A Review of Recent Advances for Preventing, Diagnosis and Treatment of Diabetes Mellitus using Semantic Web

Abstract

According to the World Health Organization (WHO), the number of patients with chronic diseases continues to increase rapidly for various reasons and these diseases are among the leading causes of death in the world. Among the chronic deaths, diabetes accounts a major cause. Especially Type 2 Diabetes (diabetes mellitus) and its complications have become the top 10 causes of death by rapidly increasing all over the world in the last 20 years. Therefore, to prevent and detect diabetes in early stages is crucial. For this purpose, machine learning, expert systems, fuzzy logic and Semantic Web based approaches have been developed. In particular, Semantic Web provides technologies to represent diabetes data as machine-processable metadata. This metadata then can be used to automatically infer possible prevention, diagnosis, treatment plans at early stages using semantic rules and SPARQL query language. Therefore, in our work, we review recent ontology-based intelligent systems for preventing, diagnosis and treatment of diabetes patients. We compare the methods in terms of aim, ontologies, technology, user interfaces, reasoning capabilities, evaluation metrics and software. In addition, we provide insights about recent developments and future directions.