Fuzzy ontology-based personalized recommendation for internet of medical things with linked open data.

Increase in chronic diseases among people gives the health care industry a challenging problem. Healthcare industry is using the Internet-of-Things (IoT) to create systems that monitor patients. The ultimate task of the system is to minimize manual efforts made to recommend food and drugs for chronic patients. However, many uncertain factors are involved with chronic patients, and existing models unable to handle it efficiently often lead to poor results. Medical records gathered from diverse devices, such as mobile and IoT devices that are raw in nature or in different formats cannot be utilized for further analysis. Since patient records grow rapidly, it is difficult for health care systems to manage and control. To overcome these limitations, the proposed system develops a fuzzy ontology-based recommender system using Type-2 fuzzy logic to recommend foods and drugs for chronic (diabetic) patient. Extraction of risk factors for chronic patients is achieved via wearable sensors and IoT-based electronic medical records are linked with linked open data (LOD) to create a knowledge base. Since, patient data sets are huge; cloud services are used to store and retrieve data for further analysis. An experiment is conducted on patient datasets and the results illustrate that the proposed work is efficient for patient data enrichment, risk factor extraction and appropriate medical advice for chronic patients. [ABSTRACT FROM AUTHOR]