Securing electronic health records without impeding the flow of information

OBJECTIVE: We present an integrated set of technologies, known as the Hippocratic Database, that enable healthcare enterprises to comply with privacy and security laws without impeding the legitimate management, sharing, and analysis of personal health information. APPROACH: The Hippocratic Database approach to securing electronic health records involves (1) active enforcement of fine-grained data disclosure policies using query modification techniques, (2) efficient auditing of past database access to verify compliance with policies and track security breaches, (3) data mining algorithms that preserve privacy by randomizing information at the individual level, (4) de-identification of personal health data using an optimal method of k-anonymization, and (5) information sharing across autonomous data sources using cryptographic protocols. CONCLUSIONS: Our research confirms that policies concerning the disclosure of electronic health records can be reliably and efficiently enforced and audited at the database level. We further demonstrate that advanced data mining and anonymization techniques can be employed to analyze aggregate health records without revealing individual patient identities. Finally, we show that web services and commutative encryption can be used to share sensitive information selectively among autonomous entities without compromising security or privacy.     

Nursing constraint models for electronic health records: a vision for domain knowledge governance

Various forms of electronic health records (EHRs) are currently being introduced in several countries. Nurses are primary stakeholders and need to ensure that their information and knowledge needs are being met by such systems information sharing between health care providers to enable them to improve the quality and efficiency of health care service delivery for all subjects of care. The latest international EHR standards have adopted the openEHR approach of two-level modelling. The first level is a stable information model determining structure, while the second level consists of constraint models or 'archetypes' that reflect the specifications or clinician rules for how clinical information needs to be represented to enable unambiguous data sharing. The current state of play in terms of international health informatics standards development activities is providing the nursing profession with a unique opportunity and challenge. Much work has been undertaken internationally in the area of nursing terminologies and evidence-based practice. This paper argues that to make the most of these emerging technologies and EHRs we must now concentrate on developing a process to identify, document, implement, manage and govern our nursing domain knowledge as well as contribute to the development of relevant international standards. It is argued that one comprehensive nursing terminology, such as the ICNP or SNOMED CT is simply too complex and too difficult to maintain. As the openEHR archetype approach does not rely heavily on big standardised terminologies, it offers more flexibility during standardisation of clinical concepts and it ensures open, future-proof electronic health records. We conclude that it is highly desirable for the nursing profession to adopt this openEHR approach as a means of documenting and governing the nursing profession's domain knowledge. It is essential for the nursing profession to develop its domain knowledge constraint models (archetypes) collaboratively in an international context.     

Privacy preservation and information security protection for patients’ portable electronic health records

As patients face the possibility of copying and keeping their electronic health records (EHRs) through portable storage media, they will encounter new risks to the protection of their private information. In this study, we propose a method to preserve the privacy and security of patients’ portable medical records in portable storage media to avoid any inappropriate or unintentional disclosure. Following HIPAA guidelines, the method is designed to protect, recover and verify patient's identifiers in portable EHRs. The results of this study show that our methods are effective in ensuring both information security and privacy preservation for patients through portable storage medium.     

Strategies for referent tracking in electronic health records

The goal of referent tracking is to create an ever-growing pool of data relating to the entities existing in concrete spatiotemporal reality. In the context of Electronic Healthcare Records (EHRs) the relevant concrete entities are not only particular patients but also their parts, diseases, therapies, lesions, and so forth, insofar as these are salient to diagnosis and treatment. Within a referent tracking system, all such entities are referred to directly and explicitly, something which cannot be achieved when familiar concept-based systems are used in what is called "clinical coding." In this paper, we describe the components of a referent tracking system in an informal way and we outline the procedures that would have to be followed by healthcare personnel in using such a system. We argue that the referent tracking paradigm can be introduced with only minor--though nevertheless ontologically important--technical changes to existing EHR infrastructures, but that it will require a radically different mindset on the part of those involved in clinical coding and terminology development from that which has prevailed hitherto.     

