Using Bayesian inference to measure the proximity of flow cytometry data

Abstract

Flow cytometry (FCM) is a widely used technique in health-related fields, including cancer diagnosis and HIV monitoring. Measuring and quantifying the proximity between two patients based on the FCM data is challenging, yet crucial in most data mining tasks. Not only does each file contain thousands of features (representing different cells), but also the features are unordered. Furthermore, the data of a single patient can be divided over multiple FCS files due to technical limitations of FCM machines. We propose in this paper the use of Bayesian inference, along with Binning, to represent and measure the proximity between two patients using FCM data. We verify the effectiveness of our approach by comparing the performance of several classification algorithms in predicting leukaemia cases.