Electronic health records: new opportunities for clinical research.

Clinical research is on the threshold of a new era in which electronic health records (EHRs) are gaining an important novel supporting role. Whilst EHRs used for routine clinical care have some limitations at present, as discussed in this review, new improved systems and emerging research infrastructures are being developed to ensure that EHRs can be used for secondary purposes such as clinical research, including the design and execution of clinical trials for new medicines. EHR systems should be able to exchange information through the use of recently published international standards for their interoperability and clinically validated information structures (such as archetypes and international health terminologies), to ensure consistent and more complete recording and sharing of data for various patient groups. Such systems will counteract the obstacles of differing clinical languages and styles of documentation as well as the recognized incompleteness of routine records. Here, we discuss some of the legal and ethical concerns of clinical research data reuse and technical security measures that can enable such research while protecting privacy. In the emerging research landscape, cooperation infrastructures are being built where research projects can utilize the availability of patient data from federated EHR systems from many different sites, as well as in international multilingual settings. Amongst several initiatives described, the EHR4CR project offers a promising method for clinical research. One of the first achievements of this project was the development of a protocol feasibility prototype which is used for finding patients eligible for clinical trials from multiple sources.

Electronic medical file exchange between on-duty care providers and the attending paediatrician: a Belgian paediatric pilot project.

The authors propose the introduction of a pilot project: "paediatric core file exchange in emergencies" (PCF-EXEM) which enables the exchange of medical data between the attending paediatrician (AP), holder of the medical record, and on-duty medical units (i.e. general practitioners, paediatricians, surgeons, emergency physicians,...). This project is based on two pillars: a protected server (PCF-server) containing paediatric core files (PCF), with important clinical data that should be available for the physician in order to quickly get a clear insight into the relevant clinical medical history of the child, and secondly, the possibility to provide feedback to the attending physician about the findings recorded during the on-call duty. The permanent availability of health data on the PCF-server and the possibility to provide feedback represent together the PCF-EXEM-project. This project meets the demand of the care providers to have relevant medical information permanently available in order to guarantee high quality care in emergency situations. The frail balance between the right to informative privacy and professional confidentiality on the one hand and the right to quality health care on the other hand has been taken into account. The technical and practical feasibility of this project is described. The objectives and vision of the PCF-EXEM project are conform to Belgian legislation concerning the processing of medical data and are in line with the still under consideration European projects which are focusing on interoperability and the development of a common access control to databanks containing health data for care providers. PCF-EXEM could therefore be a model for other EU countries as well.

A novel time series analysis approach for prediction of dialysis in critically ill patients using echo-state networks.

BACKGROUND: Echo-state networks (ESN) are part of a group of reservoir computing methods and are basically a form of recurrent artificial neural networks (ANN). These methods can perform classification tasks on time series data. The recurrent ANN of an echo-state network has an 'echo-state' characteristic. This 'echo-state' functions as a fading memory: samples that have been introduced into the network in a further past, are faded away. The echo-state approach for the training of recurrent neural networks was first described by Jaeger H. et al. In clinical medicine, until this moment, no original research articles have been published to examine the use of echo-state networks. METHODS: This study examines the possibility of using an echo-state network for prediction of dialysis in the ICU. Therefore, diuresis values and creatinine levels of the first three days after ICU admission were collected from 830 patients admitted to the intensive care unit (ICU) between May 31 th 2003 and November 17th 2007. The outcome parameter was the performance by the echo-state network in predicting the need for dialysis between day 5 and day 10 of ICU admission. Patients with an ICU length of stay <10 days or patients that received dialysis in the first five days of ICU admission were excluded. Performance by the echo-state network was then compared by means of the area under the receiver operating characteristic curve (AUC) with results obtained by two other time series analysis methods by means of a support vector machine (SVM) and a naive Bayes algorithm (NB). RESULTS: The AUC's in the three developed echo-state networks were 0.822, 0.818, and 0.817. These results were comparable to the results obtained by the SVM and the NB algorithm. CONCLUSIONS: This proof of concept study is the first to evaluate the performance of echo-state networks in an ICU environment. This echo-state network predicted the need for dialysis in ICU patients. The AUC's of the echo-state networks were good and comparable to the performance of other classification algorithms. Moreover, the echo-state network was more easily configured than other time series modeling technologies.

