J. Schmitt, W. Reif, A. Seyfang, S. Miksch
Temporal Dimension of Medical Guidelines: The Semantics of Asbru Time Annotations

Abstract:

"The temporal dimension of observations, actions, and tasks described in clinical guidelines and protocols (CGP) is important and at the same time sometimes vague or complex. Correct understanding of a modelling language of CGPs is basis for a high quality formal model.
In this paper, we describe how the temporal dimension is specified using Asbru time annotation as well as the semantics and some important properties of these time annotations."

   [Paper ]   [Presentation ]

P. Votruba, A. Seyfang, M. Paesold, S. Miksch
Improving the Execution of Clinical Guidelines and Temporal Data Abstraction in High-Frequency Domains

Abstract:

"The execution of clinical guidelines and protocols ... is a challenging task in high-frequency domains such as Intensive Care Units. On the one hand, sophisticated temporal data abstraction is required to match the low-level information from monitoring devices and electronic patient records with the high-level concepts in the CGP. On the other hand, the frequency of the data delivered by monitoring devices mandates a highly efficient implementation of the reasoning engine which handles both data abstraction and execution of the guideline.
...Asbru represent[s] CGPs as a hierarchy of skeletal plans and integrates intelligent temporal data abstraction with plan execution to bridge the gap between measurements and concepts in CGPs.
In this paper, we present our Asbru interpreter, which complies abstraction rules and plans into a network of abstraction modules by the system. This network performs the content of the plans triggered by the arriving patient data. Our approach [has been] evaluated to be efficient enough to handle high-frequency data while coping with complex guidelines and temporal data abstraction."

   [Paper ]   [Presentation ]

M. Balser, J. Schmitt, W. Reif
Verification of Medical Guidelines with KIV

Abstract:

"Medical guidelines are useful to standardize health care. As thousands of patients are treated according to these guidelines, the quality of guidelines is an important issue. In this paper, we present the first tool which directly supports interactive verification of medical guidelines."

   [Paper ]   [Presentation ]

R. Moskovitch, T. Lavie, A. Leibowitz, Y. Denekump, Y. Shahar
A Multiple-Ontology Template-Based Query Interface for a Clinical-Guidelines Search Engine

Abstract:

"A major problem in the effective use of computerized clinical guidelines is fast and accurate access at the point of care. Thus, we developed the Digital electronic Guideline Library (DeGeL) and a set of tools for incremental conversion of free-text guidelines into increasingly machine-comprehensible representations, including a search and retrieval engine. In previous research, we have designed and implemented Vaidurya, a multiple-ontology, concept-based and context-sensitive search and retrieval engine that exploit the hybrid nature of guideline representation in the DeGeL architecture. While Vaidurya offers a wide variety of querying options, which was found effective in improving the retrieval performance, it may be sometimes restricted by the user's limited familiarity with guideline ontologies or her clinical background. We therefore describe the Template-Based Query Interface. A novel approach, which we implemented, enables the user to exploit the ontology-based search capabilities in Vaidurya without being familiar with the details of the underlying ontologies or of the concepts hierqachy used for classification."

   [Paper ]   [Presentation ]

E. Shalom, Y. Shahar, E. Lunenfeld, M. Taieb-Maimon, O. Young, G. Bar, S. Martins, L. Vaszar, Y. Liel, A. Yarkoni, M. Goldstein, A. Leibowitz, T. Marom
The Importance of Creating an Ontology-Specific Consensus Before a Markup-Based Specification of Clinical Guidelines

Abstract:

"We have previously developed the Digital electronic Guideline Library (DeGeL) framework, which includes a methodology for a markup-based, increasingly formal structuring of free-text clinical guidelines (GLs), and tools to support guideline-based application. The methodology includes activities be-fore, during and after the markup process. To reduce the ambiguity of the interpretation of a GL among the Expert Physicians (EPs) who are marking up the GL, and to achieve an interpretation common to the EPs and the knowledge engineers (KEs), an indispensable step before markup is the creation of an Ontology Specific Consensus (OSC) regarding the semantics of the GL. To evaluate the role of the OSC, we created OSCs for three GLs in incremental level of detail, using the Asbru GL ontology. The EPs quantified the subjective aspects that most helped them in creating the OSC, while we assessed the clinical and ontological markup errors committed by the EPs. Using medical knowledge and understanding the GL ontology were considered more helpful than understanding the DeGeL tools; and the more detailed the OSC, the less the number of markup errors committed."

   [Paper ]   [Presentation ]

A. Hatsek, O. Young, E. Shalom, Y. Shahar
Demonstration of DeGeL: A Clinical-Guidelines Library and Automated Guideline- Support Tools

Abstract:

"Using machine-interpretable clinical guidelines to support evidence-based medicine promotes the quality of medical care. In this demonstration, we present the Digital Electronic Guidelines Library (DeGeL), a comprehensive framework, including a Web-based guideline repository and a suite of tools, to support the use of automated guidelines for medical care, research, and quality assessment. Recently, we have developed a new version (DeGeL.NET) of the digital library and of its different tools. We intend to focus in our demonstration on DeGeL's major tools, in particular for guideline specification in Web-based and standalone fashion (Uruz and Gesher), search and retrieval (Vaidurya and DegeLook) and runtime application (Spock), and to explain how they are combined within the typical lifecycle of a clinical guideline."

