|
|
Methods and tools for the development of computer-interpretable guidelines
|
|
|
Asbru
|
|
Asbru
is a task-specific and intention-based plan representation language
to embody clinical guidelines and protocols as time-oriented skeletal
plans. Skeletal plans provide a powerful way to reuse existing
domain-specific procedural knowledge, while leaving room for execution-time
flexibility to achieve particular goals. |
|
|
The Asbru plan and
guideline language and associated technologies have been developed
by the Asgaard/Asbru
project. Asgaard was the home and
citadel of the gods in Norse mythology, corresponding to Mount
Olympus in Greek mythology. It was located in the heavens and
was accessible only over the rainbow bridge, called Asbru (or
Bifrost).
|
|
| keywords |
Knowledge representation, knowledge acquisition, computer-interpretable guidelines, task-specific, intention-based, skeletal plans,
representing, reasoning with,
visualizing time-oriented patient data
|
| developed by |
The Asgaard project led by the Vienna University of Technology and
Stanford Medical Informatics.
|
| introduced |
1998
|
| status |
Under evaluation / in use / under continued development (including
development and support tools).
|
| support |
|
| in use |
Prototype applications in diabetes, jaundice and breast cancer.
|
| tools |
Associated downloadable prototype software tools include:
|
|
| description |
Asbru enables the designer to represent both the prescribed
actions of a skeletal plan and the knowledge roles required
by the various problem-solving methods performing the intertwined
supporting subtasks.
Asbru enables the intentions and goals of a guideline and
the temporal dimensions and uncertainties to be defined as
an intrinsic part of that guideline. This supports the appropriate
application of a guideline in practice and the quality assessment
of its application.
Main features:
- Prescribed actions and states can be continuous;
- Intentions, conditions, and world states are temporal
pattern;
- Uncertainty in both temporal scopes and parameters can
be flexibly expressed by bounding intervals;
- Plans might be executed in sequence, all plans or some
plans in parallel, all plans or some plans in a particular
order, or periodically;
- Particular conditions are defined to monitor the plans’
execution;
- Explicit intentions and preferences can be stated for
each plan separately. (Intentions are temporal-pattern constraints,
e.g., a process intention to administer regular insulin
twice a day; an outcome intention to maintain fasting blood
glucose within a certain range over at least 5 days a week,
that are allocated individual weights signifying their relative
importance. Such knowledge is necessary to determine, for
instance, whether a care provider is still following most
of the guideline, or, at least, its spirit. Such a provider
might be applying the guideline in modified fashion, as
is, in fact, the case in 50% of inspected guideline applications.)
|
| current work 1: Plan Execution and Analysis - Data Abstraction |
|
Temporal data abstraction bridges the gap between low-level
data delivered by, e.g., monitoring devices in an intensive
care unit and high-level concepts used, e.g., in treatment plans.
Two persisting problems are varying data quality and abstractions
which meet the intuitions of physicians. To cope with these
problems, we developed an algorithm called the Spread
and abstractions
of repeated patterns which promise to match closely the
human perception of graphs in addition to extracting features
not directly visible.
A related
project (Using Pulsoximetry and Time-Oriented Data Abstraction
Methods to Optimize Oxygen Supply for Neonates) is currently
evaluating a subset of these methods in a clinical setting,
namely the supply of oxigen to preterm neonates.
|
| current work 2: Guideline and Protocol Authoring |
Three activities in this area are being undertaken
by three separate groups in Amsterdam, Beer Sheva, Israel and
Vienna.
 The AI Department, Vrije Universiteit
Amsterdam (Frank
van Harmelen's group) is developing an intermediate representation to
visualize the upper part of the Asbru language hierarchy as
boxes in HTML.
Ben Gurion University of the Negev, Beer Sheva, Israel
(Yuval Shahar's group)
is developing DeGeL:
Digital Guidelines Library.
DeGeL is a hybrid, multifaceted representation language and
computerized, Web-based set of tools for storage, authoring,
retrieval and enactment of Asbru-based clinical guidelines.
