PROJECT TITLE:

Mining Health Examination Records — A Graph-based Approach - 2016

ABSTRACT:

General health examination is an integral part of healthcare in several countries. Identifying the participants at risk is vital for early warning and preventive intervention. The fundamental challenge of learning a classification model for risk prediction lies within the unlabeled data that constitutes the bulk of the collected dataset. Particularly, the unlabeled data describes the participants in health examinations whose health conditions will vary greatly from healthy to very-unwell. There is no ground truth for differentiating their states of health. In this paper, we tend to propose a graph-based, semi-supervised learning algorithm known as SHG-Health (Semi-supervised Heterogeneous Graph on Health) for risk predictions to classify a progressively developing state of affairs with the majority of the info unlabeled. An efficient iterative algorithm is intended and the proof of convergence is given. Extensive experiments primarily based on each real health examination datasets and synthetic datasets are performed to point out the effectiveness and efficiency of our methodology.