A framework for secure healthcare systems based on big data analytics in mobile cloud computing environments

 Technology

 14 views
of 11
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Description
In this paper we introduce a framework for Healthcare Information Systems (HISs) based on big data analytics in mobile cloud computing environments. This framework provides a high level of integration, interoperability, availability and sharing of healthcare data among healthcare providers, patients, and practitioners. Electronic Medical Records (EMRs) of patients dispersed among different Care Delivery Organizations (CDOs) are integrated and stored in the Cloud storage area, this creates an Electronic Health Records (EHRs) for each patient. Mobile Cloud allows fast Internet access and provision of EHRs from anywhere and at any time via different platforms. Due to the massive size of healthcare data, the exponential increase in the speed in which this data is generated and the complexity of healthcare data type, the proposed framework employs big data analytics to find useful insights that help practitioners take critical decisions in the right time. In addition, our proposed framework applies a set of security constraints and access control that guarantee integrity, confidentiality, and privacy of medical information. We believe that the proposed framework paves the way for a new generation of lower cost, more efficient healthcare systems.
Share
Transcript
  • 1. International Journal of Ambient Systems and Applications (IJASA) Vol.2, No.2, June 2014 DOI : 10.5121/ijasa.2014.2201 1 A FRAMEWORK FOR SECURE HEALTHCARE SYSTEMS BASED ON BIG DATA ANALYTICS IN MOBILE CLOUD COMPUTING ENVIRONMENTS Ahmed E. Youssef College of Computer & Information Sciences, King Saud University, Riyadh, KSA Faculty of Engineering, Helwan University, Cairo, Egypt ABSTRACT In this paper we introduce a framework for Healthcare Information Systems (HISs) based on big data analytics in mobile cloud computing environments. This framework provides a high level of integration, interoperability, availability and sharing of healthcare data among healthcare providers, patients, and practitioners. Electronic Medical Records (EMRs) of patients dispersed among different Care Delivery Organizations (CDOs) are integrated and stored in the Cloud storage area, this creates an Electronic Health Records (EHRs) for each patient. Mobile Cloud allows fast Internet access and provision of EHRs from anywhere and at any time via different platforms. Due to the massive size of healthcare data, the exponential increase in the speed in which this data is generated and the complexity of healthcare data type, the proposed framework employs big data analytics to find useful insights that help practitioners take critical decisions in the right time. In addition, our proposed framework applies a set of security constraints and access control that guarantee integrity, confidentiality, and privacy of medical information. We believe that the proposed framework paves the way for a new generation of lower cost, more efficient healthcare systems. KEYWORDS Electronic Health Records; Big Data; Mobile Cloud Computing; Information Security; Healthcare Systems, HL7. 1. INTRODUCTION The 21st century Healthcare Information Technology (HIT) has created the ability to electronically store, maintain, and move data across the world in a matter of seconds and has the potential to provide healthcare with tremendous increasing productivity and quality of services. It permits each provider to have his own database of patients' Electronic Medical Records (EMRs). Previous studies of the value of connected EMR systems estimated a potential efficiency savings of $77 billion per year at the 90% level of adoption; added value for safety and health could double these savings [10]. One problem in today's EMR systems is that they are highly centralized, each Healthcare Provider (HP) has its own local EMR system. This makes health information for any patient dispersed among different HPs and, therefore, its retrieval will be a challenge. The ability to universally access all patient healthcare information in a timely fashion is of utmost important [1, 10, 58]. Health information needs to be accessible and available to everyone involved in the delivery of patient healthcare from the researchers attempting to find causes, treatments, and cures for diseases to the patients themselves. Therefore, a high level of
  • 2. International Journal of Ambient Systems and Applications (IJASA) Vol.2, No.2, June 2014 2 data integration, interoperability, and sharing among different healthcare practitioners and institutions is required in order to deliver high-quality healthcare to the patients they serve [54]. The revolution in healthcare data size is another problem in today's Healthcare Information Systems (HISs). This revolution is not just about the massive size of healthcare data, but we also witness an exponential increase in the speed in which this data is generated and a complex varieties of data type (i.e., structured, semi structured, unstructured). The Development of new technologies such as capturing devices, sensors, and mobile applications is a major source of healthcare data. Additional sources are added every day; patient social network communications in digital forms are