Aspects of privacy for electronic health records

Patients' medical data have been originally generated and maintained by health professionals in several independent electronic health records (EHRs). Centralized electronic health records accumulate medical data of patients to improve their availability and completeness; EHRs are not tied to a single medical institution anymore. Nowadays enterprises with the capacity and knowledge to maintain this kind of databases offer the services of maintaining EHRs and adding personal health data by the patients. These enterprises get access on the patients' medical data and act as a main point for collecting and disclosing personal data to third parties, e.g. among others doctors, healthcare service providers and drug stores. Existing systems like Microsoft HealthVault and Google Health comply with data protection acts by letting the patients decide on the usage and disclosure of their data. But they fail in satisfying essential requirements to privacy. We propose a privacy-protecting information system for controlled disclosure of personal data to third parties. Firstly, patients should be able to express and enforce obligations regarding a disclosure of health data to third parties. Secondly, an organization providing EHRs should neither be able to gain access to these health data nor establish a profile about patients.     

Secondary use of electronic health records for building cohort studies through top-down information extraction

Controlled clinical trials are usually supported with an in-front data aggregation system, which supports the storage of relevant information according to the trial context within a highly structured environment. In contrast to the documentation of clinical trials, daily routine documentation has many characteristics that influence data quality. One such characteristic is the use of non-standardized text, which is an indispensable part of information representation in clinical information systems. Based on a cohort study we highlight challenges for mining electronic health records targeting free text entry fields within semi-structured data sources. Our prototypical information extraction system achieved an F-measure of 0.91 (precision = 0.90, recall = 0.93) for the training set and an F-measure of 0.90 (precision = 0.89, recall = 0.92) for the test set. We analyze the obtained results in detail and highlight challenges and future directions for the secondary use of routine data in general.     

Comparison of clinical knowledge management capabilities of commercially-available and leading internally-developed electronic health records

Background  

We have carried out an extensive qualitative research program focused on the barriers and facilitators to successful adoption and use of various features of advanced, state-of-the-art electronic health records (EHRs) within large, academic, teaching facilities with long-standing EHR research and development programs. We have recently begun investigating smaller, community hospitals and out-patient clinics that rely on commercially-available EHRs. We sought to assess whether the current generation of commercially-available EHRs are capable of providing the clinical knowledge management features, functions, tools, and techniques required to deliver and maintain the clinical decision support (CDS) interventions required to support the recently defined "meaningful use" criteria.     

Representing patient preference-related concepts for inclusion in electronic health records

In recent years shared decision making between patients and their health care providers and the inclusion of patient preferences in patient care have been, in theory, embraced as models for good clinical practice. Patients' experiences, values, and preferences are increasingly acknowledged as important pieces of evidence for appropriate health care decision making. To effectively use information about patient preferences in patient care, this information, which is gathered through a process of preference elicitation, needs to be integrated with other types of information, e.g., diagnoses, treatments, and patient status indicators within the context of a longitudinal electronic health record. This integration requires that patient preference-related concepts be represented nonambiguously and in a manner that renders them suitable for computer rather than human processing. In this article, the authors describe important patient preference-related concepts and illustrate the use of the LOINC semantic structure as a terminology model to create fully specified names for a sample of 15 preference elicitations from 8 published research articles.     

Stakeholder engagement: a key component of integrating genomic information into electronic health records