The DeGeL method is designed to support the translation of
text-based guidelines firstly to structured text (in XML,
segmented and labelled by Asbru semantic tags), then into
a fully formal, machine-readable, and machine-executable (Asbru)
representation. It is envisaged that the first of these phases,
marking up existing text and adding appropriate semantic labels,
will be carried out by physicians, and that knowledge engineers
will convert the resulting highly structured XML-based text
into Asbru.
Each guideline might therefore exist as free text, XML,
or Asbru, or even combinations of the three (for example,
the guideline's entry conditions might well be the first
priority for conversion into Asbru, thus supporting automated
eligibility determination). At the same time, by developing
computational tools that can handle each representation
format, the automated services that the guideline's representation
can support are gradually being enhanced (e.g. from simple
full-text search, to context-sensitive retrieval and visualization,
and finally, to automated application and quality assessment),
while providing demonstrable value (such as enhanced precision
of search and retrieval) at each phase.
The Vienna University of Technology,
Institute of Software Technology and Interactive Systems
(Silvia
Miksch's group)
is developing DELT/A to provide a relatively easy way to
translate free text into Asbru. It achieves this by displaying
both the original text and the translation, and showing the
user which parts of the Asbru code correspond to which elements
of the original text. This not only makes it easier to author
plans, but also to understand the resulting Asbru constructs
in terms of the original guideline.
|
| current work 3: Verification and Validation of Protocols |
| The Protocure II
project, funded by the EU 5FP IST program, is investigating and validating
formal methods to improve medical protocols written in Asbru.
|
| current work 4: Information Visualization |
The Vienna University of Technology,
Institute of Software Technology and Interactive Systems
is developing AsbruView - Graphical user interface to Asbru to support visualization and understanding of Asbru guidelines,
and CareVis - Integrated Visualization of Computerized
Protocols and Temporal Patient Data, further details on which can be found on this site (see links below).
|
|
|
| references: introductory papers on Asbru |
| Shahar, Y., Miksch, S., and Johnson, P.
The Asgaard project: A task-specific framework for the application
and critiquing of time-oriented clinical guidelines. Artificial
Intelligence in Medicine (14): 29-51, 1998. [SMI]
[] |
" Clinical guidelines can be viewed as
generic skeletal-plan schemata that represent clinical procedural
knowledge and that are instantiated and refined dynamically
by care providers over significant time periods. In the Asgaard
project, we are investigating a set of tasks that support the
application of clinical guidelines by a care provider other
than the guideline's designer. We are focusing on application
of the guideline, recognition of care providers' intentions
from their actions, and critique of care providers' actions
given the guideline and the patient's medical record. We are
developing methods that perform these tasks in multiple clinical
domains, given an instance of a properly represented clinical
guideline and an electronic medical patient record. In this
paper, we point out the precise domain-specific knowledge required
by each method, such as the explicit intentions of the guideline
designer (represented as temporal patterns to be achieved or
avoided). We present a machine-readable language, called Asbru,
to represent and to annotate guidelines based on the task-specific
ontology. We also introduce an automated tool for acquisition
of clinical guidelines based on the same ontology, developed
using the PROTEGE-II framework. " |
| Advani A, Lo K, Shahar Y. Intention-based
critiquing of guideline-oriented medical care. Proc AMIA Symp
1998;:483-7.
[PubMed]
[] |
" We present a methodology and tool for providing
retrospective review and critiquing of guideline-based medical
care given to patients. We show how our guideline representation
language, Asbru, which supports the use of physicians intentions
in addition to physician's actions, allows us to compare the
care given to a patient at the level of the intention to treat
in addition to the more detailed plan carried out. We have developed
an algorithm based on this representation for retrospective
quality assessment of guideline-based care. Our method takes
the physician's and institution's preferences and policies into
account in explaining or justifying physician deviations from
the recommendations of a guideline. "
|
| Miksch S. Plan Management in the Medical
Domain. AI Communications, 12(4), pp. 209-235, 1999.
