Skip to content

Analyzed 14K+ patient records to model how race and geography influence asthma mortality in the US, applying ML classification and regression methods for predictive insights.

Notifications You must be signed in to change notification settings

18rberry/UC-Berkeley-ML-Final-Project

Repository files navigation

Machine-Learning-Course-at-Berkeley-Final-Project

Final project for my Machine Learning Course at UC Berkeley. I used GLMs and non-parametric methods to predict risk of asthma mortality based on race, and causal inference to explore how living in states with higher air pollution levels causes an increase in asthma mortality rates. I used data from the census, State Department Emergency Databases (SDED), and Behavioral Risk Factor Surveillance System (BRFSS).

About

Analyzed 14K+ patient records to model how race and geography influence asthma mortality in the US, applying ML classification and regression methods for predictive insights.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published