Mining Health Examination Records - A Disease Detection Approach

Abstract

General health examination is an integral part
of healthcare in many countries like India. To identify the
participants at risk is important for early warning and preventive
measures. The majority of the collected dataset is the unlabeled
data, which is the fundamental challenge of learning a classication
model for risk prediction. Usually, the unlabeled data describes
the participants health conditions varying greatly from healthy
to very-ill. In this paper, we use a graph-based, semi-supervised
learning algorithm called SHG-Health (Semisupervised Heterogeneous Graph on Health) for risk predictions to classify a progressively developing situation with the majority ofthedataunlabeled.Wearegoingtoperformexperimentsbased on both real health
examination datasets and synthetic datasets are performed to
show the effectiveness and efciency of our method.