[] [Paper] |
"The need to improve the quality of health care has led to a strong demand for clinical protocols and computer systems
supporting both their creation and execution. Current approaches in the planning community concentrate on algorithmic
improvements, but mostly fail in medical applications. Planning approaches are based on assumptions like deterministic
behavior, which do not hold in medical domains. Additionally, they do not cover the problem area of acquisition and
verifying complex domain knowledge. In the field of medicine there is a strong movement towards clinical protocols –
resembling plans in AI – but computer support during execution of these plans (e.g., controlling, selection of alternatives) is
still basic. We need to build complex plans, but also to reason about them in different ways in order to modify plans, to
consider the effects of different plans over time, and to monitor execution. We call this range of reasoning tasks plan
management. We describe the requirements for these intertwined tasks of plan management so as to respond to the practical
demands, to compare approaches in planning and medical informatics to these requirements, and finally, to discuss how our
Asgaard project can meet them."
|
|
| references: modelling, authoring, verification and maintenance with Asbru |
| Seyfang, A.; Miksch, S.; Marcos, M.: Combining
Diagnosis and Treatment using Asbru, International Journal of
Medical Informatics, pp. 49-57, 68 (1-3), December 2002.
[PubMed]
[Vienna University Of Technology<
]
[IJMI
- Paper] |
" Traditionally, diagnosis and treatment
have been seen as two distinct tasks. Consequently, most approaches
to computer supported health care focus on one of the two-mostly
on diagnosis or rather on the interpretation of measurements
which is much better understood and formalised. However, in
practice diagnosis and treatment overlap and influence each
other in many ways. Combinations range from repeatedly going
through the diagnosis-treatment loop over a period of time to
permanent monitoring of the patients' health condition as it
is done in intensive care units. In this article we describe
how to model these combinations using the clinical protocol-representation
language Asbru. It implements treatment steps in a hierarchy
of skeletal, time-oriented plans. Diagnosis can either be described
in a declarative way in the conditions, under which treatment
steps are taken or it can be modelled explicitly as plans of
their own right. We demonstrate our approach using examples
taken from the American Association of Paediatricians' guideline
for the treatment of hyperbilirubinemia in the new-born. "
|
Votruba P, Miksch S, Seyfang A, Kosara R.
Tracing the formalization steps of textual guidelines.
Stud Health Technol Inform. 2004;101:172-6.
[PubMed]
[Vienna University of Technology]
|
"
This paper presents a new guideline authoring tool, called Guideline Markup Tool (GMT). It proposes two useful features, which are missing in existing tools. First, it facilitates the translation of a free-text guideline into a formal representation, providing special XML macros. Second, it can be used to create links between the original guideline and its formal representation. Therefore, the GMT eases the implementation of clinical guidelines in a formal representation, which can be used in monitoring and therapy planning systems.
"
|
Votruba P, Miksch S, Kosara R.
Facilitating knowledge maintenance of clinical guidelines and protocols.
Medinfo. 2004;11(Pt 1):57-61.
[PubMed]
[]
|
"
Clinical protocols and guidelines are widely used in the medi-cal domain to improve disease management techniques. Different software systems are in development to support the de-sign and the execution of such guidelines. The bottleneck in the guideline software developing process is the transformation of the text-based clinical guidelines into a formal representation, which can be used by the execution software. This paper introduces a method and a tool that was designed to provide a solution for that bottleneck. The so-called Guideline Markup Tool (GMT) facilitates the translation of guidelines into a formal representation written in XML. This tool enables the protocol designer to create links between the original guideline and its formal representation and ease the editing of guidelines applying design patterns in the form of macros. The usefulness of our approach is illustrated using GMT to edit Asbru protocols. We performed a usability study with eight participants to examine the usefulness of the GMT and of the Asbru macros, which showed that the proposed approach is very appropriate to author and maintain clinical guidelines.
