PSIP: an overview of the results and clinical implications

Adverse Drug Events (ADEs) are injuries due to medication management rather than the underlying condition of the patient. They endanger the patients and most of them could be avoided and prevented. The detection of ADEs usually relies on spontaneous reporting or medical chart reviews. The first objective of the PSIP Project is to automatically detect cases of ADEs by means of Data Mining, and to provide these cases to healthcare professionals. The second objective is to prevent ADEs by means of contextualised Clinical Decision Support Systems (Cx-CDSS) connected with Computerised Physician Order Entry (CPOE) or Electronic Health Record (EHR) systems. The detection of ADEs has been made possible through a set of rules able to identify relevant cases is a set of 92,000 medical cases. The results of this detection are provided through "ADE Scorecards". Contextualized Decision Support Systems have been developed by using the same set of rules and implemented in different software environments. The initial objectives of the PSIP project have been reached. The evaluation of the clinical impact has to be completed.

Four principles for user interface design of computerised clinical decision support systems

The paper presents results from a design research project of a user interface (UI) for a Computerised Clinical Decision Support System (CDSS). The ambition has been to design Human-Computer Interaction (HCI) that can minimise medication errors. Through an iterative design process a digital prototype for prescription of medicine has been developed. This paper presents results from the formative evaluation of the prototype conducted in a simulation laboratory with ten participating physicians. Data from the simulation is analysed by use of theory on how users perceive information. The conclusion is a model, which sum up four principles of interaction for design of CDSS. The four principles for design of user interfaces for CDSS are summarised as four A's: All in one, At a glance, At hand and Attention. The model emphasises integration of all four interaction principles in the design of user interfaces for CDSS, i.e. the model is an integrated model which we suggest as a guide for interaction design when working with preventing medication errors.

Human factors based recommendations for the design of medication related clinical decision support systems (CDSS)

This study is part of a research project aiming at developing advanced functions of medication related CDSS to support the monitoring of patients' therapeutic treatments based mainly on corresponding lab values. We adopted a user-centred approach to the design of these advanced CDSS functions. We collected existing recommendations in the literature and completed previous Human Factors (HF) field studies and analyses by focused observations and modeling. We present resulting HF based recommendations for the design of such advanced medication CDSS and focus more specifically on two innovative high level recommendations completing those already existing in the literature. For illustration purposes, an example of the operationalization of one of the recommendation is presented.

Lessons learnt from conducting a high fidelity simulation test in health IT

Testing IT-systems by use of simulation requires a thorough planning and preparation in order to create a realistic clinical environment. For a successful test through simulation a dedicated test team to control the environment is needed, as well as people to play the role of patients and staff. Relevant artifacts and elaborate scenarios ensure the narrative. This paper explores the preliminary work and execution of an extensive test of a Computerized Order Entry System prototype. Central to the setup of the test is a script which outlines the method by guiding the preparation and execution.

Accelerating patient safety through the innovative use of information technology

Numerous studies have confirmed that the patient safety challenge remains tangible. Innovative use of healthcare IT (Information Technology) could play a part in the solution, if the costs of development and implementation are weighed against the major potential savings by improving quality and safety. It is suggested through the "Safe Seven"-checklist, that the design of supporting eHealth solutions lends principles from the patient safety and physical design domains.

Impact evaluation of innovative technology: estimating the impact of the PSIP solutions

Health informatics projects often develop innovative IT solutions for health care. Systematic evaluation of their impact and risks is an ethical imperative. However, field studies can often not be conducted because of immature solutions. On the other site, lab studies are not helpful when it comes to estimating the impact of an innovative IT solution. We faced this challenge within the PSIP projects where innovative tools for medication management are developed. In this paper, we present the approaches used within the PSIP project for estimating the impact of immature solutions, including surveys of future users, a Delphi study with experts, and a simulation study. The methodology and first results of those evaluations are presented, and lessons learnt for impact evaluation of immature solutions are discussed.

