Wagdy Zahran’s scientific contributions

Pandemics like COVID-19 have posed new challenges in the healthcare sector around the world. Artificial Intelligence (AI) and the Internet of Healthcare Things (IoHT) have been widely used to combat the recent pandemic and provide assistance to the population. Security concerns in international cooperation impede the advancement of AI in IoHT services. Arguably, the confidentiality of data, the technology edge of AI providers, integrity, and availability of service are the primary concerns. To this end, in this chapter, we have proposed a blockchain-based secure framework for homomorphic AI in IoHT networks to handle security concerns. In this framework, we focus on AI as the core computation of IoHT networks. The proposed framework is based on blockchain technology and distributed storage to ensure integrity and availability in a decentralized network. The proposed framework uses homomorphic encryption to enable privacy-preserving computation, mainly AI services. Moreover, the security analysis of this framework shows that it is formally provable to meet the defined security requirements. We present a use case for diagnosing and monitoring COVID-19 during a pandemic in order to evaluate the proposed framework.KeywordsBlockchainInternet of healthcare thingsArtificial intelligenceSecurityHomomorphic encryptionPandemic

IoT technology is rapidly growing in all fields of modern industries. Billions of IoT devices contribute to facilitating life in various contexts. A centralized system can hardly handle the extensive volume of IoT networks. Blockchain technology provides an immutable decentralized platform for communication in IoT applications. However, blockchain does not provide a solution for the confidentiality of data, which can be vital in many IoT applications. To this end, in this paper, we define the security concerns of data sharing in the IoT application. On that basis, we propose a secure data-sharing framework based on blockchain. In this framework, broadcast encryption is used to provide confidentiality of data with minimum data overhead. Moreover, with homomorphic encryption, the proposed framework enables secure data queries without leaking any information about the data. In the security analysis of the proposed framework, we have formally proved that this framework meets the security requirements. Moreover, the proposed framework is evaluated in the teleconsultation use case. The evaluation results show the proposed framework’s strength in providing a secure and robust framework for data-sharing in the context of e-health.KeywordsIoTBlockchainSecureBroadcast encryptionHomomorphic encryption

The massive growth of the population with chronic diseases calls for a telecare system to enhance their quality of life and reduce their treatment costs. Most of the current solutions depend on reliable data, deterministic rules, or the similarity of patients, while studies have shown otherwise. To this end, in this paper, we have extended our previous work on the Hapicare framework to integrate probabilistic diagnosis and self-adaptive treatment. Our new framework enables sensors’ datastream analysis and online decision-making. Its ontology-based reasoning uses Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT) ontology to add contextual information to the collected data. Moreover, probabilistic reasoning is applied for diagnosis and screening to manage the uncertainty and unreliability of data as well as the indeterministic medical rules. The treatment system is designed to be modifiable by the experts and automatically adaptable to patients’ needs. The probabilistic diagnosis performance has been evaluated based on two public datasets regarding symptoms and risk factors of two chronic diseases: chronic kidney disease and dermatologic disease. The results show that our solution outperforms a classical classifier specifically when more than 40% of the data are missing. The proposed framework is also validated using four scenarios. The evaluation results demonstrate the ability of the proposed framework to help patients and doctors diagnose and treat medical conditions and episodes.

Due to longevity, the world population is getting older; this leads to an enormous number of patients with chronic diseases. Their vulnerability in facing viral and bacterial diseases, in particular in the case of the outbreak of the coronavirus, promotes teleconsultation since the latter reduces their physical interactions and consequently, their chance of contamination. Teleconsultation is considered more economical, comfortable, and practical compared to face-to-face consultations. Due to the criticality of the data and process in teleconsultation, there are numerous concerns, in particular in terms of reliability and security. Moreover, similar to all financial systems; the transparency concerns are also prominent in teleconsultation. To this end, we propose HapiFabric, a teleconsultation framework based on Hyperledger Fabric. Our proposed framework exploits this blockchain technology to improve security, reliability, and transparency of teleconsultation workflows. Without losing generality, we prioritize the elderly and patients with chronic diseases in HapiFabric becasue of their vulnerability. Our innovative teleconsultation workflows cooperate with a telemonitoring service to provide comprehensive medical care at the patients’ homes. We exploited Hapicare, an existing healthcare monitoring system with self-adaptive coaching using probabilistic reasoning, as one of the main participants of HapiFabric which provides telemonitoring services. Moreover, HapiFabric has other participants, namely patients, doctors, insurance, and auditors. We have opted for off-chain data storage of medical data using the InterPlanetary File System (IPFS). We evaluate the HapiFabric framework using two scenarios.

Given the exploding number of the elderly and patients with chronic diseases and the uneven distribution of clinicians, it is economically impossible to continue traditional medicine. Hence, the healthcare sector has been gradually gravitating towards telemedicine, which applies intelligent systems for more comprehensive medical services with minimum costs. The criticality of data and process involved in telemedicine raise various concerns in terms of reliability and security. To this end, in this paper, we propose HapiChain, a blockchain-based framework for patient-centric telemedicine. HapiChain exploits blockchain technology to improve security, scalability, and reliability of medical workflows. Although HapiChain is patient-centric, it also helps the clinicians to save time and prevent unnecessary trips without improvising the level of treatment. In HapiChain, we embed two primary telemedicine services, namely telemonitoring and teleconsultation. For the former service, Hapicare, an existing healthcare monitoring system with self-adaptive coaching using probabilistic reasoning, is used. HapiChain then completes this service by adding teleconsultation services exploiting blockchain technology. The HapiChain framework includes three main layers: (i) interface layer, (ii) DApp layer, and (iii) blockchain layer. In the first layer, Hapicare is used to communicates with the users, i.e., patients and doctors. DApp layer includes the required procedures for security and scalability of HapiChain, namely smart contracts and distributed storage. The latter is achieved using the InterPlanetary File System (IPFS). In the blockchain layer, Ethereum blockchain is used as a platform of DApps. We evaluate the HapiChain framework and the proposed teleconsultation services in a use-case.

Patients with chronic conditions require medical care at their home. To this end, a smart follow-up and monitoring system is proposed, called Hapicare; which applies ontology-based uncertain reasoning over IoT sensors data and self-assessment. While similar approaches rely on certain events and rules, the proposed monitoring system is based on probabilistic reasoning that interleaves Bayesian and non-monotonic inference. The latter is defined by using rule-based on concepts of the Semantic Sensor Network (SSN) and the SNOMED-CT ontologies. This system also considers uncertain contextual information captured from sensors and the history of patients in order to better diagnose the current situation and trigger suitable reactions. It allows also handling overlaps between symptoms, the possibility of errors and hidden facts. Hapicare is developed in the context of Medolution EU project.