Development and validation of the nomogram to predict the infection risk of the pulmonary tuberculosis among people living with HIV

This study aimed to develop and validate a nomogram for predicting the risk of PTB infection among hospitalized PLWH based on the clinical laboratory tests and the WHO-recommended four- symptom screen(W4SS).The hospitalized PLWH were randomly divided into the training set and the validation set setsrandomly.

The Lleast absolute shrinkage and selection operator regression (LASSO)was performed to select the optimal predictors associated with bacteriologically confirmed PTB. The performance of the nomograms was analyzed by usingthe receiver operating characteristic curves (ROC) curves, calibration curves, decision curve analysis (DCA), and clinical impact curve (CIC).