brfss

Behavioral Risk Factor Surveillance System (BRFSS) data, 2014-2020

Harmonize longitudinal BRFSS survey data across years and datasets (CDC national & state-restricted files). A tidycensus-style workflow to resolve variable drift, response code shifts, and REAL-D demographic arrays into tidy tibbles.

R data package for CDC BRFSS: external parquet hosting, DuckDB lazy queries, srvyr survey designs

Visualized 2015 U.S. health survey data to uncover risk factors and patterns associated with diabetes.

A reproducible R project analysing BRFSS 2015 data using descriptive statistics, logistic regression, and model diagnostics to identify factors associated with diabetes.

7 个基于美国全国性健康调查数据（NHIS / BRFSS / NHANES）的 Agent Skills 慢病风险预测技能包，可复现、可追溯 | Reproducible Agent Skills packages for chronic disease risk prediction, built entirely on public US national survey data

SMOTE frente a CTGAN con desbalance extremo (bajo peso: 1,52 %) en 289.693 registros del CDC BRFSS 2023: 3 clasificadores × 4 configuraciones; CTGAN sin ganancia real (diferencias ≈ 0,02 en F1-macro).

Code and models for our ICACIE2019 paper "Prediction of Stroke Risk Factors for Better Pre-emptive Healthcare: A Public-Survey-Based Approach"

Data analysis project using R and R Studio and data from the 2013 Behavioral Risk Factor Surveillance System (BRFSS).

Mental Health Prediction using BRFSS 2021

CDC BRFSS tobacco-use trends (2011-2019) alongside U.S. monthly mortality data (2020-2023).

This project analyses the 2015 BRFSS health survey to identify key predictors of diabetes risk using data cleaning, statistical analysis, and machine‑learning models. BRFSS stands for Behavioral Risk Factor Surveillance System — a large, annual telephone‑based health survey run by the U.S. Centers for Disease Control and Prevention (CDC).

Educational diabetes risk awareness web app — XGBoost model trained on BRFSS big data (2020–2024) using Google BigQuery & Cloud Storage + personalized prevention advice powered by Gemini 2.5-flash. Built with Streamlit. For Canada / North America.

Analysis code and data for state-level trends in urban-rural differences in cigarette smoking, BRFSS 2018-2025 (PLOS ONE, under review)

Descriptive analysis of health-access disparities for transgender respondents in the CDC BRFSS survey.

CogniGuard-ML: A Leakage-Resistant Explainable Automated Machine Learning Framework for Early Cognitive Function Decline Risk Prediction Using Population Health Data

Analysis of CDC BRFSS 2022 data exploring how sleep duration relates to mental and physical health outcomes.

Heart attack risk prediction using the 2011 BRFSS dataset (506k records) with H2O AutoML, imbalance handling strategies, feature selection and precision-recall optimization for clinical risk detection.

Primeiro projeto apresentado na disciplina de Inteligência Computacional em Saúde utilizando a base de dados de indicadores de saúde para tarefa de classificação de indivíduos com diabetes.

Diabetes risk prediction from CDC/BRFSS health indicators — cleaning, stats, logistic regression & SVM