Weather-related Disease Prediction Dataset

This dataset integrates medical symptoms and weather conditions to facilitate research into the prediction of diseases influenced by meteorological factors. The data spans a range of weather parameters alongside reported medical symptoms from a sizable number of anonymized individuals.

Variables:

Age: Age of the patient.

Gender: Gender of the patient (encoded numerically).

Temperature (C): Daily average temperature in Celsius.

Humidity: Daily average humidity percentage.

Wind Speed (km/h): Daily average wind speed in kilometers per hour.

Symptoms: Various symptoms such as nausea, joint pain, abdominal pain, high fever, chills, fatigue, runny nose, pain behind the eyes, etc., encoded as binary values (1 for present, 0 for absent).

Pre-existing Conditions: Conditions like asthma history, high cholesterol, diabetes, obesity, HIV/AIDS, nasal polyps, high blood pressure, encoded as binary values.

Data Collection Method:

The data was collected from anonymous medical records and corresponding local weather stations. All personal identifiers have been removed to ensure patient confidentiality and data privacy, adhering to ethical standards for medical data handling.

Usage Notes:

This dataset is intended for use in academic and research settings, especially in studies focused on the impact of weather on human health. It could be particularly useful for developing machine learning models to predict the likelihood of disease outbreaks based on weather patterns.