Rules-based decision support system and domain ontology for diabetes diagnosis

Dendani Nadjette (1) , Allouani Rayene (1)

1 UBMA - Université Badji Mokhtar [Annaba]

Artificial intelligence must have access to objects, categories, properties and relations between all of them to implement knowledge engineering. Initiating common sense, reasoning and problem-solving power in machines is a difficult and tedious. AI decision support systems are used in multiple fields, such as the medical field. In which making a decision consists of posing a diagnosis and proposing a treatment. Various applications of decision-making support were developed in this domain. Those applications are intended to help medical workers (doctors, nurses...etc) in their process of decision making. It involves the use of powerful tools of Artificial Intelligence, such as the rules-based reasoning (RBR). Which stimulates the judgment and behaviour of a human or an organization that has expert knowledge and experience in a particular field by following a certain set of rules. Systems that use rules-based reasoning are also known as Expert Systems. An expert system is composed of a user interface, an inference engine and a knowledge base. The use of ontologies in the medical domain has seen a huge growth in recent years and was accompanied by a great success, which motivated us to create an ontology related to our field of work, the diagnosis of diabetes, to serve as our knowledge base. In this paper we proposed a rules-based decision support system for patients with diabetes. It uses the Rules-based technique for reasoning and a domain ontology for representing the knowledge to detect diabetes, its type, its seriousness and giving the appropriate care plan. This system helps both doctors and patients to check, analyse and repair solutions. It analyzes the symptoms of the patients and gives the exact types of diabetes, its seriousness level and the appropriate treatment for every patients. In addition to that, it offers an analysis of the data stored by the system, based on different factors such as: type of diabetes, age of the patient...

Mots clés: Rules-based reasoning; Expert Systems; Ontology; Diabetes; Diagnosis; Decision-making; Artificial Intelligence; Medicine

Domaines: Intelligence artificielle [cs.AI]

Dendani Nadjette, Allouani Rayene. Rules-based decision support system and domain ontology for diabetes diagnosis. 30es Journées Francophones d'Ingénierie des Connaissances, IC 2019, AFIA, Jul 2019, Toulouse, France. pp.224-230. ⟨hal-02329609⟩