"
|
| Kosara, R.; Miksch, S.; Seyfang, A. and
Votruba P.: Tools for Acquiring Clinical Guidelines in Asbru,
in Proceedings of the Proceedings of Sixth World Conference
on Integrated Design and Process Technology (IDPT'02).
[] [Paper]
|
" In order for clinical guidelines to be verified,
they must first be acquired or at least translated into a format
that can be treated formally. Most guidelines today either exist
as plain text, tables, or flow-charts. We present two tools
that support this translation: The Guideline Markup Tool (GMT)
and the Pontifex Intelligent XML Editor Extension (PIXEE). The
GMT provides a relatively easy way to translate free text into
Asbru. It does this by displaying both the original text and
the translation, and showing the user which parts of the Asbru
code correspond to which elements of the original text. This
not only makes it easier to author plans, but also to understand
the resulting Asbru constructs in terms of the original guideline.
PIXEE is a more general XML editor that has some special features
due to a richer representation of the language than pure XML.
It provides means to aggregate information dynamically and also
to more effectively work with language constructs. Both these
tools make the translation into a formal language easier and
therefore enable us to formally verify guidelines, thus reducing
errors and ambiguities in them. "
|
| Seyfang A, Miksch S, Marcos M. Combining
diagnosis and treatment using Asbru. Medinfo. 2001;10(Pt 1):533-7.
[PubMed]
[Vienna
- paper] |
"Traditionally, diagnosis and treatment have
been seen as two distinct tasks. Consequently, most approaches
to computer supported health care focus on one of the two -
mostly on diagnosis or rather on the interpretation of measurements
which is much better understood and formalized. However, in
practice diagnosis and treatment overlap and influence each
other in many ways. Combinations range from repeatedly going
through the diagnosis-treatment loop over a period of time to
permanent monitoring of the patients' health condition as it
is done in intensive care units. In this paper we describe how
to model these combinations using the clinical protocol-representation
language Asbru. It implements treatment steps in a hierarchy
of skeletal, time-oriented plans. Diagnosis can either be described
in a declarative way in the conditions, under which treatment
steps are taken or it can be modelled explicitly as plans of
their own right. We demonstrate our approach using examples
taken from the American Association of Paediatricians' guideline
for the treatment of hyperbilirubinemia in the new-born."
|
Marcos, M.; Berger, G.; van Harmelen, F.;
ten Teije, A.; Roomans, H.; Miksch, S.: Using Critiquing for
Improving Medical Protocols: Harder than it Seems, in Quaglini,
S.; Barahona, P.; Andreassen, S. (eds.): Proceedings of European
Conference on Artificial Intelligence in Medicine (AIME 2001),
Springer, Berlin, pp. 431-441, 2001.
[Abstract]
[Paper]
|
" Medical protocols are widely recognised to
provide clinicians with high-quality and up-to-date recommendations.
A critical condition for this is of course that the protocols
themselves are of high quality. In this paper we investi-gate
the use of critiquing for improving the quality of medical protocols.
We constructed a detailed formal model of the jaundice protocol
of the American Associ-ation of Pediatrics in the Asbru representation
language. We recorded the actions performed by a pediatrician
while solving a set of test cases. We then compared these expert
actions with the steps recommended by the formalised protocol,
and analysed the differences that we observed. Even our relatively
small test set of 7 cases revealed many mismatches between the
actions performed by the expert and the protocol recommendations,
which suggest improvements of the protocol. A major problem
in our case study was to establish a mapping between the ac-tions
performed by the expert and the steps suggested by the protocol.
We discuss the reasons for this difficulty, and assess its consequences
for the automation of the critiquing process. "
|
| Duftschmid G, Miksch S, Gall W. Verification
of temporal scheduling constraints in clinical practice guidelines.
Artif Intell Med 2002 Jun;25(2):93-121.
[PubMed]
[Paper] |
" In this paper, we focus on the detection
of flaws within temporal scheduling constraints. Temporal scheduling
constraints are important elements of therapy management, and
are frequently incorporated in clinical practice guidelines.