Designing, implementing and evaluating e-prescription: a field study and comparison with PSIP results

E-prescription is amongst the most widespread medical electronic support functions. However, several studies reported acceptance and utilisation rates not as high as expected. This paper performs firstly an analysis of the literature on e-prescription characteristics and functionalities especially with respect to their actual usage. Then a specific field study was conducted in an Internal Medicine ward, to investigate human factor issues associated to the introduction of an e-prescription system. Finally, the findings of the field study are framed within the actual implementation of various electronic support outputs resulting from the European Project "Patient safety through intelligent procedures in medication" (PSIP). The results show the importance of a systemic view when designing, implementing and evaluating medical support systems, as the pre-existing structures and tools largely influence the impact of those systems and their effects.

Improvement of inter-services communication through a CDSS dedicated to myocardial perfusion scintigraphy

This study addresses the question of communication between medical wards and the nuclear medicine department for the realization of myocardial perfusion scintigraphy. It analyses the effects of a reminder for completing the content of an order form. It shows that the CDSS impacted ordering practices. It could be seen as a system enabling to structure the information and improve the quality of orders.

Validation of completeness, correctness, relevance and understandability of the PSIP CDSS for medication safety

Medication errors and resulting Adverse Drug Events (ADEs) are an important issue of global healthcare. Within the European PSIP project that aims at developing solutions to improve medication safety, contextualized decision support modules aiming to prevent ADEs are being developed. The objective of this work was to thoroughly validate part of the CDSS (Clinical Decision Support System) and the underlying Knowledge Base, in order to detect incorrect or unclear alerts. We systematically developed a repository of test cases and used them for validation. The development of the test cases showed that there are differences among experts in interpreting the correctness of an alert, and that the clinical context is important when judging whether it is adequate. Overall, validation did not find major errors in the Knoweldge Base, but developed several recommendations for further improvement.

A methodology and supply chain management inspired reference ontology for modeling healthcare teams

Numerous studies and strategic plans are advocating more team based healthcare delivery that is facilitated by information and communication technologies (ICTs). However before we can design ICTs to support teams we need a solid conceptual model of team processes and a methodology for using such a model in healthcare settings. This paper draws upon success in the supply chain management domain to develop a reference ontology of healthcare teams and a methodology for modeling teams to instantiate the ontology in specific settings. This research can help us understand how teams function and how we can design ICTs to support teams.

Architecture of a decision support system to improve clinicians' interpretation of abnormal liver function tests

The objective of this work was to create a self-working computerized clinical decision support system (CDSS) able to analyze liver function tests (LFTs) in order to provide diagnostic suggestions and helpful care support to clinicians. We developed an expert system that processes exclusively para-clinical information to provide diagnostic propositions. Drugs are a major issue in dealing with abnormal LFTs, therefore we created a drug-disease causality assessment tool to include drugs in the differential diagnosis. Along with the results, the CDSS will guide clinicians in the care process offering them case-specific support in the form of guidelines, order sets and references to recent articles. The CDSS will be implemented in Geneva University Hospitals clinical information system (CIS) during year 2011. For the time being, preliminary tests have been conducted on case reports chosen randomly on Pubmed. Considered as medical challenges, case reports were nevertheless processed correctly by the program to the extent that 18 cases out of 20 were diagnosed accurately.

Implementation of a taxonomy aiming to support the design of a contextualised clinical decision support system

Clinical Decision Support Systems (CDSS) are recently implemented in hospital settings to improve the reliability of drug ordering. However, such systems have limited effects due to their tendency to overalert. To healthcare professionals consider alerts, it is necessary to adapt the CDSS to their activity. Thus, it is necessary to consider contextualisation aspects in the system design. In this article, we propose a taxonomy integrating contextualisation elements issued from an activity analysis to guide the design of a contextualised CDSS. This taxonomy has been developed within the framework of the European project PSIP (Patient Safety through Intelligent Procedures in medication) aiming to make easier the identification and the prevention of Adverse Drug Events.

3,520 medication errors evaluated to assess the potential for IT-based decision support

We have previously studied system failures involved in medication errors using a limited number of root cause analyses as source. The aim of this study was to describe a larger number of medication errors with respect to harm, involved medicines and involved system problems - thus providing information for the development of IT-based decision support. We evaluated 3,520 medication error reports derived from 12 months of consecutive reporting from 13 hospitals in the Capital Region of Denmark. We found 0.65% errors with serious harm and 16% with moderate harm. A small number of medicines were involved in the majority of the errors. The problems in the medication error process were heterogeneous. Some were related to specific medicines and others were related to the computerized order entry system. Accordingly decision support targeted at specific medicines and improved IT systems are part of the continuing work to reduce the frequency of medication errors.