increasing, collection of genomic information became cheaper and more medical knowledge/discoveries are being accumulated. Such big healthcare data is difficult to process or analyze using common database management tools. Obviously, capturing, storing, searching, and analyzing healthcare big data to find useful insights will improve the outcomes of the healthcare systems through smarter decisions and will lower healthcare cost as well, however, it requires efficient analytical algorithms and powerful computing environments. Finally, the increased reliance on networked healthcare data brings new challenges to securing medical records in EHR systems. Authenticating individuals and authorizing global secure access to patients’ records are vital security requirements. Physical face-to-face methods of identifying and authenticating patients and providers no longer apply; methods of electronic identification and authentication are required. Moreover, electronic records are susceptible to inappropriate access, compromised data integrity, or widespread unauthorized distribution. New security measures are needed to secure patients’ records on HISs. In this paper we introduce a framework for secure HISs based on big data analytics in mobile cloud computing environments. This framework provides a high level of integration, interoperability, and sharing of EHRs among HPs, patients, and practitioners. It integrates distinct EMRs of a patient from different HPs distracted among different cities, states, and regions and store them in the Cloud data storage areas. Mobile Cloud computing technology [57-61] provides a fast Internet access, and provision of EHRs from anywhere and at any time with high availability. Due to the massive size of healthcare data, the exponential increase in the speed in which this data is generated and the complexity of healthcare data type, the proposed framework employs big data analytics to find useful insights that help practitioners take critical decisions in the right time. Our proposed framework applies a set of security constraints and access control that guarantee integrity, confidentiality, and privacy of medical data. Authenticated healthcare providers, practitioners, and patients are authorized by the Cloud Service Providers (CSPs) at different levels of privilege and permissions to securely access EHRs and retrieve patients’ information. We believe that the proposed framework paves the way for a new generation of lower cost, more efficient healthcare systems. The rest of this paper is organized as follows: section 2 discusses the problem of integrating patients' EMRs dispersed among different CDOs. Section 3 discusses how mobile cloud computing solution improves integration, interoperability, and availability of EHRs. Section 4 explores the issue of "Big" healthcare data analysis. Security issues associated with EHR are discussed in section 5. Our proposed framework for HISs is given in section 6. Finally, in section 7, we give our conclusion remarks and future work. 2. INTEGRATING ELECTRONIC MEDICAL RECORDS Today, there is a widespread use of EMRs or EHRs systems. These terms are used interchangeably by many in both healthcare industry and health science literature; however, they describe completely different concepts according to Health Information and Management System Society (HIMSS) Analytics [6, 7]. An EMR is a formatted record of patient health information
  • 3. International Journal of Ambient Systems and Applications (IJASA) Vol.2, No.2, June 2014 3 owned by a hospital or any healthcare provider. The data in the EMR system is the legal record of what happened to the patient during his encounter at the CDO and is owned and managed by one CDO [6]. A significant disadvantage to EMRs is that they cannot be easily and accurately electronically shared and distributed. On the other hand, HIMSS defined the EHR as “a longitudinal electronic record of patient health information generated by one or more encounters in any care delivery setting. Included in this information are patient demographics, progress notes, problems, medications, vital signs, past medical history, immunizations, laboratory data, and radiology reports. The EHR automates and streamlines the clinician's workflow” [7]. The definition of EHR system is “the set of components that form the mechanism by which EHRs are created, used, stored, and retrieved” [8, 9]. EHRs are typically composed of a subset of EMRs maintained by each CDO and is assigned to a patient. In [10] Zhang and Liu compared between EMR and EHR from different perspectives. This comparison is shown in Table 1. Table 1: A comparison between EMRs and EHRs [10] EMR EHR Definition The legal record of clinical services for patient within a CDO. A subset of EMRs from one or more CDOs where patient received clinical services. Owner Owned by one CDO Owned by several CDOs Customer and Usage Scope EMR systems are supplied by enterprise vendor and installed by hospitals, health systems, clinics, etc. EHR systems are run by community, state, or regional emergence, or national wide emergence organization. Right of patients Patients can get access to some EMR information once authorized by the EMR owner Patients are provided with interactive access as well as the ability to append information. Interoperability with other CDOs Each EMR contains the patient’s encounter in a single CDO. It does not contain other CDO counter data. Sharing information among multiple CDOs. An EHR provide a mean of communication among clinicians contributing to the patient’s care by sharing health information between different EMR systems in different CDOs. The challenge here is how to integrate distinct EMRs scattered in different CDOs in different cities, states, and regions to create unified EHRs. In our framework, the Cloud provides a solution for this problem by networking the CDOs and collecting patients’ EMRs from the interconnected CDOs. It is also desirable to have a unified standard format for EHRs to support interoperability and data sharing. 