Towards a universal architecture for disease data models sharing and evaluation

Abstract

Usually, medical researchers find it cumbersome to find disease data profiles that suit their research experiments requirements. In this paper, we propose a functional architecture where medical researchers can share disease data profiles after removing patients' sensitive information. In addition, the proposed architecture is equipped with some features that facilitate collaborative discussions among researchers. Besides, some machine learning techniques are adopted for analysis and modelling of disease datasets. This way, it is expected that medical researchers can better collaborate together and perform their researches on larger patient samples obtaining more accurate and representative results. The main functionalities of the architecture are introduced. One component of the architecture, which is the evaluation engine, was implemented using Matlab showing its advantages as a tool for researchers. The case of analyzing a model for a chronic disease known as Juvenile idiopathic arthritis has been studied. Obtained results show the applicability and effectiveness of the proposed approach.