Towards a standardised representation of a knowledge base for adverse drug event prevention

Knowledge representation is an important part of knowledge engineering activities that is crucial for enabling knowledge sharing and reuse. In this regard, standardised formalisms and technologies play a significant role. Especially for the medical domain, where knowledge may be tacit, not articulated and highly diverse, the development and adoption of standardised knowledge representations is highly challenging and of outmost importance to achieve knowledge interoperability. To this end, this paper presents a research effort towards the standardised representation of a Knowledge Base (KB) encapsulating rule-based signals and procedures for Adverse Drug Event (ADE) prevention. The KB constitutes an integral part of Clinical Decision Support Systems (CDSSs) to be used at the point of care. The paper highlights the requirements at the domain of discourse with respect to knowledge representation, according to which GELLO (an HL7 and ANSI standard) has been adopted. Results of our prototype implementation are presented along with the advantages and the limitations introduced by the employed approach.

Drug knowledge expressed as computable semantic triples

The majority of questions that arise in the practice of medicine relate to drug information. Additionally, adverse reactions account for as many as 98,000 deaths per year in the United States. Adverse drug reactions account for a significant portion of those errors. Many authors believe that clinical decision support associated with computerized physician order entry has the potential to decrease this adverse drug event rate. This decision support requires knowledge to drive the process. One important and rich source of drug knowledge is the DailyMed product labels. In this project we used computationally extracted SNOMED CT™ codified data associated with each section of each product label as input to a rules engine that created computable assertional knowledge in the form of semantic triples. These are expressed in the form of "Drug" HasIndication "SNOMED CT™". The information density of drug labels is deep, broad and quite substantial. By providing a computable form of this information content from drug labels we make these important axioms (facts) more accessible to computer programs designed to support improved care.

Electronic medical record information system for patient consultations in Chinese medicine

Currently there are no widely used systems to electronically record individual patient consultations with Traditional Chinese Medicine (TCM) practitioners. As TCM practice differs significantly from western medicine both in diagnosis and treatment, using information systems created for western medicine is not suitable. There is a need for information systems developed specifically for TCM practitioners to manage patient consultation and treatments. Such system should be designed to facilitate safe and effective practice by providing decision support, utilising existing knowledge such as known herb-drug interactions to signal safety risks. Utilising current and developing standards and vocabularies such as those developed by the World Health Organisation (WHO) is important to facilitate interoperability with other systems. To facilitate continued growth in consumer demand, this type of system should be compatible with the needs of the individual electronic health records and other medical systems, and provide interfaces to external systems such as Medicare, pathology and radiology systems, and insurance systems. This paper presents the high level design of a patient consultation system for TCM practitioners that addresses the individual practitioner's needs for health records entry, storage, retrieval, display and support in managing health care delivery to patients and be part of Australia's emerging e-health system.

Decision support: time for collaboration

OBJECTIVES

To summarize current outstanding research in the field of decision support.

METHODS

A selection of excellent research articles published in 2010 in the field of computerized clinical decision support systems.

RESULTS AND CONCLUSIONS

This selection of articles shows that decision support systems (DSS) are getting better integrated into the electronic health record systems (EHR) and into the clinician's workflow. As a result, there is a better collaboration between physicians and DSS, which improves the care of patients.

Creating knowledge archive in the internet medical consultant for decision support at the point of care

The Internet Medical Consultant - IMC is a knowledge sharing system for physicians. The system's main purpose is to collect and store the communication between its users and to provide easy retrieval of stored information. The system provides access to human generated knowledge at the point of care. Having that kind of knowledge at hand can be very helpful for physicians when they make decisions. This paper describes the process of knowledge capturing, creating and searching the knowledge archive, for final utilisation of that knowledge at point of care.

