|
|
Methods and tools for the development of computer-interpretable guidelines |
|
 PROforma |
|
Formal knowledge representation method for the development and execution of clinical guidelines |
|
PROforma highlights:
Process description language [Sutton and Fox, 2003] grounded in a logical model of decision making and plan enactment;
Task-based formalism: plans, decisions, enquiries and actions;
Suites of authoring, verification and testing tools
(AREZZO® and Tallis);
Supports web or standalone execution;
Clinical applications in use and in development.
|
|
| keywords |
Knowledge representation, computer-interpretable guidelines, development and execution, representation formalism, clinical knowledge authoring tool, guideline execution engine, Arezzo, Tallis, WWW-based enactment. |
| developed by |
Advanced Computation Laboratory, Cancer Research UK |
| introduced |
Development started in 1992; Arezzo technology released: 1996; Tallis technology introduced: 2000. |
| status |
PROforma, Arezzo and Tallis are in use / under continued development. |
| support |
EU 3rd Framework Dilemma project (1992-5).
EU 4th Framework Health Telematics PROMPT project (1996-9). |
| in use |
Many PROforma-based applications have been developed (see below for details). |
| tools |
Tallis technology can be downloaded for research use by members of non-profit organisations,
subject to signing a non-disclosure agreement with Cancer Research Technology (CRT), Cancer Research UK, London
(see links below for the form and CRT contact details).
Arezzo and Arezzo applications are commercially developed by InferMed Ltd. Arezzo Tools
can also be demonstrated by InferMed on request.
|
|
| description: Language and method |
PROforma is a formal knowledge representation
language capable of capturing the structure and content of a clinical
guideline in a form that can be interpreted by a computer. The language
forms the basis of a method and a technology for developing and publishing
executable clinical guidelines.
Applications built using PROforma software are designed to support the management of medical procedures and clinical decision making at the point of care.
Developing PROforma applications
In PROforma, a guideline application is modelled as a set of tasks and data items.
The notion of a task is central -
the PROforma task model (figure 1) divides from the keystone (generic task) into four types: plans, decisions, actions and enquiries.
Figure 1: The PROforma task model
Plans are the basic building blocks of a guideline and may contain any number of tasks of any type, including other plans.
Decisions are taken at points where options are presented, e.g. whether to treat a patient or carry out further investigations.
Actions are typically clinical procedures (such as the administration of an injection) which need to be carried out.
Enquiries are typically requests for further information or data, required before the guideline can proceed.
PROforma software consists of a graphical editor to support the authoring process, and an engine to execute the guideline
specification. The engine can also be used as a tester during the application development phase.
A PROforma editor supports the construction of a guideline in terms of the four task types.
Using the icons shown in the diagram, networks of tasks can be composed that represent plans or procedures carried out over time.
In the editor, logical and temporal relationships between tasks are captured naturally by linking them as required with arrows.
Any procedural and medical knowledge required by the guideline as a whole or by an individual task is entered using templates attached to each task.
The resulting populated graphical structure is automatically converted into a database ready for execution.
|
| PROforma tools |
The first implementation of software to create, visualise and enact PROforma guidelines was
Arezzo®, now a commercial product available from
InferMed Ltd., London.
Arezzo® consists of a Composer (graphical knowledge authoring tool) and Performer (application tester and execution engine).
Arezzo® applications are designed to be enacted on MS Windows platforms.
Tallis is a new Java implementation of PROforma-based authoring
and execution tools developed by Cancer Research UK. Tallis is based on a later version of the PROforma language model.
It consists of a Composer (to support creation, editing, and graphical visualisation of guidelines),
Tester and Engine (to enact guidelines and allow them to be manipulated by other applications).
Tallis is also designed for delivering web-based services; applications will run on any platform
and integrate with other components, including 3rd party applications.
The Tallis Publisher (based on Java Servlets) forms part of the Tallis software suite.
This has also been built to allow guidelines to be published and enacted over the WWW.
|
| PROforma in use |
Arezzo-based PROforma technologies and applications
(including commercial and prototype clinical
decision support systems) |
|
system |
summary
|
links |
ORAMA
Optimal Renal Anaemia Management Assessment
|
In clinical use. Developed by
InferMed Ltd for Hoffmann-La Roche.
|
|
Retrogram
HIV treatment |
In clinical use. Developed by
Virology Networks and InferMed Ltd for Hoffmann-La Roche.
|
|
MACRO
Web-based clinical trial management system
|
MACRO has been used at over 200 sites in 35 countries across the world since July 1999. |
|
ARNO
Cancer pain control |
Collaboration between InferMed Ltd., St. Christopher's Hospice and King's College Hospital in London.
