Search

The privacy protection mechanism in the health context is becoming a crucial task given the exponential increase in the adoption of the Electronic Health Records (EHRs) all around the world. This kind of data can be used for medical investigation and research only if it is filtered out of all the so called Protected Health Information (PHI). This paper proposes a clinical de-identification system based on deep learning techniques for Named Entity Recognition and aimed at recognizing PHI entities to be replaced by surrogates in EHRs for anonymization purposes. This system is based on ELECTRA, a recent neural language model, and is enhanced through a sub-document level analysis aimed at grouping input sentences together, through a Sentences Grouping Factor (SGF), with the aim of broadening the representation context and consequently enhancing its ability to learn. This system was experimentally tested on the official dataset distributed in 2014 by Informatics for Integrating Biology & the Bedside research group, exhibiting superior performance compared to the state of the art in terms of detection at the category level, crucial for properly substituting PHI entities with surrogates. The effectiveness of the proposed system with respect to its components has been also confirmed by a further experimental analysis performed by substituting BERT language model in place of ELECTRA and varying SGF in accordance with limitations concerning the maximum input size for the language model used.

Medical personnel is the front-liner in receiving the electronic Protected Health Information (ePHI). Thus, they become a crucial factor in preserving the security of ePHI in HIS. Previous studies exhibit numerous negligence issues from medical personnel resulting in data leakage. Therefore, this study is conducted to analyze the security awareness level, and which aspects and profile groups need more emphasis on understanding the security standard. The assessment uses the HIPAA Security Rule as a reference and is divided into administrative and physical aspects. The results illustrated an inadequate understanding of the medical personnel with score of 2,588 from the target

Chronic disease exists over a period of time and it is very crucial because it can affect the health of disability people more. Normally people think that they are not suffering or affected by the disease because they do not have symptoms. But it does not necessarily mean a person with no symptom has no chronic disease. This paper presents design and prototype implementation of a blockchain system which remotely monitors patient health records. The patient monitoring system is a big challenge and other security threats arises as the health care data transferred from one to another and authorization to create and read transactions, is a major concern related to data loss. The data loss of the patient protected health information which are generated from the devices should be handled carefully. So in this paper we proposed a solidity based smart contract run over a Ethereum virtual machine to facilitate the secure analysis and storing of transactions from and to the sensors. Using the Ethereum protocol, based on a private blockchain and writing the smart contracts to keep track of the patient health information. We have created an automatic system through which the sensors collects the data, then communicates with the decentralized application via the smart contract. The method inside the smart contract collects data when they are called, also reads and writes transactions of all events on the Ethereum virtual network. This solidity based smart contract system along with injected web3, metamask, and truffle environment would support alert transaction to the patient and medical professionals.

Despite well-documented cyber threats to patients' protected health information (PHI), sparse evidence exists about the state of cybersecurity behavior of health care workers and medical private practices. There is evidence of insecure behavior in hospital settings, even though specific insights about private practice are still absent. In addition to mandatory standards for securing PHI, such as the Health Insurance Portability & Accountability Act (HIPAA), small business viability and their patients' security and privacy are critically dependent upon technology availability and reliability. In this survey of 131 clinical audiologists we show that many lack time, staff expertise, or funds to deploy adequate cybersecurity that prevents and mitigates threats to security and privacy. We find widespread deployment of HIPAA-compliant cybersecurity, including antivirus software and individual logins. Only 9.9% of participants reported at least one data breach in 2019, significantly less than the average for small businesses and health care providers, and only 24.4% reported having cyber insurance. Practice owners view patient data as well protected and unlikely victims for cyber attacks and breaches. These results have important implications for cybersecurity products and services, and to medical professionals who must acknowledge the acute importance of cybersecurity in securing protected health information and mitigating risks. Small business private practice health care providers who are particularly sensitive to the impacts of cyber attacks and must prioritize and adopt countermeasures that decrease the risks to patients and their own businesses.

Static access control models do not take the dynamic sensitivity and risk levels of data and the compliance requirements together when allowing or disallowing access to part or whole of such data. For example, HIPAA requires of "minimum access" to protected Health information. In general several compliance requirements require "least-privilege" principle to be followed for protecting private data. In that process, the existing access control models fail to honor compliance requirements. In this paper, we have analyzed this problem and proposed how dynamic access control can be used to reduce the risk of sensitive data exposure due to static access control models.

Clinical narratives host vast accumulations of patient data pivotal for research and development of health related products. In order for this data to be utilized, the underlying protected health information needs to be de-identified to ensure medical confidentiality. Given the voluminous size of clinical texts, manual de-identification of such large datasets is both expensive and impractical. Therefore, the concept of automated de-identification is a highly appealing prospect. Machine learning or model based sequential labeling algorithms, such as the named entity recognition algorithms and rule-based algorithms are among the most effective approaches to automated de-identification. A natural question to ask is how we can combine them to have the best of both worlds. In this paper, we present an analytical and easy to interpret framework to dynamically combine a sequential labeling model and a soft-rule-based model in an incremental learning setup. This framework is applied to a case study, which is part of a project prototyping automated de-identification system for New Zealand clinical free text data. Evaluations show that our approach can accommodate changes in the incoming data through dynamic updating. The simplicity of the framework also allowed us to gain insights on behaviour e.g. change of importance between the machine learning and rule models.