We present a suitable verification method that is based on calculating
the minimal network of temporal constraints on the execution
of guideline activities.... Although we concentrate on the guideline
representation language Asbru as the demonstration medium of
our method within this paper, our approach can be reused to
verify several alternative guideline representation formats.
" |
|
| references: Asbru visualisation tools |
Seyfang, A., Miksch, S., Conde, C. P., Wittenberg, J., Marcos, M. and
Rosenbrand, K. (2005). A Many-Headed Bridge between Informal and Formal
Guideline Representations. Proc. 10th Conf Artificial Intelligence in
Medicine (AIME), in press.
[]
[]
|
"
Clinical guidelines become more and more important as a means to improve the quality of care by supporting the medical staff. Modeling guidelines in a computer-processable form is a prerequisite for various computer applications, to improve the quality of guidelines and to support their application. However, transforming the original text into a formal guideline representation is a difficult task requiring both computer scientist skills and medical knowledge. To bridge this gap, we designed an intermediate representation named MHB.
"
|
W. Aigner, S. Miksch. CareVis: Integrated Visualization of Computerized
Protocols and Temporal Patient Data. Presentation: Workshop on Intelligent
Data Analyis in Medicine and Pharmacology (IDAMAP-2004), Stanford, USA;
06-09-2004; in: "Workshop Notes of the Workshop on Intelligent Data Analyis
in Medicine and Pharmacology", (2004), ISBN 961-6209-47-7.
[]
[Vienna University of Technology]
|
"
Currently, visualization support for patient data analysis is mostly limited to the representation of directly measured data. Contextual information on performed treatment steps is an important source for finding reasons and explanations for certain phenomena in the measured patient data. But this kind of information is mostly spared out in the analysis process.
We describe the development of CareVis – interactive visualization methods to integrate and combine classical data visualization with the visualization of treatment information in terms of logic and temporal aspects. We provide multiple simultaneous views to cover different aspects of a complex underlying data structure of treatment plans and patient data. The tightly coupled views use visualization methods well-known to domain experts and are designed to facilitate users’ tasks. The views are based on the concepts of clinical algorithm maps and LifeLines which have been extended in order to cope with the powerful and expressive plan representation language Asbru.
The user-centered development approach applied for these interactive visualization methods has been guided by user input gathered via a user study, design reviews, and prototype evaluations.
"
|
W. Aigner, S. Miksch: "Supporting Protocol-Based Care in Medicine via
Multiple Coordinated Views"; Presentation: CMV: 2nd International
Conference on Coordinated and Multiple Views in Exploratory Visualization,
IEEE, London, UK; 07-13-2004; in: "Proceedings International Conference on
Coordinated and Multiple Views in Exploratory Visualization (CMV 2004)",
IEEE, (2004), ISBN 0-7695-2179-7; 118 - 129.
[]
[Vienna University of Technology]
|
"
Computer supported protocol-based care aims to aid physicians in the treatment process. The main focus of current research is directed towards the formal methods and representations used “behind the scenes” of such systems. This work on the contrary, is situated at the human end of the human-machine chain.
We describe the development of interactive visualization methods to support protocol-based care. We provide multiple simultaneous views to cover different aspects of a complex underlying data structure of treatment plans and patient data. The tightly coupled views use visualization methods well-known to domain experts and are designed to facilitate users’ tasks. The views are based on the concepts of clinical algorithm maps and LifeLines which have been extended in order to cope with the powerful and expressive plan representation language Asbru.
The user-centered development approach applied for these interactive visualization methods has been guided by user input gathered via a user study, design reviews, and prototype evaluations.
"
|
| Kosara, R.; Miksch, S.; Hauser, H.: Focus
and Context Taken Literally, IEEE Computer Graphics and its
Applications, Special Issue: Information Visualization, pp.
22-29, 22(1), Jan.-Feb., 2002.