3. HEALTHCARE MOBILE CLOUD COMPUTING In recent years, mobile devices have started becoming abundant in many healthcare applications. The reason for the increasing usage of mobile computing is its ability to provide a tool to the user when and where it is needed regardless of user movement, hence, supporting location independence. However, it suffers some inherent problems such as limited scalability of users and devices, limited availability of software applications, resources scarceness in embedded gadgets, frequent disconnection and finite energy of mobile devices. In healthcare sector, the effect of these limitations is magnified due to the massive size, excessive complexity, and rapid generation of healthcare data. As a result, a wide range of healthcare applications are difficult to run in
  • 4. International Journal of Ambient Systems and Applications (IJASA) Vol.2, No.2, June 2014 4 mobile devices such as radiology processing and recognition, patients' social networking data management, genomic information and sensor data applications. In addition, progress in interoperation and sharing data among different EMR systems has been extremely slow due to the high cost and poor usability. What is needed is an environment that is capable of capturing, storing, searching, sharing and analyzing healthcare big data efficiently to provide right intervention to the right patient at the right time. Cloud computing [15-29] provides an attractive IT platform to cut down the cost of EHR systems in terms of both ownership and IT maintenance burdens for many medical practices. Cloud environment can host EHRs and allows sharing, interoperability, high availability, and fast accessibility of healthcare data. Cloud Computing (CC) platforms possess the ability to overcome the discrepancies of mobile computing with their scalable, highly available and resource pooling computing resources. The main idea behind CC is to offload data and computation to a remote resource provider (i.e., the Internet) which offers broad network access. The concept of offloading data and computations in the Cloud, is used to address the inherent problems in mobile computing by using resource providers (i.e., cloud resources) other than the embedded devices themselves to host the execution of user applications and store users’ data. The problems are addressed as follows: 1) by exploiting the computing and storage capabilities (resource pooling) of the cloud, mobile intensive applications can be executed on low resource and limited energy mobile devices, 2) the broad network access of the cloud overcomes the limited availability and frequent disconnection problems since cloud resources are available in anywhere and at any time, 3) the infrastructure of cloud computing is very scalable, cloud providers can add new nodes and servers to cloud with minor modifications to cloud infrastructure, therefore; more services can be added to the cloud, this allows more mobile users to be served and more portable devices to be connected [60]. A study by Juniper Research states that the consumer and enterprise market for cloud-based mobile applications is expected to rise to $9.5 billion by 2014 [61]. In healthcare sector we believe that this environment is very promising and is expected to change how healthcare services are provisioned. Mobile cloud computing technology will contribute to healthcare sectors in the following ways: • Integrating healthcare data dispersed among different healthcare organizations and social media. • Providing a shared pool of computing resources that is capable of storing and analyzing healthcare big data efficiently to take smarter decisions at the right time. • Providing dynamic provision of reconfigurable computing resources which can be scaled up and down upon user demand. This will help reduce the cost of cloud-based healthcare systems. • Improving user and device scalability and data availability and accessibility in healthcare systems. Healthcare cloud can provide two deployment Models. These models describe the level of data sharing among different CDOs, patients, and practitioners when using the cloud. These models are: • Private healthcare cloud: The cloud infrastructure is owned solely by a CDO. It may be managed by the CDO or a CSP and may exist on or off premise. The CSP provides the same capability in terms of security and privacy protection as those in the EMR system running by a CDO. • Community healthcare cloud: The cloud infrastructure is shared by several CDOs and supports a specific community that has shared concerns (e.g., mission, security