Cyber data breaching has tremendously increased over the years, especially in countries like India. Medical documents have information more valuable than any other document shared online. Various laws came into existence which restricts the flow of protected health information in any sort of communication. Considering the possible threats involved in medical data transfer, there is a need to de-identify protected health information in any type of medical document effectively and also minimize the possibility of reverse engineering or re-identification. Existing works completely focus on electronic health records with only textual data. Our aim is to present the importance of de-identification in visual data along with textual features and also show a method for achieving it using a transfer learning based approach. An end-to-end artificial intelligence based application is presented which de-identifies all types of protected health information from either an image or a pdf with both textual and image data or DICOMs.

The digitizing medical record has seen a pattern shift in the healthcare industry which increases the data in terms of complexity, diversity, and timeliness. Healthcare industry is encounters crucial threat owing to security breaches of healthcare databases. The patients were provided to destitution due to scamming data and stolen information by medical identity theft like data breaches are not influenced patients who are PHI (Protected Health Information) and PII (Personally Identifiable Information) but healthcare institutions. Automated health care system introducing personal and electronic health records (PHRs and EHRs) increase more data risk which advises privacy and security policies measures. Biometrics need in healthcare industry is increasing in the worldwide healthcare market. This paper identifies the healthcare data breaches and their primary causes with the role of PHI and HIPAA Act for dissuading data breaches. HIPAA Privacy Rule provides policies and standards to preserve Protected Health Information (PHI) of individuals held by the entities. In biometric market HIPAA Act enforces various needs to preserve confidentiality and privacy of patient information attained from healthcare facilities to develop fulfillment for dealing various principles.

Comprehend Medical is a stateless and Health Insurance Portability and Accountability Act (HIPAA) eligible Named Entity Recognition (NER) and Relationship Extraction (RE) service launched under Amazon Web Services (AWS) trained using state-of-the-art deep learning models. Contrary to many existing open source tools, Comprehend Medical is scalable and does not require steep learning curve, dependencies, pipeline configurations, or installations. Currently, Comprehend Medical performs NER in five medical categories: Anatomy, Medical Condition, Medications, Protected Health Information (PHI) and Treatment, Test and Procedure (TTP). Additionally, the service provides relationship extraction for the detected entities as well as contextual information such as negation and temporality in the form of traits. Comprehend Medical provides two Application Programming Interfaces (API): 1) the NERe API which returns all the extracted named entities, their traits and the relationships between them and 2) the PHId API which returns just the protected health information contained in the text. Furthermore, Comprehend Medical is accessible through AWS Console, Java and Python Software Development Kit (SDK), making it easier for non-developers and developers to use., ICMLA 2019. $\copyright$ 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses in any current or future media including reprinting/republishing this material for advertising, promotional purposes, creating new collective works, for resale or redistribution to servers or lists, reuse of any copyrighted component of this work in other works. arXiv admin note: text overlap with arXiv:1812.05270

e-Healthcare promises to be the next big wave in healthcare. It offers all the advantages and benefits imaginable by both the patient and the user. However, current e-Healthcare systems are not yet fully developed and mature, and thus lack the degree of confidentiality, integrity, privacy, and user trust necessary to be widely implemented. Two primary aspects of any operational healthcare enterprise are the quality of healthcare services and patient trust over the healthcare enterprise. Trust is intertwined with issues like confidentiality, integrity, accountability, authenticity, identity, and data management, to name a few. Privacy remains one of the biggest obstacles to ensuring the success of e-Healthcare solutions in winning patient trust as it indirectly covers most security concerns. Addressing privacy concerns requires addressing security issues like access control, authentication, non-repudiation, and accountability, without which end-to-end privacy cannot be ensured. Achieving privacy from the point of data collection in wireless sensor networks, to incorporating the Internet of Things, to communication links, and to data storage and access, is a huge undertaking and requires extensive work. Privacy requirements are further compounded by the fact that the data handled in an enterprise are of an extremely personal and private nature, and its mismanagement, either intentionally or unintentionally, could seriously hurt both the patient and future prospects of an e-Healthcare enterprise. Research carried out in order to address privacy concerns is not homogenous in nature. It focuses on the failure of certain parts of the e-Healthcare enterprise to fully address all aspects of privacy. In the middle of this ongoing research and implementation, a gradual shift has occurred, moving e-Healthcare enterprise controls away from an organizational level toward the level of patients. This is intended to give patients more control and authority over decision making regarding their protected health information/electronic health record. A lot of works and efforts are necessary in order to better assess the feasibility of this major shift in e-Healthcare enterprises. Existing research can be naturally divided on the basis of techniques used. These include data anonymization/pseudonymization and access control mechanisms primarily for stored data privacy. This, however, results in giving a back seat to certain privacy requirements (accountability, integrity, non-repudiation, and identity management). This paper reviews research carried out in this regard and explores whether this research offers any possible solutions to either patient privacy requirements for e-Healthcare or possibilities for addressing the (technical as well as psychological) privacy concerns of the users.

The Electronic Health Record (EHR) is the implementation of a computer system to keep a history of patient health records. All information related to patients is stored as patients who have medical history, immunization status, sugar level, and blood pressure records. EHR also contains the patient protected health information such as patient name and patient id. However, before processing further any text processing method, the protected health information needs to be removed from the data. This research employs a combination of long short term memory neural networks and conditional random fields in order to remove protected health information within the data. We employ several evaluations criteria to discover the best model. Our final evaluation result yields 0.76 the proposed model best result.

