Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning

Abstract

A system and method for analyzing a sputum sample from a subject suspected of having lung cancer comprising obtaining a plurality of cells from the sputum sample from the subject, marking the plurality of cells with i) a plurality of cell lineage specific marker compositions, ii) a cell viability composition and iii) a tetra (4-carboxyphenyl) porphyrin (TCPP) composition; analyzing with the flow cytometer the plurality of cells marked with i-iii to obtain a subpopulation selected for cell size from the plurality of cells based upon an automatically selected bead size exclusion gate; from the cell size selected subpopulation, selecting a viable singlet population of cells using an automated non-debris gate and an automated singlets gate; from the viable singlet population of cells, obtaining flow cytometer values based upon the plurality of cell lineage specific marker compositions, the viability marker and the TCPP marker; applying a trained classifier to meta data from the subject and the flow cytometric values obtained; and generating, based upon the application of the trained classifier, a classification for the sputum sample wherein the classification is selected from a plurality of classification options comprising cancer and non-cancer.