[Paper]
|
" Pointing out relevant information to a user
is one application of focus+context techniques in information
visualization. We present a method for doing this which uses
selective blur to direct the user's attention. This method is
based on the depth of field (DOF) effect used in photography
and cinematography, and is therefore both familiar to users
and perceptually effective. Because this method blurs objects
based on their relevance rather than their distance, we call
it Semantic Depth of Field (SDOF). We also present four example
applications that use SDOF to show its usefulness in practice,
and also provide details of a fast implementation that makes
it possible to use blur in interactive applications. A short
report on the results of a user study we performed is also given.
" |
| Kosara R, Miksch S. Metaphors of Movement:
A Visualization and User Interface for Time-Oriented, Skeletal
Plans, Artificial Intelligence in Medicine, Special Issue:
Information Visualization in Medicine, pp. 111-131, 22(2), 2001.
[PubMed]
[paper
- AIM]
[U
Vienna - Paper] |
" Therapy planning plays an increasingly important
role in the everyday work of physicians. Clinical protocols
or guidelines are typically represented using flow-charts, decision
tables, or plain text. These representations are badly suited,
however, for complex medical procedures.One representation method
that overcomes these problems is the language Asbru. But because
Asbru has a LISP-like syntax (and also incorporates many concepts
from computer science), it is not suitable for physicians.Therefore,
we developed a visualization and user interface to deal with
treatment plans expressed in Asbru. We use graphical metaphors
to make the underlying concepts easier to grasp, employ glyphs
to communicate complex temporal information and colors to make
it possible to understand the connection between the two views
(Topological View and Temporal View) available in the system.In
this paper, we present the design ideas behind AsbruView, and
discuss its usefulness based on the results of a usability study
we performed with six physicians. "
|
| Kosara, R.; Miksch, S.: Visualization Methods
for Data Analysis and Planning in Medical Applications, International
Journal of Medical Informatics, pp. 141-153, 68 (1-3), December
2002.
[Paper] |
"
Time plays an important role in medicine, both the past and the future. The medical history of a patient
represents the past, which needs to be understood by the physician to make the right decisions. The
past contains two different kinds of information: measured data (such as blood pressure) and incidents
(such as seizures). Planning therapies, on the other hand, requires looking into the future to a certain
extent.
Visual representations exist for both the past and the future, and they are very useful for getting a
better understanding of data or a plan. This paper surveys visualization techniques for both data analysis
and planning, and compares them based on a number of criteria.
" |
| Miksch, S., Kosara, R., Shahar, Y., and
Johnson, P. AsbruView: Visualization of time-oriented, skeletal
plans. In: The Fourth International Conference on Artificial
Intelligence Planning Systems 1998 (AIPS-98) (Carnegie-Mellon
University, Pittsburgh, Pennsylvania), AAAI Press, Menlo Park,
CA, 11-18.
[SMI]
[U.
Vienna] |
" Skeletal plans are a powerful way to
reuse existing domain-specific procedural knowledge. The main
draw-backs are that the compositions and the interdependencies
of different skeletal plans and their components are not lucid.
The aim of this paper is to overcome these limitations and to
present the visualization of time-oriented, skeletal plans.
Within the Asgaard project, we have developed a time-oriented
and intention-based language, called Asbru, to represent such
skeletal plans. The Asbru syntax is defined in Backus-Naur form
(BNF). Reading BNF or similar forms are next to impossible even
for domain experts. We explored different representations and
automated knowledge-acquisition tools. However, the domain experts
did not accept any of these representations. Consequently, we
investigated different metaphor graphics and ended up with a
plan visualization utilizing the metaphors of "tracks" and "traffic"
called AsbruView. We formatively evaluated different approaches
of this plan visualization with physicians applying treatment
protocols of mechanical ventilated newborn infants.
" |
|
| references: Asbru in use |
Marcos, M., Roomans, H., ten Teije, A. and van Harmelen, F. (2002).
Improving medical protocols through formalisation: a case study. 6th Intl
Conf Integrated Design & Process Technology.