Patient data are regarded as highly sensitive and protected information by federal, state and local policies that make it available to only those who have been given access to Protected Health Information (PHI). In many applications, the access to PHI and real patient data can be substituted with generated realistic synthetic data used instead of real patient data. While methods exist that can generate synthetic data, it is unclear how to evaluate synthetic data quality. The objective of this paper is to present investigation of a new method for statistically testing the quality of synthetic patient data. Weighted Itemsets Error (WIE) measure compares frequent itemsets in the synthetic data with expected itemsets in real data, thus allowing for evaluating cooccurrence of data items. The derived measure is tested in the context of synthetic data comprising of medical diagnoses. The results demonstrate the effects of parameters that control WIE measure, and indicate that WIE is a simple yet powerful approach for evaluating synthetic datasets.

Making healthcare energy efficient and green is an excellent way to help solve the Climate Crisis. The UN Climate Agreement on reducing carbon emissions reached in Paris during December, 2015, along with all the recent critical climate events, help raise awareness to the urgent need to reduce electricity use through efficiency. Green Healthcare, Green Computing, and Green IT (Information Technology) are all excellent ways to reduce electricity use and save money doing it. Globally, the healthcare sector is growing in importance and plays a key role in world economics. The healthcare sector makes heavy use of technology including social media. Technological advances have revolutionized the healthcare industry worldwide – from modern testing techniques to improved surgical equipment, remote health monitoring technologies with the help of modern digital equipment, etc. There are many online healthcare portals. The complexity of the healthcare industry helps account for the large environmental footprint. A big challenge facing the healthcare sector is how best to improve the energy efficiency and sustainability of this very complex system. Efforts over the past few years to analyze and create highly efficient data centers presents an excellent opportunity for cost effective Green IT at hospitals. Given the complexity of the healthcare industry, there is a need for extensive use of data science, Big Data, and analytics as an ideal way to determine how green healthcare outcomes can be improved. Hospitals and healthcare in general can take significant steps in the green direction by combining big data analytics with cloud computing. This paper gives examples of how Data Science, Big Data, Analytics, and Cloud Technology can be used in healthcare to significantly improve a hospital’s IT Energy Efficiency along with information on the best ways to improve energy efficiency for healthcare in a cost effective manner.

General Data Protection Regulation (GDPR) is no more buzz word and it sets new standard on security across globe. Every organization who deals with data started doing self-assessment to check how it has impact on their business and what are all the ways they can prepare themselves to comply with GDPR. Since 1995, Europe Union (EU) followed "Data Protective Directive" (Directive) on Data privacy. Fourth Industrial Revolution (4IR) has range of new technologies covering digital, artificial, biological and big data and impacting all discipline from aeronautical to economies and industries. Because of fast-moving technology and transformed individual and business behaviors, directive is outdated and is replaced with the General Data Protection Regulation (REGULATION (EU) 2016/679) Compared with Directive, GDPR is most ambitious one and it covers more operators under this act. The regulation completely changes the groundwork for how organizations can manage personal data of EU citizens. GDPR gives more control on Personally Identifiable Information (PII), Protected Health Information (PHI) or other sensitive information and imposes new rules on organization who manage and process PII or PHI. Objective of this white paper is to give broad overview of forthcoming GDPR and it doesn’t focus on legal clause or penalty details. This covers the difference between Directive and GDPR, who are all covered under these new regulations. This also gives idea about consequences of the GDPR if an organization don’t comply with GDPR and how organization to prepare themselves so that they can continue their business as usual without any impact and guide to avoid data breach and penalty.

This paper describes the de-identification of personally identifiable information (PIIs) in electronic health records (EHRs) using two models of conditional random fields (CRFs) and bidirectional long short term memory networks (LSTMs). Most medical records store private information such as PATIENT NAME, HOSPITAL NAME, LOCATION, etc. that needs to be de-identified or redacted before being passed on for further medical research. The process of removing such information using machine learning techniques is started with pre-processing of raw data by tokenization and detection of sentences. On comparing the techniques, it is noted that CRFs require manual feature engineering to train the model whereas LSTM is capable of handling long term dependencies without much insight about the dataset. Bi-directional LSTM network was used to generate context information from suitable word representations. Finally, a predictive layer was applied to predict the protected health information (PHI) terms having maximum probability.Evaluated with the i2b2 gold data set of clinical narratives of patients of 2014 De-identification challenge, we propose an efficient solution for redaction using two models, both of which achieve good F-scores for PHIs of all types. The LSTM-based model achieved a micro-F1 measure of 0.9592, which performs better than the CRF-based model.

To preserve patient confidentiality, there is a need to identify PHIs (Protected Health Information) from free text text clinical records, and such sensitive information must either be removed or replaced. Identification of the PHI's are normally performed manually on large sets of structured EHR databases, which is time-consuming, prohibitively expensive and error-prone. Hence, methods for automatic or semi-automatic identification of personal health information are of significant scientific and commercial interest. In this paper, we propose an innovative computational framework based on novel text mining and machine learning algorithms for automatic identification of PHIs from massive, unstructured free text clinical records, discharge summaries and other care documents. The experimental evaluation of the proposed algorithmic framework development, for several publicly available i2b2 challenge datasets from Informatics for Integrating Biology & the Bedside (i2b2) shared tasks, has shown promising outcomes.