Three different cases of exploiting decision support services for adverse drug event prevention

Clinical Decision Support Systems (CDSSs) are implemented in clinical settings in order to improve patient outcomes and/or clinical practices. However, they are still not widely accepted by healthcare professionals due to over-alerting. The aim of the "Patient Safety through Intelligent Procedures in medication" (PSIP) project is to develop and demonstrate innovative tools so as to generate and provide relevant knowledge to healthcare professionals and patients for Adverse Drug Event (ADE) prevention by means of Information and Communication Technologies (ICT). PSIP employs a Knowledge Base (KB) as the core of its CDSS. This KB encapsulates signals capable of automatically detecting potential ADEs and contextualizing the CDSS output to the patient and healthcare professionals. To exploit the KB, a Global Knowledge Platform (GKP) has been created comprising of a KB system, a Connectivity Platform and appropriate user interface modules. The GKP has been tested to demonstrate integration of the KB in different work situations and it has been deployed in three different medical applications. The first is a Web application; the second involves a commercial French EHR (Electronic Health Record) and the third is a Danish CPOE (Computerised Physician Order Entry) system. This paper presents recent progress as regards the exploitation of the PSIP KB and the results obtained in the three different medical applications.

Mental health promotion system

Mental activity promotion system is presented that analyzes, quantifies, trains and prescribes based on analysis of logical, memorizing, concentrative, decisive, in conditions where time and space is involved, possibility of dementia, and on evaluation of lifestyle of subjects. Special consideration has been made to make the system motivational, persuasive, attractive and fun to use. The system has been successfully deployed in Bitgeoul Senior health town, Gwangju, South Korea.

Information contextualization in decision support modules for adverse drug event prevention

This paper presents an analysis of hospitals' organization and Hospital Information Systems' features which can contribute in contextualization of Clinical Decision Support Systems (CDSS) for Adverse Drug Event (ADE) prevention. We identified four categories of contextualization: ENVIRONMENT, TASKS, USERS and TEMPORAL ASPECTS. Based on this analysis, we studied the technical possibilities at the architectural level to determine which component(s) of a standalone knowledge platform could technically handle contextualization. The results impact three types of components of this platform: (1) a CDSS providing decision support based on ADE signals mined in large data repositories; (2) a Connectivity Platform providing transformation and routing services (enabling any application to connect to the CDSS); (3) three prototype applications for accessing the decision support services realized within an industrial Computerized Physician Order Entry, an industrial Electronic Health Record and in an independent Web prototype, respectively. In each of the above components we present the dimension(s) of contextualization that has/have been determined to cope with and the design followed in the implementation phase.

Dynamic composition of medical support services in the ICU: Platform and algorithm design details

The Intensive Care Unit (ICU) is an extremely data-intensive environment where each patient needs to be monitored 24/7. Bedside monitors continuously register vital patient values (such as serum creatinine, systolic blood pressure) which are recorded frequently in the hospital database (e.g. every 2 min in the ICU of the Ghent University Hospital), laboratories generate hundreds of results of blood and urine samples, and nurses measure blood pressure and temperature up to 4 times an hour. The processing of such large amount of data requires an automated system to support the physicians' daily work. The Intensive Care Service Platform (ICSP) offers the needed support through the development of medical support services for processing and monitoring patients' data. With an increased deployment of these medical support services, reusing existing services as building blocks to create new services offers flexibility to the developer and accelerates the design process. This paper presents a new addition to the ICSP, the Dynamic Composer for Web services. Based on a semantic description of the medical support services, this Composer enables a service to be executed by creating a composition of medical services that provide the needed calculations. The composition is achieved using various algorithms satisfying certain quality of service (QoS) constraints and requirements. In addition to the automatic composition the paper also proposes a recovery mechanism in case of unavailable services. When executing the composition of medical services, unavailable services are dynamically replaced by equivalent services or a new composition achieving the same result. The presented platform and QoS algorithms are put through extensive performance and scalability tests for typical ICU scenarios, in which basic medical services are composed to a complex patient monitoring service.

Distributed guidelines (DiG): a software framework for extending automated health decision support to the general population

This article presents a framework and methodology to create personal health record (PHR) systems able to transform raw health data into meaningful information for the general population. By bridging the semantic gap between an individual and his or her health data, it is expected that better care will ensue through consumer empowerment. An important challenge for the realization of this vision is the lack of available expert knowledge in a format that is concomitantly easy to codify, share, and be used by the general population. To address this challenge, we developed a novel approach to encode expert knowledge into machine-interpretable, reusable components called "consumer guidelines." Once encoded, guidelines are easily shared, extended, and modified. These guidelines can exist as distributed documents on the Internet and be executed by our processing engine (Health-Guru) to provide an individual with personalized assessment against various health risks based on the evidence data stored in a PHR.