Dengue Surveillance & Modeling in Latin America

This project explores epidemiological data from 10 Latin American countries (2020–2024) to analyze and predict Dengue outbreaks using statistical and computational methods.

Objective

Understand trends and risk factors for Dengue incidence and apply predictive modeling to support public health surveillance.

Tools & Technologies

• Python, Jupyter Notebooks
• Statistical modeling & regression
• Classification models for risk prediction
• SEIR (Susceptible-Exposed-Infected-Recovered) simulation
• Data visualization (matplotlib, seaborn, etc.)
• Reports and dashboards (PDFs)

Workflow

1. Data Collection & Cleaning: Gathered datasets from official sources and prepared them for analysis.
2. Exploratory Analysis: Investigated incidence patterns and potential risk factors.
3. Machine Learning Models: Built regression and classification models to predict risk levels.
4. SEIR Simulation: Modeled disease spread dynamics to understand outbreak potential.
5. Reporting: Generated graphs, charts, and summary reports to document findings.

Key Takeaway

This project demonstrates practical experience in epidemiological data analysis, predictive modeling, and disease simulation, providing insights into Dengue surveillance and public health decision-making.