This paper describes a framework for leveraging the cloud platform and big data technologies to perform medical image data analytics even across multiple institutions. The key challenges we have addressed are the security, privacy requirements, scalability of the solution and use of cloud based analytics for the existing proprietary legacy systems with network connectivity in hospitals. The Digital Imaging and Communication in Medicine (DICOM) medical images acquired for clinical purposes are to be shared with radiologists and institutions for interpretation of images to support disease diagnosis, who are miles away from the institutions. Prior to sharing DICOM images with third parties, we need to follow strict guidelines with respect to de-identification of Protected Health Information (PHI) from the medical data to be shared. To de-identify PHI information from images, we have devised a newer generation de-identification techniques based on the big data platform to obscure privacy information from DICOM tags, embedded text in images and face information from CT and MR images. Further to facilitate accurate analysis on medical images, Clinical Decision Support System (CDSS) inference model is developed. In the paper, we proposed few use cases and developed a cloud based framework to distribute/share clinical images with CDSS to radiologists on the move and to the institutions that do not exist in the host organization premises. The developed solution satisfies all the PHI de-identification requirements, supports scalability by efficiently using big data cloud technologies, for faster and reliable processing. We covered obstetrics/gynecology ultrasound application using deep learning approach as an example to illustrate CDSS.

The healthcare sector has generally been a late adopter of information technology solutions. As a result of the American Recovery and Reinvestment Act of 2009, the Centers for Medicare and Medicaid Services implemented a program whereby financial incentives were made available for eligible healthcare entities and healthcare providers implementing health information technology solutions. These healthcare entities and providers were required to attest to "meaningful use" (e.g. electronic data capture of clinical data, provision of electronic health records to patients) in order to receive the financial incentives. This program, more than any other key driver, has transformed the utilization of health information technology (HIT) in clinical settings. Health IT is now ubiquitous. With the advent of these HIT solutions has come large caches of private and protected health information which must be guarded from both accidental disclosure and nefarious criminal activity. Compliance monitoring efforts by the Department of Health and Human Service's Office for Civil Rights have increased dramatically in recent years with multi-million dollar fines being levied across the country for security gaps. As a result of this increased risk, many healthcare organization are revisiting their information security position and culture in the age of electronic medical records. This paper will review the current state of that culture.

Cloud-based analytics allow for inexpensive processing of large amount of data. However, processing protected health information (PHI) in cloud is a challenging task due to strict regulations (e.g., HIPAA) requiring features (e.g., dataisolation) which most cloud-based platforms do not currentlysupport in their offerings. This makes it difficult to leveragemany technologies well suited to the cloud (e.g., Apache Spark)to process PHI. To address this issue, we have developedthe Watson Health Cloud (WHC), a cloud-based platformfor the storage and analysis of large amount of PHI. TheWHC enables all the features necessary to store and processPHI, with little customization needed by the end-user. Thispaper describes the lessons learned from developing a cloudplatform for PHI. Specifically, we discuss the architecture andimplementation challenges we faced throughout development. We hope the insights gained from our experiences help otherswhen designing frameworks and applications which processPHI.

The electronic collection of patient information is a common practice across healthcare organisations in South Africa. Patients are encouraged to manage and control their own health data and information through the use of personal electronic health records (PEHRs). However, as this is a new type of electronic health record, there are concerns that must be addressed before patients make use of the technology. One of these concerns relate to using mobile devices to manage PEHRs, as patients fear that their health data may be breached due to the mobility and security concerns of these devices. The purpose of this paper is to investigate the information security controls that health care providers must put in place to protect PEHRs accessed from a mobile device. An inductive research approach was used which included an extensive literature review, while a thematic analysis of the data was used in identifying, analysing and reporting patterns within the data. The conceptual m-Health privacy framework was used to identify the 10 privacy principles for the mobile health platform and compared with the three distinct information security threats for the mobile platform. The study found that the data in transit was not as well protected by the framework, while the individual and database of the health care organisation was better regulated. The recommendation of the study is to improve the framework through the inclusion of specific information security controls to protect a patient's privacy whilst in transit when using PEHRs.

Healthcare system in America has moved to handle computerized healthcare data and even though the processing became easier it has also given rise to risks never faced before. With the availability of health data to customers via his/her mobile device, we're seeing Protected Health Information (PHI) data flowing through multiple layers before reaching the customer. This dynamic further increases risks and compliance has to be ensured at every level. According to studies, 60% of PHI data thefts are initiated by insiders due to improper/careless handling or accessing data with malicious intent. This paper will focus on the computational methodologies and approaches needed to ensure compliance and minimize the risks in handling Healthcare data.

The Health Authority - Abu Dhabi (HAAD) mobile e-Service is a smartphone or smart device installed with the HAAD mobile app. This connects to one or more e-services at the HAAD Cloud to facilitate healthcare services for the residents at the Emirate of Abu Dhabi in the United Arab Emirates (UAE). A mobile device in this context can be effectively considered Internet of Things (IoT), which can provide advanced online services to both healthcare provider and requestor under the control and monitor of the HAAD. Health information is among the most sensitive information of an individual that can be collected and shared. The information that needs to be protected in the healthcare sector is often referred to as Protected Health Information (PHI). Service providers with a good reputation for privacy protection will find it easier to build a trusted relationship with their users. The Health Insurance Portability and Accountability Act of 1996 (HIPAA) defines a set of security and privacy rules to be followed by healthcare providers in the United States of America. The HIPAA standards are designed for protecting health information. This paper discusses related privacy requirements for Mobile e-Service at the HAAD in accordance with the HIPAA privacy requirements.

