As part of Engineer Honors thesis, I identified XX biomarkers present in the breath of pediatric patients that can be used to identify children with pulmonary M. tuberculosis (TB) infections with XX% accuracy. The TB status of each child was determined using culture and nucleic acid amplification (i.e. GeneXpertTM). Breath samples were collected from patients at the Red Cross Memorial Children’s Hospital in Cape Town, South Africa. Breath molecules were concentrated and stored on carbon tubes which were analyzed via two-dimensional gas chromatography and time of flight mass spectrometry (GCxGC TOFMS). Statistical and machine learning (RF, SVM, PCA) methods were implemented to determine a suite of XX discriminatory breath biomarkers that discriminate TB-positive from TB-negative pediatric patients.
For more information on the data-science side of the project, click here.