Establishing a serologic decision tree model of extrapulmonary tuberculosis by MALDI-TOF MS analysis

Matrix-assisted laser desorption-ionization time of flight mass spectrometry (MALDI-TOF MS) combined with weak cationic exchange (WCX) magnetic beads was used to establish a decision tree model that distinguished extrapulmonary tuberculosis (EPTB) from non-EPTB individuals. Eight-one patients with EPTB and 112 non-EPTB individuals (72 disease controls and 40 healthy controls) were involved in this study. The model was set up by 5 of 19 differentially expressed peaks (P < 0.05), m/z 4100, 4310, 6093, 8605, and 14,019. This model can discriminate patients with EPTB from non-EPTB with a sensitivity of 97.7% and a specificity of 84.1%. The test set verified that this model had good sensitivity and specificity: 94.4% and 83.6%, respectively. In conclusion, MALDI-TOF MS combined with WCX magnetic beads is a powerful technology for constructing a decision tree model and the model we built could serve as a potential diagnostic tool for EPTB.