In recent years, sharing electronic medical records (EMRs) for more researchers outside the associated institutions is significant. For privacy preservation of the corresponding patients and the associated institutions, a de-identification task on the EMRs to be shared is a must. Although the deidentification task has been considered with positive research outcomes worldwide, especially those from the i2b2 (Informatics for Integrating Biology and the Bedside) shared tasks in 2006 and 2014, the task has not yet been a solved problem and still needs more investigation realistically. In this paper, we propose an automatic de-identification solution in a multilevel hybrid semi-supervised learning paradigm with a key focus on correctly identifying protected health information (PHI) in the EMRs. Similar to the existing works, our work defines a hybrid approach by combining a machine learning-based method with a conditional random fields model and a rule-based method in a post-processing phase to handle the PHI types with disambiguity. Nevertheless, our work is more general and practical. First, it considers the structure complexity of each EMR so that each section can be treated properly for more correct PHI identification up to its structure complexity: structured, semi-structured, or un-structured. Second, each EMR is then examined in our approach at three different levels of granularity such as a token level in the supervised learning phase, an entity level in the rule-based post-processing phase, and a section level along with the structure complexity in the semi-supervised learning phase. Many various detail levels will give our approach a deeper look at each EMR for more effectiveness. Third, our solution is conducted in a self-training manner so that it can get started with a small annotated data set in practice and get more effective with new EMRs over time. Evaluated with the i2b2 data set in comparison with the related works, our solution is effective with better F-measure values for the AGE, LOCATION, and PHONE PHI types and comparable for the other PHI types.

There are many potential security risks associated with viewing, accessing, and storage of DICOM files on mobile devices. Digital Imaging and Communications in Medicine (DICOM) is the industry standard for the communication and management of medical imaging. DICOM files contain multidimensional image data and associated meta-data (e.g., patient name, date of birth, etc.) designated as electronic protected health information (e-PHI). The HIPAA (Health Insurance Portability and Accountability Act) Privacy Rule, the HIPAA Security Rule, the ARRA (American Recovery and Reinvestment Act), the Health Information Technology for Economic and Clinical Health Act (HITECH), and applicable state law mandate comprehensive administrative, physical, and technical security safeguards to protect e-PHI, which includes (DICOM) medical images. Implementation of HIPAA security safeguards is difficult and often falls short. Mobile device use is proliferating among healthcare providers, along with associated risks to data confidentiality, integrity, and availability (CIA). Mobile devices and laptops are implicated in wide-spread data breaches of millions of patients’ data. These risks arise in many ways, including: i) inherent vulnerabilities of popular mobile operating systems (e.g., iOS, Android, Windows Phone); ii) sharing of mobile devices by multiple users; iii) lost or stolen devices; iv) transmission of clinical images over public (unsecured) wireless networks; v) lack of adequate password protection; vi) failure to use recommended safety precautions to protect data on a lost device (e.g., data wiping); and vi) use of personal mobile devices while accessing or sharing e-PHI. Analysis of commonly used methods for DICOM image sharing on mobile devices elucidates areas of vulnerability and points to the need for holistic security approaches to ensure HIPAA compliance within and across clinical settings. Innovative information governance strategies and new security approaches are needed to protect against data breaches, and to aid in the collection and analysis of compliance data. Generally, it is difficult to share DICOM images across different HIPAAcompliant Picture Archive and Communication Systems (PACS) and certified electronic health record (EHR) systems - while it is easy to share images using non-FDA approved, personal devices on unsecured networks. End-users in clinical settings must understand and strictly adhere to recommended mobile security precautions, and should be held to greater standards of personal accountability when they fail to do so.

Virtual health care or e-Health is a powerful paradigm for creating patient-centered and technology supported service-oriented health care systems. Such systems can provide effective health care to everyone at any time and from anywhere. Health care providers, clinical technicians, domain experts, physicians, and patients may be geographically distributed, yet are connected through a reliable network for sharing their knowledge and expertise. They may use a variety of devices, such as smart medical devices, or smart phones, or laptops to automatically access, share, and synthesize health related knowledge, patient records, and clinical information. In this integrated health care environment decision making is leveraged on collective intelligence and social responsibility. Context-dependent privacy and security rules can be enforced in knowledge sharing and health service delivery. In this paper we introduce a holistic mobile health care model which is context-aware, knowledge-centric, and patient friendly. The model facilitates cooperation of several health care partners and patients so that knowledge and evidence based treatment will be available to all clients at all times in all places.

Healthcare software applications are designed to collect, store, and manage patients' personal and medical information. Such applications are required to maintain the patients' privacy and to comply with the privacy laws and regulations. In the United States, patients' privacy is protected with federal regulations, more specifically the Health Insurance Portability and Accountability Act (HIPAA) of 1996 and its amendments. To guarantee compliance with HIPAA, the software application must have a decision engine which should be consulted before any operation is carried on the patients' information to determine the operation validity and compliance. This decision engine will use HIPAA privacy rules in the decision making process, which triggers the need to formally express HIPAA privacy rules in the form of formal privacy policies. In this work, we evaluate the potential languages that can be used to formally express the extracted HIPAA privacy policies. Also, we expose any required extensions to the specification language features to support the decision engine logic.

