Abstract: This disclosure describes a method and system for active machine learning model that automatically and continuously improve the model with high accuracy, sensitivity, specificity and universality.

Abstract: A method and system for detecting TB in a bodily fluid sample are described. By extracting extracellular vesicles (EVs) from the bodily fluid sample and employing antibody-conjugated nanoparticles to capture Mtb-related biomarkers, it is shown that the test can be completed within hours instead of weeks, and the detection limit can be significantly lowered with high accuracy. Additionally, the method and system described is capable of distinguishing between active and latent TB infections.