[Framework for responsible venous access and IV management]. / Allen op één lijn ? Kaders voor verantwoorde veneuze toegang en infuusmanagement.

Intravascular catheters are indispensable in current healthcare. The introduction of a peripheral venous or central venous catheter and managing infusion therapy are care processes that over time have become integral to the organisation, and in which multiple care providers play a role. Introducing an IV appears to be a straightforward repetitive task, but often proves to be a considerable burden to the patient and a source of dissatisfaction, morbidity and mortality. Inadequate decision-making, inexperience and lack of a guideline can lead to poor IV management. There is a need for improvement in many care facilities. A programmatic approach such as the Vessel Health and Preservation Principle can be a great asset in this. In this article we outline the framework for responsible vascular access and infusion therapy.

Privacy Protection through pseudonymisation in eHealth.

The ISO TC215 WG4 pseudonymisation task group has produced in 2008 a first version of a technical specification for the application of pseudonymisation in Healthcare Informatics 0. This paper investigates the principles set out in the technical specification as well as its implications in eHealth. The technical specification starts out with a conceptual model and evolves from a theoretical model to a real life model by adding assumptions on the observability of personal data.

The use of a compliant EHR when providing clinical pathway driven care to a subset of diabetic patients: recommendation from a Working Group.

The Belgian National Health Insurance Institute (NHII) and other Healthcare Authorities intend to improve the quality of care through promoting clinical pathway driven care and by optimising cooperation between the responsible primary care physician and the diabetologist. Patients and healthcare professionals are granted some (financial) benefits when meeting the conditions defined in a mutual agreement.This article describes the conditions and the functional requirements to be met by an EHR to enable and to maximise the benefits of a clinical pathway driven patient care to a specific group of diabetic type 2 patients, based on a mandate issued by the NHII.The generic and specific functional requirements are then translated in test criteria for certification and prioritised in an implementation plan.

Design of a flexible platform for execution of medical decision support agents in the intensive care unit.

This paper addresses the design of a generic and scalable platform for the execution of medical decision support agents in the intensive care unit (ICU). As will be motivated, medical decision support agents can impose high computational load and in practical setups a large amount of such agents are typically running in parallel. Future ICU systems will rely on extensive medical decision support. However, in current systems only one workstation is typically dedicated for the execution of medical decision support agents. Therefore, we propose an architecture based on middleware technology to allow for easy distribution of the agents along multiple workstations. The architecture allows for easy integration with a general ICU data flow management architecture.

The European Institute for Innovation through Health Data.

The European Institute for Innovation through Health Data (i~HD, www.i-hd.eu) has been formed as one of the key sustainable entities arising from the Electronic Health Records for Clinical Research (IMI-JU-115189) and SemanticHealthNet (FP7-288408) projects, in collaboration with several other European projects and initiatives supported by the European Commission. i~HD is a European not-for-profit body, registered in Belgium through Royal Assent. i~HD has been established to tackle areas of challenge in the successful scaling up of innovations that critically rely on high-quality and interoperable health data. It will specifically address obstacles and opportunities to using health data by collating, developing, and promoting best practices in information governance and in semantic interoperability. It will help to sustain and propagate the results of health information and communication technology (ICT) research that enables better use of health data, assessing and optimizing their novel value wherever possible. i~HD has been formed after wide consultation and engagement of many stakeholders to develop methods, solutions, and services that can help to maximize the value obtained by all stakeholders from health data. It will support innovations in health maintenance, health care delivery, and knowledge discovery while ensuring compliance with all legal prerequisites, especially regarding the insurance of patient's privacy protection. It is bringing multiple stakeholder groups together so as to ensure that future solutions serve their collective needs and can be readily adopted affordably and at scale.

Privacy protection for HealthGrid applications.

OBJECTIVES: This contribution aims at introducing the problem of privacy protection in e-Health and at describing a number of existing privacy enhancing techniques (PETs). The recognition that privacy constitutes a fundamental right is gradually entering public awareness. Because healthcare-related data are susceptible to being abused for many obvious reasons, public apprehension about privacy has focused on medical data. Public authorities have become convinced of the need to enforce privacy protection and make considerable efforts for promoting through privacy protection legislation the deployment of PETs. METHODS: Based on the study of the specific features of Grid technology, ways in which PET services could be integrated in the HealthGrid are being analyzed. Grid technology aims at removing barriers between local and remote resources. The privacy and legal issues raised by the HealthGrid are caused by the transparent interchange and processing of sensitive medical information. PET technology has already proven its usefulness for privacy protection in health-related marketing and research data collection. RESULTS: While this paper does not describe market-ready solutions for privacy protection in the HealthGrid, it puts forward several cases in which the Grid may benefit from PETs. CONCLUSION: Early integration of privacy protection services into the HealthGrid can lead to a synergy that is beneficial for the development of the HealthGrid itself.