There is a high-tech term called telemedicine, which uses information technologies and telecommunication for exchanging medical information among patients and health service providers from different locations. Many video conferencing tools such as WebEx, Go To Meeting, Skype, Google+ Hangouts, etc. Are commonly used these days. Even though these tools vouch for some level of privacy and secured encrypted connections, there are still security risks and vulnerabilities associated with them such as data leaks, call intrusions, identity theft, etc. The risk is even higher during medical video conferencing as there involves many protected health information (PHI) data exchanges. And, any such violations or breach of PHI data can result in civil and criminal penalties as per the Health Insurance Portability and Accountability Act (HIPAA). In this paper, we conduct a literature survey on the security level of such tools, associated risks and possible alternative methods or tools.

The environmental impact of the healthcare sector has become an important factor globally and is continuing to draw the attention of regulators. The energy use of the healthcare sector (whose largest sub-segment is ‘hospitals’) has been growing due to many factors. These factors include the rapid growth and adoption of Information and Communication Technology (ICT) in healthcare. The new IT technologies and applications used in healthcare include ‘cloud computing’, ‘mMedicine’, i.e. ‘mobility in Health’, eHealth, and tele(health) care for ‘remote delivery of healthcare services’. In general, the healthcare industry needs to reap the benefits of emerging technologies such as mobile computing and cloud computing, along with the use of Health Information Technology (HIT) to help solve the ever growing operating cost problems. One challenge facing the healthcare sector is how best to calculate the energy efficiency of this very complex sector. The work done over the past few years to analyze and create very energy efficient data centers presents an excellent opportunity for cost effective green IT at hospitals.

This paper aims to develop an approach that enables cloud computing clients to verify health regulatory compliance claimed by cloud computing providers. In this approach, clients of cloud computing could check automatically how the cloud provider meets the regulatory compliance such as HIPAA legislation for their health records. Although cloud providers often furnish their services with third party certifications on meeting regulatory compliances, the client does not have any means to verify how regulatory compliances are actually achieved in a wide variety of cloud service scenarios in relation to their electronic protected health information (e-PHI). Our approach is based on three processes: (i) Mechanisms to represent health regulations in machine processable form; (ii) Collection of service specific compliance related real-time data from cloud servers; and (iii) Automatic reasoning about the compliances between the machine processable regulations and the collected data from servers.

The key challenges in the area of public health informatics are, the identification of relevant health data sets, its representation and meaningful use of the information for decision making. To make effective use of data represented in Public Health Records, the data needs to be `seamlessly' shared or be interoperable among health care providers. It is believed that adoption of health care standards will help achieve interoperability. However, analyzing and identifying the standard most suitable for the organization is not a trivial task. The authors propose a simple, informal method to identify the appropriate standard, based on requirements, to achieve interoperability. The method is applied to a real world case study of a Primary Health Care provider in India. A scenario, where an expecting mother needs to be referred to the hospital for a pregnancy related medical condition is considered. The authors model data, analyze and identify standards relevant for interoperable transfer of maternal health information between public health centres and hospitals.

The interest for clinical research, using medical data stored in the EMR, is increasing. However, perception and attitude medical data, including protected health information, could differ depending on the person. Different perception and attitude could interfere with the activation of medical information utilizing. Therefore, we attempted to find different perception and attitude toward protected health information preserving medical data in clinical research. We collected 267 paper and online surveys, from three groups: clinical researcher (n=113), non-clinical researcher (n=72) and patients group (n=82). And differences among three groups are measured in terms of perception and attitude toward protected health information. Three groups have significant difference, except agreement using of medical data including PHI, in perception and attitude toward protected health information (p

Health care industries are adopting Electronic Medical Record (EMR) system from paper based records. With EMR, health services can be provided at accelerated rate but privacy, security and storage of information will be of concern. There are different regulations for the use and disclosure of health information. In this research study, we focus on Health Insurance Portability and Accountability Act (HIPAA) and discuss how it protects health information of an individual while allowing the flow of information to carry out necessary health care functions. The web based EMR system is proposed based on security and privacy features defined by HIPAA.

People in the past thought there must be a replacement to the healthcare system of that time that almost never provides practitioners timely and efficient access to a patient's complete health history. An electronic health record (EHR) is an evolving concept defined as a systematic collection of electronic health information about individual patients or populations.Emerging electronic health record models present numerous challenges to health care systems, physicians, and regulators. This article provides explanation of some of the reasons driving the development of the EHR, describes three EHR models of currently developing in Australia and United Kingdom and the United States, and discusses some of the practical and legal challenges that health care providers potentially face both during and after EHR implementation.

