Feature selection and prediction of treatment failure in tuberculosis

Using a multi-country dataset managed by the National Institute of Allergy and Infectious Diseases we applied various machine learning techniques to identify factors statistically associated with treatment failure and to predict treatment failure based on baseline demographic and clinical characteristics alone.

Authors

Christopher Martin Sauer, David Sasson, Kenneth Paik, Ned McCague, Leo Anthony Celi , Iván Sánchez Fernández, Ben M.W. Illigens

Files

• file_E_1.Rmd - model selection and optimization for tuberculosis treatment failure
• file_E_1.Rmd - contains data visualization on basic clinical characteristics
• there are also two knitted HTML documents which include all of our analysis without the need to run any code