How Gaussian mixture modelling can help to verify reference intervals from laboratory data with a high proportion of pathological values

Abstract

Although there are several indirect methods that can be used to verify reference limits, they have a common weakness in that they assume a low proportion of pathological values. This paper investigates whether a Gaussian decomposition algorithm can identify the non-pathological fraction even if it is not the main subset of mixed data.

Keywords

• machine learning
• reference interval
• gaussian mixture modelling
• reflimr
• refiner