The University of California has committed to the development of a system to encourage collaboration among its 5 Medical Center campuses. (UC Davis, UC San Francisco, UC Los Angeles, UC Irvine, UC San Diego). The name of this system is UC-ReX, for the UC Research eXchange. A key component of this system is a tool that identifies cohorts of research participants across campuses. Each campus has established an instance of i2b2 (Informatics for Integrating Biology and Bedside) onsite. The use of SHRINE (Shared Health Information Network) technology enables the propagation of federated queries across instances of i2b2. UC-ReX is (presently) a SHRINE network. By leveraging i2b2 and SHRINE technologies across participating academic medical centers, the University of California system has stood up a resource that allows access to the de©\identified records of over 12 million patients across the state. This project provides a governance structure, infrastructure, and front end that enables research teams to validate the existence and size of potential research cohorts through a user friendly UI while eliminating the possible exposure of Protected Health Information (PHI). We discuss the technology that allows sharing of de-identified information among the independently operated medical centers, with multiple electronic medical record systems, in the UC-ReX network, the mechanisms by which these tools were implemented, the security model that drives the network infrastructure setup, and present the resulting network infrastructure as the model is brought into practice. Ultimately this project allows a researcher with the appropriate authorization, access to a grand total of 12.4 million patients with an estimated number of approximately 175 million observa

Introduction: Electronic medical records (EMR) are considered superior in documentation of care for medical practice. Current disaster medical response involves paper tracking systems and radio communication for mass casualty incidents (MCIs). These systems are prone to errors, may be compromised by local conditions, and are labor intensive. Communication infrastructure may be impacted, overwhelmed by call volume, or destroyed by the disaster, making self-contained and secure EMR response a critical capability. As the prehospital disaster EMR allows for more robust content including Protected Health Information (PHI), security measures must be instituted to safeguard these data. Objectives: To develop a secure prehospital disaster triage/EMR system that prevents unintentional disclosure of private information, may be used by prehospital personnel during the MCI triage process, and can be relayed via wireless system to local and distant medical assets. Methods: The Wireless Information System for medicAl Response in Disasters (WIISARD) Research Group developed a handheld linked wireless EMR system utilizing current technology platforms. Smart phones connected to radio frequency identification (RFID) readers may be utilized to efficiently track casualties resulting from the incident. Medical information may be transmitted on an encrypted network to fellow prehospital team members, medical dispatch, and receiving medical centers. Results: This system has been field tested in a number of exercises with excellent results and future iterations will incorporate robust security measures. Conclusions: A secure prehospital triage EMR improves documentation quality during disaster drills.

Security and privacy requirements are often not explicitly stated and are often not easy to elicit. In this paper, we discuss data use agreements (DUAs) as a source of security and privacy requirements that can be leveraged by requirements engineers. Within the healthcare domain, regulations created pursuant to the U.S. Health Insurance Portability and Accountability Act (HIPAA) specify that a DUA must exist for certain uses and disclosures of protected health information as a limited data set. For compliance reasons, it is important for requirements engineers to ask for and evaluate DUAs, as they are legally binding on the parties. We discuss HIPAA-governed DUAs and the information contained within them. Using four DUAs, we apply commitment, privilege, and right (CPR) analysis to identify legally compliant requirements. Through this work, we have identified contractual compliance requirements while also identifying compliance problems in relation to DUAs.

Privacy concern is arguably the major barrier that hinders the deployment of electronic health record (EHR) systems which are considered more efficient, less error-prone, and of higher availability compared to traditional paper record systems. Patients are unwilling to accept the EHR system unless their protected health information (PHI) containing highly confidential data is guaranteed proper use and disclosure, which cannot be easily achieved without patients' control over their own PHI. However, cautions must be taken to handle emergencies in which the patient may be physically incompetent to retrieve the controlled PHI for emergency treatment. In this paper, we propose a secure EHR system, HCPP (Healthcaresystem for Patient Privacy), based on cryptographic constructions and existing wireless network infrastructures, to provide privacy protection to patients under any circumstances while enabling timelyPHI retrieval for life-saving treatment in emergency situations. Furthermore, our HCPP system restricts PHI access to authorized (not arbitrary) physicians, who can be traced and held accountable if the accessed PHI is found improperly disclosed. Last but not least, HCPP leverages wireless network access to support efficient and private storage/retrieval of PHI, which underlies a secure and feasible EHR system.

The explosion of medical image usage in clinical and research domains brings us a great challenge of securely handling, storing, retrieving and transmitting biomedical images. Medical images are often large files and they have to be stored for a long time if they are part of a patient’s medical record. As medical images usually contain Protected Health Information (PHI), such data is also subjected to various regulations such as HIPAA. Cost effective measures which provide strong security for such data are essential. Therefore, we present a secure and cost effective distributed file system, JigDFS, for archiving medical images/data.

Electronic health information systems (e.g. health record systems, clinical information systems) can assist in the provision of better health care services for patients and help doctors and other health care workers treat and diagnose patients more effectively and efficiently. One of the most important issues in health-related information systems is high information security and stringent access control for patient's health data to protect the patient's privacy and to prevent the use of data harmfully or illegally. Carrying health records with a patient, for example in a personal digital assistant (PDA) or a mobile phone, could provide greater control of the patient's health data and privacy. It can also facilitate exchanging this health data with health care workers at the point of care and only to the level desired. In this paper, we propose a portable personal electronic health record architecture which natively supports a greater level of privacy using an extended digital certificate- based approach. Other challenges to security accompanying a portable device-based approach are also considered.

Privacy is important in health care delivery. Effective and efficient health care delivery is about exploiting information &#8211, accurate information, complete information. Without privacy, patient trust is diminished, information flow may be compromised and, so too, patient care. When patient care is compromised, inefficiencies emerge and there are verifiable costs to the individual, to the provider and to the health care system as a whole. Privacy, therefore, should be seen as a cornerstone of successful business operations in health care not an afterthought driven by compliance issues.

