasks, including classification, regression, and clustering. Potential use cases include informing public health campaigns, creating tools for early intervention, and supporting healthcare analysis and decision-making processes.
Coverage
The data originates from individuals located in Mexico, Peru, and Colombia. While a specific time range for data collection is not provided, the dataset is not expected to receive further updates. The age range of individuals in the dataset spans from 14 to 61 years. It is noted that most of the data was generated using synthetic techniques, with a portion collected directly from users via a web platform.
License
Attribution 4.0 International (CC BY 4.0)
Who Can Use It
This dataset is valuable for:
- Healthcare researchers and public health organisations for studying obesity trends and risk factors.
- Machine learning practitioners and data scientists for building and testing predictive models.
- Policy makers to inform the development of health initiatives and interventions.
- Developers creating applications for personal health monitoring or health recommendations.
Dataset Name Suggestions
- Obesity Lifestyle Prediction Dataset
- Obesity Risk Factors Data
- Global Lifestyle Obesity Study
- Healthcare Obesity Levels Dataset
- Diet and Activity Obesity Data
Attributes
Original Data Source: Healthcare Obesity Levels Dataset
QUALITY