Integrating genomic information into clinical care and the electronic health record can facilitate personalized medicine through genetically guided clinical decision support. Stakeholder involvement is critical to the success of these implementation efforts. Prior work on implementation of clinical information systems provides broad guidance to inform effective engagement strategies. We add to this evidence-based recommendations that are specific to issues at the intersection of genomics and the electronic health record. We describe stakeholder engagement strategies employed by the Electronic Medical Records and Genomics Network, a national consortium of US research institutions funded by the National Human Genome Research Institute to develop, disseminate, and apply approaches that combine genomic and electronic health record data. Through select examples drawn from sites of the Electronic Medical Records and Genomics Network, we illustrate a continuum of engagement strategies to inform genomic integration into commercial and homegrown electronic health records across a range of health-care settings. We frame engagement as activities to consult, involve, and partner with key stakeholder groups throughout specific phases of health information technology implementation. Our aim is to provide insights into engagement strategies to guide genomic integration based on our unique network experiences and lessons learned within the broader context of implementation research in biomedical informatics. On the basis of our collective experience, we describe key stakeholder practices, challenges, and considerations for successful genomic integration to support personalized medicine.Genet Med15 10, 792–801.     

Computer-assisted expert case definition in electronic health records

PurposeTo describe how computer-assisted presentation of case data can lead experts to infer machine-implementable rules for case definition in electronic health records. As an illustration the technique has been applied to obtain a definition of acute liver dysfunction (ALD) in persons with inflammatory bowel disease (IBD).MethodsThe technique consists of repeatedly sampling new batches of case candidates from an enriched pool of persons meeting presumed minimal inclusion criteria, classifying the candidates by a machine-implementable candidate rule and by a human expert, and then updating the rule so that it captures new distinctions introduced by the expert. Iteration continues until an update results in an acceptably small number of changes to form a final case definition.ResultsThe technique was applied to structured data and terms derived by natural language processing from text records in 29,336 adults with IBD. Over three rounds the technique led to rules with increasing predictive value, as the experts identified exceptions, and increasing sensitivity, as the experts identified missing inclusion criteria. In the final rule inclusion and exclusion terms were often keyed to an ALD onset date. When compared against clinical review in an independent test round, the derived final case definition had a sensitivity of 92% and a positive predictive value of 79%.ConclusionAn iterative technique of machine-supported expert review can yield a case definition that accommodates available data, incorporates pre-existing medical knowledge, is transparent and is open to continuous improvement. The expert updates to rules may be informative in themselves. In this limited setting, the final case definition for ALD performed better than previous, published attempts using expert definitions.     

Modelling and implementing electronic health records in Denmark

The Danish Health IT strategy [Danish Ministry of Interior and Health, National Strategy for IT in the Health Sector 2003-2007, Copenhagen, 2003 (in Danish). http://www.im.dk/publikationer/itstrategi/itstrategi.pdf. notes that integration between electronic health records (EHR) systems has a high priority. A prerequisite for real integration and semantic interoperability is agreement of the data content and the information models. The National Board of Health is working on a common model for EHR, and its adoption is now being promoted through pilot projects. At the same time, several development and implementation projects are taking place at a regional level. These EHRs are built on information models from different vendors and are based on different integration platforms. The Danish EHR observatory, which has been monitoring the development of EHRs in Denmark since 1998, has analysed the challenges of using different information models and integration platforms. This paper also maps the development in Denmark to the new paradigms in modelling techniques and integration technology.     

Towards stroke prediction using electronic health records

Background

As of 2014, stroke is the fourth leading cause of death in Japan. Predicting a future diagnosis of stroke would better enable proactive forms of healthcare measures to be taken. We aim to predict a diagnosis of stroke within one year of the patient’s last set of exam results or medical diagnoses.

Methods

Around 8000 electronic health records were provided by Tsuyama Jifukai Tsuyama Chuo Hospital in Japan. These records contained non-homogeneous temporal data which were first transformed into a form usable by an algorithm. The transformed data were used as input into several neural network architectures designed to evaluate efficacy of the supplied data and also the networks’ capability at exploiting relationships that could underlie the data. The prevalence of stroke cases resulted in imbalanced class outputs which resulted in trained neural network models being biased towards negative predictions. To address this issue, we designed and incorporated regularization terms into the standard cross-entropy loss function. These terms penalized false positive and false negative predictions. We evaluated the performance of our trained models using Receiver Operating Characteristic.

