The World Health Organization estimates that 16% of all multi-drug resistant tuberculosis (MDR-TB) patients are lost to follow up (LTFU), placing them at increased risk for the development of additional resistance to antituberculosis medications and early death. Despite mounting knowledge about the risk factors for LTFU from MDR-TB treatment and the End TB Strategy directive that patients at-risk for suboptimal treatment success be given priority attention, there is currently no evidence-based method that allows for the early identification of patients at-risk for being lost from care. This study will develop a model for predicting LTFU from MDR-TB treatment that can ultimately be used to guide MDR-TB providers in identifying patients at high-risk for LTFU and prioritizing their receipt of support services that promote care engagement and retention.
Primary Aim: To develop a prediction model for LTFU from MDR-TB care based on the patient characteristics available at treatment initiation utilizing LASSO regression and k-fold cross-validation.