Browsing by Author "Haddad, Alaa"

Accessing healthcare services by several stakeholders for diagnosis and treatment has become quite prevalent owing to the improvement in the industry and high levels of patient mobility. Due to the confidentiality and high sensitivity of electronic healthcare records (EHR), the majority of EHR data sharing is still conducted via fax or mail because of the lack of systematic infrastructure support for secure and reliable health data transfer, delaying the process of patient care. As a result, it is critically essential to provide a framework that allows for the efficient exchange and storage of large amounts of medical data in a secure setting, where the storing the data over the cloud do not remain secure all the time. Since the data are accessible to the end user only by using the interference of a third party, it is prone to breach of authentication and integrity of the data. This thesis introduces the development of a Patient-Centered Blockchain-Based EHR Management (PCBEHRM) system that allows patients to manage their healthcare records across multiple stakeholders and to facilitate patient privacy and control without the need for a centralized infrastructure. In addition, the proposed system ensures a secure and optimized scheme for sharing data while maintaining data security and integrity over the Inter Planetary File System (IPFS). Further, the proposed system introduces a sophisticated End to End Encryption (E2EE) functionality by combining the ECC (Elliptic Curve Cryptography) method and the Advanced Encryption Standard (AES) method. This is to enhance the security of system, reduce the computational power for memory optimization, and ensure authentication and data integrity. We have also demonstrated how the proposed system design enables stakeholders such as patients, labs, researchers, etc., to obtain patient-centric data in a distributed and secure manner that is integrated using a web- based interface for the patient and all users to initiate the EHR sharing transactions. Finally, the thesis enhances the proposed PCBEHRM system with deep learning artificial intelligence capabilities to revolutionize the management of the EHR and offer an add-on diagnostic tool based on the captured EHR metadata. Deep learning in healthcare now had become incredibly powerful for supporting clinics and in transforming patient care in general and is increasingly applied for the detection of clinically important features in the images beyond what can be perceived by the naked human eye. Chest X-ray images are one of the most common clinical methods for diagnosing several diseases. The proposed enhancement integrated deep learning feature is a developed lightweight solution that can detect 14 different chest conditions from an X-ray image. Given an X-ray image as input, our classifier outputs a label vector indicating which of 14 disease classes does the image fall into. The proposed diagnostic add-on tool focuses on predicting the 14 diseases to provide insight for future chest radiography research. Finally, the proposed system was tested in Microsoft Windows@ environment by compiling a smart contract prototype using Truffle and deploying it on Ethereum using Web3. The proposed system was evaluated in terms of the projected medical data storage costs for the IPFS on blockchain, and the execution time for a different number of peers and document sizes. The results show that the proposed system achieves a reduced storage cost of 73.4172% and a 76% in execution time in comparison to other proposed systems in the open literature. The Results of the study conclude that the proposed strategy is both efficient and practicable. The add-on deep learning diagnostic feature flags any present diseases predicted from the health records and assists doctors and radiologists in making a well-informed decision during the detection and diagnosis of the disease.

Skin disease is one of the common form of disease form in the world. Diagnosis of the skin diseases may requires a high level of dermatologist expertise. The advancement in computer and IT capabilities can offer a good opportunity and provide support to help in skin diseases diagnosis, which still suffer from shortage many countries and computer aided skin diseases diagnosis system can provide more objective and reliable solution to this issue. There are many researches in detecting skin disease like detection of skin cancer, and tumor skin. However the accurate recognition of disease is extremely challenging due to: low contrast between lesions and skin, visual similarity between disease and non-disease areas, and this study aims to detect skin disease by captured image and apply enhancement techniques in image for make it ready to diagnosis the skin diseases by apply segmentation the image by two of clustering algorithms for give more accurately result which there are K-Means clustering algorithm with the fixed number of clusters to do processing, and second one is Fuzzy C-Means algorithm which allows one piece of data to belong to two or more clusters so it is more flexible. By using two of segmentation algorithm, the study can achieve more accurately result in the project, whereas it reach to 94% within the dataset and 85% with the external data, making it a competitor for the rest of the projects especially it is processing four types of skin disease to detect which are: acne, psoriasis, melanoma, and heat rashes. The useful information that will help to detect the disease using mobile application with save time, its need to 5-8 minutes to get the final analysis result. The project is built successfully and the interface application is connecting properly database, and all the project functionalities is working properly, despite that there are some problems occurred through the image analysis with the data collected that are distorted by a watermark that obstacle the classification process. Moreover tips and instructions if possible to do them as a quick ambulatory are discussed all system functionalities is working properly, despite that there are some problems were we faced.