Clinical Decision Support System for Diabetes Based on Ontology Reasoning and TOPSIS Analysis

Abstract

Introduction Although a number of researchers have considered the positive potential of Clinical Decision Support System (CDSS), they did not consider that patients' attitude which leads to active treatment strategies or HbA1c targets. Materials and Methods We adopted the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD) published to propose an HbA1c target and antidiabetic medication recommendation system for patients. Based on the antidiabetic medication profiles, which were presented by the American Association of Clinical Endocrinologists (AACE) and American College of Endocrinology (ACE), we use TOPSIS to calculate the ranking of antidiabetic medications. Results The endocrinologist set up ten virtual patients' medical data to evaluate a decision support system. The system indicates that the CDSS performs well and is useful to 87%, and the recommendation system is suitable for outpatients. The evaluation results of the antidiabetic medications show that the system has 85% satisfaction degree which can assist clinicians to manage T2DM while selecting antidiabetic medications. Conclusions In addition to aiding doctors' clinical diagnosis, the system not only can serve as a guide for specialty physicians but also can help nonspecialty doctors and young doctors with their drug prescriptions.

Analysis of the Practice of Dengue Prevention and Sustainable Control with Multi-attribute Decision-making

“…The purpose of this study is to explore the ranking of factors affecting the dengue fever epidemic by GRA, and uses grey multi-attribute decision-making analysis and the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method to predict which areas of Tainan may become prevalent areas for dengue fever. The findings can can provide reference for the prevention and control of dengue fever to government departments, vector mosquito control operators, and environmental remediation workers, before and after the occurrence of dengue fever cases, in the hope of reducing the risk and scale of dengue fever through prevention and treatment measures [9][10][11][12][13][14].…”

AgriEnt: A Knowledge-Based Web Platform for Managing Insect Pests of Field Crops

“…To this end, OWL2 (Web Ontology Language) rules are applied to a semantic patient profile that collects information concerning vital signs, nutritional history, and laboratory test values. In [12], the authors presented a recommender system focused on antidiabetic medication. This system considers the safety and positivity of HbA1c to determine the ranking of antidiabetic medications.…”

“…In this sense, SWRL rules are simpler and easier to define than DRL rules [31]. On the other hand, works such as [12,24,28] relied on fussy technologies for developing the rules. Like the Drool tool, fuzzy technologies used in these works (such as jfuzzylogic) do not allow the direct use of ontologies.…”

“…One of the pillars of the Semantic Web are the ontologies, which can be referred as to a formal and explicit specification of a shared conceptualization [7]. Nowadays, decision support systems based on ontologies have been widely accepted as solutions in different domains such as recommender systems [8], software engineering [9], and health [10][11][12]. This opens the door for opportunities to apply this technology to the agriculture domain, specifically for crop insect pest's diagnosis and management.…”

A survey on semanticized and personalized health recommender systems

“…Chen, Jiang, Huang, and Bau () proposed a DSS for diabetes based on ontology reasoning and TOPSIS analysis. There are four modules in the system: (1) the patient consultation management module, (2) the patient perfect HbA1c target inference module, (3) the drug knowledge ontology and reasoning module, and (4) the antidiabetic medication ranking module.…”