Requirement specification of an ontology-based semantic recommender system for medical prescriptions and drug interaction detection Online publication date: Mon, 20-Jul-2020
by Ali Asghar Safaei; Sayyed Saeid Safaei
International Journal of Electronic Healthcare (IJEH), Vol. 11, No. 1, 2019
Abstract: The prescription of proper drugs is very important for disease treatment and patient health. Search and analyse the resources to find the drug interactions is a time-consuming and difficult task. It is possible to accelerate this process and improve the quality of drug prescriptions using the life sciences information sources available on the semantic web. In this paper, requirement specification of a ontology-based semantic recommender system for medical prescriptions and drug interaction detection has been presented. The main functions of the system and its requirements were initially extracted and described in detail by observing the existing system in the hospitals, interviewing medical specialists, and analysing questionnaires. Then, an appropriate ontology was designed and implemented for the system by using Protégé to detect drug interactions. A prototype was developed using Java to evaluate the functions of drug recommendations and drug interaction detection. The system performance was evaluated under different scenarios compared with similar approaches for drug prescription and interaction detection. The evaluation results demonstrated the enhanced performance of the proposed approach in both drug prescription and interaction detection functions. This indicates the benefits of proposed system as a computerised physician ordering entry.
Online publication date: Mon, 20-Jul-2020
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Electronic Healthcare (IJEH):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email firstname.lastname@example.org