Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients Full Text
BMC Pulmonary Medicine, 08/10/2012
Aguiar FS et al. – The classification and regression tree (CART) model developed for these hospitalized patients with clinical suspicion of Tuberculosis (TB) had fair to good predictive performance for pulmonary TB. The most important variable for prediction of TB diagnosis was chest radiograph results. Prospective validation is still necessary, but the model offer an alternative for decision making in whether to isolate patients with clinical suspicion of TB in tertiary health facilities in countries with limited resources.