Differential Diagnosis Knowledge Building by Using CUC-C4.5 Framework
نویسنده
چکیده
Problem statement: The Case Based Reasoning (CBR) method can be implemented in differential diagnosis analysis. C4.5 algorithm has been commonly used to help the method’s knowledge building process. This process is completed by constructing decision tree from previously handled cases data. The C4.5 algorithm itself can be used with an assumption that all the cases has an exact and equal truth value thus have an exact contribution in decision tree building process. However, the decision makers sometimes not sure about the truth of the cases in the cases database, therefore the confidence value can be different for case by case. Besides that, the C4.5 algorithm can only handle cases that are stored in a flat table with data in form of categorized text or in discrete class. This algorithm has not yet explained about how is decision tree building mechanism in situation when the data are stored in relational tables. It also has not yet explained about the process of knowledge building when the data are in the form of number in continuous class. Meanwhile, the observed objects in this research, that is medical record data, are mostly stored in a complex relational database and have common form of categorized text, discrete number, continuous number and image. Therefore, the C4.5 is needed to be improved so it can handle decision building for cases database of medical record. Approach: We develop a knowledge building framework that can handle confidence level difference of cases in cases database. The framework we build also allows the data are stored in relational database. Moreover, our framework can process data in the form of categorized text, discrete number, continuous number and image. This framework is named CUC-C4.5, abbreviated from Complex Uncertain Case C4.5 as it is the improvement from C4.5 algorithm. Results: The CUC-C4.5 framework has been applied on the case of differential diagnosis knowledge building in a group decision support system to handle geriatric patient. This framework was implemented by using PHP and Javascript programming language and MySQL DBMS. Conclusion: The CUC-C4.5 can support differential diagnosis analysis on group decision support system for geriatric assessment.
منابع مشابه
Validity of Using Recombinant Melon Profilin, Cuc m 2, for Diagnosis of Melon Allergy
Background: Allergy is a clinical disorder affecting humans worldwide. Allergenic extracts prepared from natural source materials remain heterogeneous in composition and content, but are regularly used for diagnosis and immunotherapy. Recombinant allergens are suitable candidates to use in place of natural allergens; however, the recombinant allergens should be assessed and compared with the na...
متن کاملValidity of Using Recombinant Melon Profilin, Cuc m 2, for Diagnosis of Melon Allergy
Background: Allergy is a clinical disorder affecting humans worldwide. Allergenic extracts prepared from natural source materials remain heterogeneous in composition and content, but are regularly used for diagnosis and immunotherapy. Recombinant allergens are suitable candidates to use in place of natural allergens; however, the recombinant allergens should be assessed and compared with the na...
متن کاملIntra-urban Land Cover Classification from High-resolution Images Using the C4.5 Algorithm
Nowadays, the availability of high-resolution images has increased the number of researches on urban land use and land cover classification. Most of them have used object oriented image analysis with successful results. Although object oriented analysis offers effective tools to represent the knowledge of the scene, the tasks of building semantic network and selecting attributes are time-consum...
متن کاملAn optimization framework for classifier learning from image data for computer-assisted diagnosis
In computer-assisted medical diagnosis it is often hard or even impossible to obtain a valid set of rules for disease classification by classical knowledge engineering methods. Alternatively, machine learning methods are applied to obtain classifiers from sets of data pre-classified by medical experts. Typically in a medical context, available data sets are imbalanced with respect to the possib...
متن کاملMining the Classification Rules: The Egyptian Rice Diseases as Case Study
Applications of learning algorithms in knowledge discovery are promising and relevant area of research. It is offering new possibilities and benefits in real-world applications, helping us understand better mechanisms of our own methods of knowledge acquisition. Decision trees is one of learning algorithms which posses certain advantages that make it suitable for discovering the classification ...
متن کامل