   [Paper ]   [Presentation ]

P. Terenziani, L. Giordano, A. Bottrighi, S. Montani, L. Donzella
SPIN Model Checking for the Verification of Clinical Guidelines

Abstract:

"In this paper, we propose a new computer-based approach to model clinical guidelines, adopting the agent-based paradigm. We .rst show how clinical guidelines can be modelled in an agent like fashion in the speci.cation language Promela of the model checker SPIN. Then, we describe the impact of such a move: by using SPIN model-checking facilities, one can automatically prove a wide range of properties concerning the modeled guidelines. As a proof of concept, we apply such a methodology to the clinical guidelines in GLARE, a domain-independent prototypical system for acquiring, representing and executing clinical guidelines, which has been built within a 7-year project with Azienda Ospedaliera San Giovanni Battista in Turin (one of the largest hospitals in Italy)."

   [Paper ]   

P. Terenziani, S. Montani, A. Bottrighi, G. Molino, M. Torchio
Applying Artificial Intelligence to Clinical Guidelines: the GLARE Approach

Abstract:

"In this paper, we present GLARE, a domain-independent system for acquiring, representing and executing clinical guidelines. GLARE is characterized by the adoption of Artificial Intelligence (AI) techniques at different levels in the definition and implementation of the system. First of all, a high-level and user-friendly knowledge representation language has been designed, providing a set of representation primitives. Second, a user-friendly acquisition tool has been designed and implemented, on the basis of the knowledge representation formalism. The acquisition tool provides various forms of help for the expert physicians, including different levels of syntactic and semantic tests in order to check 'the well-formedness' of the guidelines being acquired. In particular, extended AI temporal reasoning techniques are used to check the consistency of temporal constraints. Third, a tool for executing guidelines on a specific patient has been made available. The tool relies on an 'agenda' technique, which provides great flexibility, including the possibility of managing repeated and/or concurrent actions. The execution module also provides hypothetical reasoning facilities, to support physicians in the comparison of alternative diagnostic and/or therapeutic strategies. The GLARE approach has been successfully tested on clinical guidelines in different domains such as bladder cancer, reflux esophagitis, heart failure and stroke."

   [Paper ]   

M. Peleg, D. Wang, A. Fodor, S. Keren, E. Karnieli
Adaptation of Practice Guidelines for Clinical Decision Support: A Case Study of Diabetic Foot Care

Abstract:

"Clinical guidelines usually need to be adapted to fit local practice before they can be actually used by clinicians. Reasons for adaptation include variations of institution setting such as type of practice and location, availability of resources, difference of patient populations, local policies, and practice patterns. When a guideline is implemented for clinical decision support and integrated with an institution's clinical information system, the data model of the local electronic medical record (EMR) and the data actually collected and stored in it also influence the guideline's adaptation. The purpose of this work is: (1) to characterize a tool-supported process for guideline encoding that addresses local adaptation and EMR integration, and (2) to identify the types of changes in guideline encoding during the local adaptation process."

   [Paper ]   [Presentation ]

M. Sedlmayr, T. Rose, R. Röhrig, M. Meister
A Workflow Approach towards GLIF Execution

Abstract:

"Medical guidelines for patient treatment furnish a major knowledge resource for any hospital operation. The question arises of how to capture know-how about patient treatment and how ... to offer guidance to physicians in the process of patient care and treatment. In this paper, we ... report on the use of process management concepts for the support of specific medical processes."

   [Paper ]   [Presentation ]

J. Fox, V. Patkar, R. Thomson, E. Black
PROforma guidelines and care pathways: performance in trials and future plans

Abstract:

"PROforma is a language for modelling clinical processes, along with associated tools and methods for creating clinical decision support, care planning, workflow and other applications. Of the applications that have been built using the language some have been evaluated in primary healthcare settings ... and others in specialist care of patients, including breast cancer, leukaemia and management of HIV+ patients. Eight of these trials have included quantitative evaluations on a variety of measures of quality and/or effectiveness of care, and all have shown significant positive effects. This paper provides an overview of these results and previews the CREDO project, which aims to extend the PROforma method from focused decision-support and workflow applications to supporting large, multi-disciplinary care pathways, such as cancer care."

   [Paper ]   

V. Patkar, C. Hurt, R. Steele, A. Purushotham, S. Love, M. Williams, R. Thomson, J. Fox
Impact of a computerised decision support system on compliance with evidence- based guidelines for triple assessment

Abstract:

"Over the past decade, the aim of many western healthcare systems to improve consistency and safety in patient care has prompted considerable investment in the development of evidence-based clinical guidelines. However the effective dissemination of these guidelines in routine clinical care has remained a challenging task and computerised decision support (CDS) systems have been proposed as a means to implement guidelines in practice. This study aimed to evaluate a new CDS system, Triple Assessment Decision Support (TADS), which computerises guidelines for the triple assessment of women referred to specialist breast cancer units. The study aimed first to compare the quality of clinicians’ decisions made with and without decision support and, secondly, to explore the opinions of clinicians regarding the software. A balanced-block crossover experiment with simulated cases was used, together with a questionnaire study. Twenty four practising breast clinicians from England and Wales National Health Service hospitals participated in the study. Clinicians made significantly more deviations from guideline recommendations without the support of TADS (60/120 errors without decision support; 16/120 errors with decision support, P< 0.001). Opinions of participating clinicians towards TADS became more positive after they had used it (P< 0.025). The results of the study suggest that the system can significantly enhance safety and consistency of patient care in breast cancer by promoting compliance with best practice."

   [Paper ]