The Health Insurance Portability and Accountability Act (HIPAA, 1996) requires secure and private treatment of medical information. Congress included the U.S. military healthcare system under HIPAA’s umbrella. However, a combat environment can place unusual constraints on the provision of medical services. This paper develops a model of battlefield medical treatment and evacuation, and then uses the knowledge of experts in a Delphi group to assess the completeness and accuracy of that model, and to recommend improvements to the process. The Delphi group agreed that partial compliance is provided for HIPAA at the beginning of treatment and evacuation, and full compliance is followed later in the process. Recommendations for improving this model were largely administrative, (written guidance, training, and use of cover sheets.) Authorities may want to revisit the issue of the partial compliance to bring law and policy into agreement with practice learned in the crucible of the battlefield.

We describe a case study in which we evaluated an open-source electronic health record (EHR) systempsilas requirements for compliance with the U.S. Health Insurance Portability and Accountability Act (HIPAA). Our findings suggest that legal compliance must be requirements-driven, while establishing due diligence under the law must be test-driven.

Electronic health records (EHR) promise to improve communication between health care providers, thus leading to better quality of patients' treatment and reduced costs. As highly sensitive patient information provides a promising goal for attackers and is also demanded by insurance companies and employers, there is an increasing social and political pressure regarding the prevention of health data misuse. This paper presents a detailed description of the new system PIPE (pseudonymization of information for privacy in e-health) which differs from existing approaches in its ability to securely integrate primary and secondary usage of health data. Therefore, PIPE provides a solution to shortcomings of existing approaches. Our approach may be used as a basis for implementing secure EHR architectures or as an extension to existing systems.

Information privacy typically concerns the confidentiality of personal identifiable information (PII) and protected health information (PHI) such as electronic medical records. Thus, the information access control mechanism for e-health services must be embedded with privacy-enhancing technologies. Role-based access control (RBAC) model has been widely investigated and applied to various applications for a period of time. This paper presents an extended framework of RBAC with privacy-based extensions to tackle such a need. With the context of e-health care informatics, this paper proposes an aggregation decision-making layer interacted with a set of autonomous RBAC models to aggregate PHI.

Information privacy is usually concerned with the confidentiality of protected health information (PHI) such as electronic medical records (EMR). To meet the needs of highly mobile patients in healthcare scenarios, mobile devices such as personal digital assistants (PDAs) are being used for storing entire patient histories and physicals, research data collection forms, the physician's reference desk, current care plans, and drug orders. Thus, the information access control mechanism for mobile ad hoc healthcare applications must be embedded with privacy- enhancing technologies. This paper presents the research issues of developing a privacy access control model for supporting mobile ad hoc healthcare applications. This paper also shows how extensible Access Control Markup Language (XACML) can protect confidential EMR in such a setting.

Medical researchers are legally required to protect patients' privacy by removing personally identifiable information from medical records before sharing the data with other researchers. We present an evaluation of methods for computer-assisted removal and replacement of protected health information (PHI) from free-text nursing notes collected in the intensive care unit as part of the MIMIC II project. A semiautomated method was developed to allow clinicians to highlight PHI on the screen of a tablet PC and to compare and combine the selections of different experts reading the same notes. An analysis of the performance of three human expert de-identifiers and of an automated system is presented. Expert adjudication demonstrated that inter-human variability was high, with few false positives and many false negatives. The sensitivity of human experts working alone ranged from 0.63 to 0.93, with an average of 0.81, and the average positive predictive value was 0.98. An algorithm generated few false negatives but many false positives. Its sensitivity was 0.85, but its positive predictive value was only 0.37. The de-identified database of nursing notes was re-identified with realistic surrogate (but unprotected) dates, serial numbers, names, and phrases to provide a gold standard database of over 2600 notes (approximately 340,000 words) with over 1700 instances of PHI. This reference gold standard database of nursing notes and the Java source code used to evaluate algorithm performance will be made freely available on Physionet in order to facilitate the development and validation of future de-identification algorithms.

As an official rule for healthcare privacy and security, Health Insurance Portability and Accountability Act (HIPAA) requires security services supporting implementation features: Access control; Audit controls; Authorization control; Data authentication; and Entity authentication. Audit controls proposed by HIPPA Security Standards are audit trails, which audit activities, to assess compliance with a secure domain's policies, to detect instances of non-compliant behavior, and to facilitate detection of improper creation, access, modification and deletion of Protected Health Information (PHI). Although current medical imaging systems generate activity logs, there is a lack of regular description to integrate these large volumes of log data into generating HIPPA compliant auditing trails. The paper outlines the design of a HIPAA's compliant auditing system for medical imaging system such as PACS and RIS and discusses the development of this security monitoring system based on the Supplement 95 of the DICOM standard: Audit Trail Messages.

All personally identifiable information must be removed from patient medical records before the data can be shared with other researchers. We present an automated method of removing protected health information (PHI) from free-text nursing notes taken from a U.S. hospital. We have previously shown that one clinician can locate PHI in nursing notes with an average sensitivity of 0.81, and for teams of two clinicians the sensitivity is 0.94. Our method uses lexical look-up tables, regular expressions, and simple heuristics to locate PHI with an overall sensitivity of 0.92 (0.98 for names, 0.96 for dates), which is significantly better than the average sensitivity of a single human. The algorithm has a positive predictive value of only 0.44, so additional software was developed to allow the user to review the terms identified as PHI and manually eliminate false positives. The algorithm is open-source and will be made freely available on PhysioNet together with a re-identified corpus of nursing notes