An Approach to Management of Health Care and Medical Diagnosis Using a Hybrid Disease Diagnosis System

Introduction: In order to simplify the information exchange within the medicaldiagnosis process, a collaborative software agent’s framework is presented. Thepurpose of the framework is to allow the automated information exchangebetween different medicine specialists.Methods: This study presented architecture of a hybrid disease diagnosis system.The architecture employed a learning algorithm and used soft computing to builda medical knowledge base. These machine intelligences are combined in acomplementary approach to overcome the weakness of each other. To evaluatethe hybrid learning algorithm and compare it with other methods, 699 sampleswere used in each experiment, where 60% was for training, 20% was for crossvalidation, and 20% for testing.Results: The results were obtained from the experiments on the breast cancerdataset. Different methods of soft computing system were merged to creatediagnostic software functionality. As it is shown in the structure, the system hasthe ability to learn and collect knowledge that can be used in the detection of newimages. Currently, the system is at the design stage. The system is to evaluate theperformance of hybrid learning algorithm. The preliminary results showed abetter performance of this system than other methods. However, the results canbe tested with hybrid system on larger data sets to improve hybrid learningalgorithm.Conclusion: The purpose of this paper was to simplify the diagnosis process of apatient by splitting the medical domain concepts (e.g., causes, effects, symptoms,tests) in human body systems (e.g., respiratory, cardiovascular), thoughmaintaining the holistic perspective through the links between common concepts.

Keywords:

Medical diagnosis , Diagnosis process , Genetic algorithms , Ontology