Artificial Intelligence Approach for Processing Electronic Medical Records

Abstract

In this thesis it has been clarified the meaning of medical records to the patient and the extent of the difficulties faced by doctors in the use of such records to improve medical services. In the past, patient’s medical records were treated as paper-based only. However, the importance of storing and manipulating these records electronically has been manifested in the past few years. With the increased incentive to enrich the delivery of medical care, the use of EMR should continue to increase. This thesis has identified many of EMR benefits; it has also listed many of implementations issues and challenges that the current EMR systems implementers are facing in different countries. A technique has been proposed to integrate different medical care systems databases. This approach consists of five main steps: 1. Accessing and extracting different medical databases tuples relationships regardless their different structures, by analyzing each database attribute and each attribute’s properties. 2. Transforming retrieved relationships into a readable form, by analyzing the synonym relations between attributes. 3. Building a frame-base model for each database, by analyzing the different relationships and defining a DTD. 4. Using an XML-generator to generate frame-based XML cases. XML proves to provide a simple and clear way of representing proper cases. 5. Building the case-base which is considered a very critical task. This step is still under development with the intension to using genetic algorithms. Peculiarities of this technique: 1. Many of integration techniques proposed in the literature have been designed for carrying out the integration of predefined well-known structured data sources. On the contrary, the proposed technique is capable of handling heterogeneous information sources as it’s working on unknown structured data sources. 76 2. It is the capability of handling unknown terms and values by using its imbedded dictionary that enables our approach to handle any key-term by getting its synonym. The dictionary itself is considered an advantage as it’s dynamic and can be filled with any medical terms. Different dictionary formats (XML and database) makes it easy for end-users to fill it in an easy way. Bottlenecks that may affect the algorithm: 1. The more dictionary filling process, the more accuracy we have in extracting different terms from the data sources. 2. Many difficulties are encountered when managing unstructured data sources, as it is difficult to get the relationships that these data sources are built on. Also an AI technique has been proposed aiming to generate medical clinical cases to be utilized by a CBR medical diagnostic system. This approach consists of five main steps: 1. Gathering the needed medical documents to generate EMR by using Semantic Similarity Retrieval Model (SSRM). Then these documents will be used to get the electronic patient records. 2. Converting the electronic patient records EMR to medical clinical cases by using a proposed methodology to map each EMR attribute to the appropriate medical case attribute. The technique is based