The Healthgrid White Paper.

Over the last four years, a community of researchers working on Grid and High Performance Computing technologies started discussing the barriers and opportunities that grid technologies must face and exploit for the development of health-related applications. This interest lead to the first Healthgrid conference, held in Lyon, France, on January 16th-17th, 2003, with the focus of creating increased awareness about the possibilities and advantages linked to the deployment of grid technologies in health, ultimately targeting the creation of a European/international grid infrastructure for health. The topics of this conference converged with the position of the eHealth division of the European Commission, whose mandate from the Lisbon Meeting was "To develop an intelligent environment that enables ubiquitous management of citizens' health status, and to assist health professionals in coping with some major challenges, risk management and the integration into clinical practice of advances in health knowledge." In this context "Health" involves not only clinical procedures but covers the whole range of information from molecular level (genetic and proteomic information) over cells and tissues, to the individual and finally the population level (social healthcare). Grid technology offers the opportunity to create a common working backbone for all different members of this large "health family" and will hopefully lead to an increased awareness and interoperability among disciplines. The first HealthGrid conference led to the creation of the Healthgrid association, a non-profit research association legally incorporated in France but formed from the broad community of European researchers and institutions sharing expertise in health grids. After the second Healthgrid conference, held in Clermont-Ferrand on January 29th-30th, 2004, the need for a "white paper" on the current status and prospective of health grids was raised. Over fifty experts from different areas of grid technologies, eHealth applications and the medical world were invited to contribute to the preparation of this document.

Development of the Logical Observation Identifier Names and Codes (LOINC) vocabulary.

The LOINC (Logical Observation Identifier Names and Codes) vocabulary is a set of more than 10,000 names and codes developed for use as observation identifiers in standardized messages exchanged between clinical computer systems. The goal of the study was to create universal names and codes for clinical observations that could be used by all clinical information systems. The LOINC names are structured to facilitate rapid matching, either automated or manual, between local vocabularies and the universal LOINC codes. If LOINC codes are used in clinical messages, each system participating in data exchange needs to match its local vocabulary to the standard vocabulary only once. This will reduce both the time and cost of implementing standardized interfaces. The history of the development of the LOINC vocabulary and the methodology used in its creation are described.

External quality assessment (EQA) of Belgian clinical laboratories. The telematics paradigm.

Technology that enables communication between information systems has recently become cheaper and more powerful. It is therefore timely to consider the effects of the introduction of such techniques in external quality assessment (EQA) schemes on both users and organizers. Traditionally, results are returned to EQA organizers as hand-written numbers on structured forms. These data are then manually entered into a computer. The process is time-consuming, slow (as it depends on the postal service), prone to error at every transcription stage, and expensive, as clerical staff must be employed to input the data. Computer-to-computer communication allows this process to be improved. A telematics system for electronic data interchange has been developed for the Belgian EQA programme and it offers several advantages, such as the use of standardized semantics, expression of results in laboratory familiar units, possible interface with the Laboratory Information System, faster data analysis, shorter report time and long-term performance evaluation.

The explanatory role of events in causal and temporal reasoning in medicine.

The logic of time and the way we reason about time is intrinsically connected with the way we reason about causality. In this paper, we focus our attention on some of the less obvious ways in which reasoning about time and causality interact. It is explained why in temporal reasoning a firm distinction has to be made between the ontology, i.e., what happens, and the way we describe the ontology. Temporal events need to be redescribed in such a way that they causally explain why some of the events are followed by the others. While building a temporal/causal theory, certain events may be omitted, not because they do not play a causal role, but because they do not play an explanatory role. In doing so, it is possible to eliminate the distinction between theories representing time as dense, and theories that represent time as discrete.

Privacy enhancing techniques - the key to secure communication and management of clinical and genomic data.