Results

The best neural network incorporated and combined the different sources of temporal data through a dual-input topology. This network attained area under the Receiver Operating Characteristic curve of 0.669. The custom regularization terms had a positive effect on the training process when compared against the standard cross-entropy loss function.

Conclusions

The techniques we describe in this paper are viable and the developed models form part of the foundation of a national clinical decision support system.

     

Ethical,legal, and social implications of incorporating genomic information into electronic health records

The inclusion of genomic data in the electronic health record raises important ethical, legal, and social issues. In this article, we highlight these challenges and discuss potential solutions. We provide a brief background on the current state of electronic health records in the context of genomic medicine, discuss the importance of equitable access to genome-enabled electronic health records, and consider the potential use of electronic health records for improving genomic literacy in patients and providers. We highlight the importance of privacy, access, and security, and of determining which genomic information is included in the electronic health record. Finally, we discuss the challenges of reporting incidental findings, storing and reinterpreting genomic data, and nondocumentation and duty to warn family members at potential genetic risk.Genet Med15 10, 810–816.     

Learning from heterogeneous temporal data in electronic health records

Electronic health records contain large amounts of longitudinal data that are valuable for biomedical informatics research. The application of machine learning is a promising alternative to manual analysis of such data. However, the complex structure of the data, which includes clinical events that are unevenly distributed over time, poses a challenge for standard learning algorithms. Some approaches to modeling temporal data rely on extracting single values from time series; however, this leads to the loss of potentially valuable sequential information. How to better account for the temporality of clinical data, hence, remains an important research question. In this study, novel representations of temporal data in electronic health records are explored. These representations retain the sequential information, and are directly compatible with standard machine learning algorithms. The explored methods are based on symbolic sequence representations of time series data, which are utilized in a number of different ways. An empirical investigation, using 19 datasets comprising clinical measurements observed over time from a real database of electronic health records, shows that using a distance measure to random subsequences leads to substantial improvements in predictive performance compared to using the original sequences or clustering the sequences. Evidence is moreover provided on the quality of the symbolic sequence representation by comparing it to sequences that are generated using domain knowledge by clinical experts. The proposed method creates representations that better account for the temporality of clinical events, which is often key to prediction tasks in the biomedical domain.     

Publication bias in clinical trials of electronic health records

ObjectiveTo measure the rate of non-publication and assess possible publication bias in clinical trials of electronic health records.MethodsWe searched ClinicalTrials.gov to identify registered clinical trials of electronic health records and searched the biomedical literature and contacted trial investigators to determine whether the results of the trials were published. Publications were judged as positive, negative, or neutral according to the primary outcome.ResultsSeventy-six percent of trials had publications describing trial results; of these, 74% were positive, 21% were neutral, and 4% were negative (harmful). Of unpublished studies for which the investigator responded, 43% were positive, 57% were neutral, and none were negative; the lower rate of positive results was significant (p < 0.001).ConclusionThe rate of non-publication in electronic health record studies is similar to that in other biomedical studies. There appears to be a bias toward publication of positive trials in this domain.     

Defining and measuring completeness of electronic health records for secondary use

We demonstrate the importance of explicit definitions of electronic health record (EHR) data completeness and how different conceptualizations of completeness may impact findings from EHR-derived datasets. This study has important repercussions for researchers and clinicians engaged in the secondary use of EHR data. We describe four prototypical definitions of EHR completeness: documentation, breadth, density, and predictive completeness. Each definition dictates a different approach to the measurement of completeness. These measures were applied to representative data from NewYork–Presbyterian Hospital’s clinical data warehouse. We found that according to any definition, the number of complete records in our clinical database is far lower than the nominal total. The proportion that meets criteria for completeness is heavily dependent on the definition of completeness used, and the different definitions generate different subsets of records. We conclude that the concept of completeness in EHR is contextual. We urge data consumers to be explicit in how they define a complete record and transparent about the limitations of their data.