[]
[]
|
"
Medical practice protocols or guidelines contain more or less precise recommendations
to assist practitioners and patient decisions about appropriate health care for specific
circumstances. In order to reach their potential benefits, protocols must fulfill strong
quality requirements. Medical bodies worldwide have made efforts in this direction, but
mostly using informal methods such as peer review of protocols. In this paper we present
a different approach, namely the quality improvement of medical protocols through formalisation.
Currently, protocols are described using a combination of different formats, e.g. text,
flow diagrams and tables. The underlying idea of our work is that making these descriptions
more precise, with the help of a more formal language, will expose parts where the
protocols are ambiguous, incomplete or even inconsistent. By pointing out these anomalous
parts, we expect to obtain useful indications for the improvement of the protocols.
This idea is widely acknowledged in fields like software engineering, where formal methods
are used as a tool for early detection of specification and design errors, but has been
largely unexplored for medical protocols.
The research question that we try to answer in this paper is: can formalisation contribute
to improve the quality of medical protocols? To answer this question, we have
carried out a case study on protocol formalisation. For this purpose, a choice had to be
made on the specific protocol representation language as well as on the medical protocols
to be used. Several languages exist for representing medical protocols. For our case
study we need a sufficiently formal and detailed enough language since only precise descriptions
will allow us to uncover anomalies in the protocols. We have chosen Asbru,
firstly because it is more precise in the description of various medical aspects, and secondly
because Asbru protocols are more declarative, and thus they are more amenable to
formal analysis. Concerning the protocols, we have tried to select two examples covering
different features. The first one is a protocol for the management of diabetes mellitus
type 2, which comes from the set of protocols developed by the Dutch Association of
General Practitioners. The second example is a pediatrics protocol for the management
of jaundice in healthy newborns, developed by the American Academy of Pediatrics.
"
|
Seyfang A, Miksch S, Marcos M.
Combining diagnosis and treatment using Asbru.
Int J Med Inform. 2002 Dec 18;68(1-3):49-57.
[PubMed]
[Vienna University of Technology]
|
"
Traditionally, diagnosis and treatment have been seen as two distinct tasks. Consequently, most approaches to computer supported health care focus on one of the two-mostly on diagnosis or rather on the interpretation of measurements which is much better understood and formalised. However, in practice diagnosis and treatment overlap and influence each other in many ways. Combinations range from repeatedly going through the diagnosis-treatment loop over a period of time to permanent monitoring of the patients' health condition as it is done in intensive care units. In this article we describe how to model these combinations using the clinical protocol-representation language Asbru. It implements treatment steps in a hierarchy of skeletal, time-oriented plans. Diagnosis can either be described in a declarative way in the conditions, under which treatment steps are taken or it can be modelled explicitly as plans of their own right. We demonstrate our approach using examples taken from the American Association of Paediatricians' guideline for the treatment of hyperbilirubinemia in the new-born.
"
|
|
| references: technical documents |
|
Seyfang, A.; Kosara, R.; Miksch S.: Asbru Reference Manual,
Asbru Version 7.3, Vienna University of Technology, Institute
of Software Technology and Interactive Systems, Vienna, Technical
Report, Asgaard-TR-2002-1, 2002.
[Manual]
|
"
"
|
|
|
| contact |
Silvia Miksch
Institute of Software
Technology and Interactive Systems
Vienna University of Technology
Favoritenstrasse 9-11/188
A-1040 Vienna
Austria
E: silvia@ifs.tuwien.ac.at
|
| links |
in2vis
|
|
| acknowledgements |
| Silvia Miksch, Vienna University of Technology & Danube University Krems, Austria |
| page history |
Entry on OpenClinical: 2002
Last main updates: 03 September 2003; 24 May 2005
Design - template v0.3: 25 June 2005. |
|
|
|
|
AsbruView - Graphical user interface to Asbru to support visualization and understanding of Asbru guidelines [OC]