OBJECTIVES: To introduce some of the privacy protection problems related to genomics based medicine and to highlight the relevance of Trusted Third Parties (TTPs) and of Privacy Enhancing Techniques (PETs) in the restricted context of clinical research and statistics. METHODS: Practical approaches based on two different pseudonymisation models, both for batch and interactive data collection and exchange, are described and analysed. RESULTS AND CONCLUSIONS: The growing need of managing both clinical and genetic data raises important legal and ethical challenges. Protecting human rights in the realm of privacy, while optimising research potential and other statistical activities is a challenge that can easily be overcome with the assistance of a trust service provider offering advanced privacy enabling/enhancing solutions. As such, the use of pseudonymisation and other innovative Privacy Enhancing Techniques can unlock valuable data sources.

The distinction between linguistic and conceptual semantics in medical terminology and its implication for NLP-based knowledge acquisition.

Natural language understanding systems have to exploit various kinds of knowledge in order to represent the meaning behind texts. Getting this knowledge in place is often such a huge enterprise that it is tempting to look for systems that can discover such knowledge automatically. We describe how the distinction between conceptual and linguistic semantics may assist in reaching this objective, provided that distinguishing between them is not done too rigorously. We present several examples to support this view and argue that in a multilingual environment, linguistic ontologies should be designed as interfaces between domain conceptualizations and linguistic knowledge bases.

On the design of a generic and scalable multilayer software architecture for data flow management in the intensive care unit.

OBJECTIVES: The current Intensive Care Information Systems (IC-ISs) collect and store monitoring data in on automated way and can replace all paper forms by an electronic equivalent, resulting in a paperless ICU. Future development of IC-ISs will now have to focus on bedside clinical decision support. The current IC-ISs are data-driven systems, with a two-layer software architecture. This software architecture is hardly maintainable and probably not the most optimal architecture to make the transition towards future systems with-decision support. The aim of this research was to address the design of an alternative software architecture based on new paradigms. METHODS: State-of-the art component, middleware and agent technology were deployed to design and implement a software architecture for ICU data flow management. RESULTS: An advanced multi-layer architecture for efficient data flow management in the ICU has been designed. The architecture is both generic and scalable, which means that it neither depends on a particular ICU nor on the deployed monitoring devices. Automatic device detection and Graphical User Interface generation are taken into account. Furthermore, a demonstrator has been developed as a proof that the proposed conceptual software architecture is feasible in practice. The core of the new architecture consists of Bed Decision Agents (BDAs). The introduction of BDAs, who perform specific dedicated tasks, improves the adaptability and maintainability of the future very complex IC-ISs. CONCLUSIONS: A software architecture, based on component, middleware and agent technology, is feasible and offers important advantages over the currently used two-layer software architecture.

A Dutch medical language processor: part II: evaluation.

This paper provides a preliminary evaluation of a general Dutch medical language processor (DMLP). Four examples of different potential applications (based on different linguistic modules) are presented, each with its own evaluation method. Finally, a critical review of the used evaluation methods is offered according to the state of the art in medical language processing.

From syntactic-semantic tagging to knowledge discovery in medical texts.

In the GALEN project, the syntactic-semantic tagger MultiTALE is upgraded to extract knowledge from natural language surgical procedure expressions. In this paper, we describe the methodology applied and show that out of a randomly selected sample of such expressions coming from the procedure axis of Snomed International, 81% could be analysed correctly. The problems encountered fall in three different categories: unusual grammatical configurations within the Snomed terms, insufficient domain knowledge and different categorisation of concepts and semantic links in the domain and linguistic models used. It is concluded that the Multi-TALE system can be used to attach meaning to words that not have been encountered previously, but that an interface ontology mediating between domain models and linguistic models is needed to arrive at a higher level of independence from both particular languages and from particular domains.

Determination of user requirements for the secure communication of electronic medical record information.

Health professionals need to have accurate patient data in order to make the right diagnosis and to give an optimal treatment. In many cases, the 'medical' record, whether in electronic form or paper form is distributed over several health care providers and health care enterprises. Technically, there are several ways to provide access to remote record information or parts thereof. Legislation however puts restrictions on the communication of personal information in order to protect the privacy of the patient. This paper gives an overview of requirements and constraints when communicating electronic medical record information and summarises the findings of the SEMRIC project in determining requirements from a number of practical cases.