  • 5. International Journal of Ambient Systems and Applications (IJASA) Vol.2, No.2, June 2014 5 requirements, and policy). It is managed by a CSP or by the CDOs and may exist on or off premise. Healthcare services provided by healthcare clouds are classified as follows: • Software as a Service (SaaS): Healthcare applications, such as EHRs, are hosted as a service and provided to practitioners, healthcare providers, and patients across the Internet, with no need to install and run on their own computer. Hosted applications can be accessed through web browsers from various client devices such as laptops, PDAs and cell phones. Multiple users can share the applications and avoid the trouble associated with software maintenance, upgrading and the need for additional licenses. • Platform as a Service (PaaS): PaaS is a development platform that allows healthcare providers to not only deploy but also design, model, develop and test healthcare applications directly on the Cloud. It supports work in groups on collaborative healthcare projects where project team members are geographically distributed. This requires PaaS to provide development infrastructure including tools and programming languages. • Infrastructure as a Service (IaaS): healthcare providers can directly use independent virtual machines that isolate the underlying physical hardware of the cloud from them. They can dynamically provision/release virtual computing resources based on their increasing/decreasing resource demand. 4. HEALTHCARE BIG DATA Improving healthcare services and reducing medical cost are the ultimate goals of nations worldwide. However, the revolution of healthcare data size remains an obstacle that hinder achieve this goal. In 2012, worldwide digital healthcare data was estimated to be equal to 500 petabytes and is expected to reach 25,000 petabytes in 2020 [62]. Obviously, capturing, storing, searching, sharing and analyzing such big data to find useful insights will improve the outcomes of the healthcare systems through smarter decisions and will lower healthcare cost as well, however, traditional database management tools are no longer suitable to process these data. New efficient algorithms are required to accomplish this task. For example, in the United States, more than 71 million individuals are admitted to hospitals each year, according to the latest survey from the American Hospital Association. Studies have concluded that in 2006 well over $30 billion was spent on unnecessary hospital admissions. The Heritage Provider Network (HPN) arises the question: "Can we identify earlier those most at risk and ensure they get the treatment they need?" and it believes that the answer is "yes". To achieve its goal of developing a breakthrough algorithm that uses available patient data to predict and prevent unnecessary hospitalizations, HPN sponsored the Heritage Health $3 Million Prize Competition. Winning solutions will use a combination of several predictive models and the winning team will create an algorithm that predicts how many days a patient will spend in a hospital in the next year. Once known, HPs can develop new care plans and strategies to reach patients before emergencies occur, thereby reducing the number of unnecessary hospitalizations. This will result in increasing the health of patients while decreasing the cost of care [62]. Big data analytics is motivated in healthcare through the following aspects [62]: • Healthcare data is now growing very rapidly in terms of size, complexity, and speed of generation and traditional database and data mining techniques are no longer efficient in storing, processing and analyzing these data. New innovative tools are needed in order to handle these data within a tolerable elapsed time.
  • 6. International Journal of Ambient Systems and Applications (IJASA) Vol.2, No.2, June 2014 6 • The patient’s behavioral data is captured through several sensors; patients' various social interactions and communications. • The standard medical practice is now moving from relatively ad-hoc and subjective decision making to evidence-based healthcare. • Inferring knowledge from complex heterogeneous patient sources and leveraging the patient/data correlations in longitudinal records. • Understanding unstructured clinical notes in the right context. • Efficiently handling large volumes of medical imaging data and extracting potentially useful information and biomarkers. • Analyzing genomic data is a computationally intensive task and combining with standard clinical data adds additional layers of complexity. 5. SECURITY ISSUES In cloud-based HIS, security should be the top priority from day one. Patients’ data should be protected with comprehensive physical security, data encryption, user authentication, and application security as well as the latest standard-setting security practices and certifications, and secure point-to-point data replication for data backup. These security issues have been extensively investigated for cloud computing in general [13, 14, 30-53]. A major challenge to healthcare cloud is the security threats including tampering or leakage of sensitive patient’s data on the cloud, loss of privacy of patient’s information, and the unauthorized use of this inf
  • Related Search
    We Need Your Support
    Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

    Thanks to everyone for your continued support.

    No, Thanks