|
|
Evidence without Effort
Clinical decision support |
A collaboration by InferMed and BMJ Publishing. Integration of decision support with
Clinical Evidence.
|
|
RAGs
Genetic risk management |
Support for GPs in assessing and communicating genetic risk information to women who are worried about their personal risk to breast and ovarian cancer.
|
|
ERA
Early referral for suspected cancer |
ERA is designed to help GPs comply with UK NHS urgent (two week) cancer referral guidelines
|
|
CAPSULE
Decision support for prescribing in primary care.
|
Described in: Walton RT et al. Evaluation of computer support for prescribing (CAPSULE) using simulated cases.
BMJ. 1997 Sep 27;315(7111):791-5.
|
|
e-Asma
Decision support for asthma management.
|
University of the Basque Country, San Sebastián;
Basque Foundation for Medical Research; Basque Health Service.
|
|
|
Tallis-based PROforma applications and technologies
|
|
system |
background
|
links |
CREDO
A clinical trial of decision-making and workflow management in the care of women at risk of or with a proven diagnosis of breast cancer.
|
Collaboration: Cancer Research UK, Addenbrookes Hospital, Cambridge,
Guys Hospital, London, Carol Franc Buck Breast Care Center, University of California/San Francisco
|
|
HOMEY
The
Development of natural language and speech interfaces for patient home
monitoring and clinical services
|
5FP EU-funded project. Tallis has been adapted to permit spoken
interaction with clinical (or other) applications. An interface in a patient interviewing
application has been built and demonstrated.
|
|
LISA
Decision support for collaborative care in childhood acute lymphoblastic leukaemia
|
LISA is a decision support system embedded in a clinical database system for helping clinicians comply with dose amendement rules defined in a trial protocol for the treatment of children with acute lymphoblastic leukaemia.
|
|
|
|
|
| references |
| Sutton DR, Fox J.
The Syntax and Semantics of the PROforma guideline modelling language.
J Am Med Inform Assoc. 2003 Sep-Oct;10(5):433-43.
[PubMed]
[PubMedCentral]
|
"
PROforma is an executable process modelling language that has been successfully used to build and deploy a range of decision support systems, guidelines and other clinical applications. It is one of a number of recent proposals for representing clinical protocols and guidelines in a machine-executable format ... In this paper we outline the task model for the language and provide an operational semantics for process enactment, together with a semantics for expressions which may be used to query the state of a task during enactment. The operational semantics includes a number of public operations that may be performed on an application by an external agent, including operations that change the values of data items, recommend or make decisions, manage tasks that have been performed, and perform any task state changes that are implied by the current state of the application...
"
|
| Fox J., Thomson R.
Decision Support and
Disease Management: A Logic Engineering Approach. IEEE Transactions on
Information Technology in Biomedicine, vol 2 no. 4, December 1998, pp217-228
[PubMed]
[CRUK paper]
|
"This paper describes the development and application of PROforma, a unified technology for clinical decision support and disease management... The work has been based on logic engineering, a distinct design and development methodology that combines concepts from knowledge engineering, logic programming, and software engineering... The principal technical results of the work are the PROforma logic language for
defining clinical processes and an associated suite of
software tools for delivering applications, such as
decision support and disease management procedures...
The development toolset includes a powerful visual
programming environment. for composing applications from
these standard components, for verifying consistency and
completeness of the resulting specification and for
delivering stand-alone or embeddable applications. Tools
and applications that have resulted from the work are
described and illustrated, with examples from specialist
cancer care and primary care. The results of a number of
evaluation activities are included..."
|
| Fox J. and Das S. Safe and Sound: Artificial Intelligence in Hazardous
Applications. Jointly published by the AAAI, Menlo Park, CA, and MIT Press, Cambridge Mass., 2000. ISBN 0-262-06211-9
MIT Press
Preface
|
"Computer science and artificial
intelligence are increasingly used in the hazardous and
uncertain realms of medical decision making, where small
faults or errors can spell human catastrophe. This book
describes, from both practical and theoretical
perspectives, an AI technology for supporting sound
clinical decision making and safe patient management.
The technology combines techniques from conventional
software engineering with a systematic method for
building intelligent agents. Although the focus is on
medicine, many of the ideas can be applied to AI systems
in other hazardous settings. The book also covers a
number of general AI problems, including knowledge
representation and expertise modeling, reasoning and
decision making under uncertainty, planning and
scheduling, and the design and implementation of
intelligent agents. The book, written in an informal
style, begins with the medical background and
motivations, technical challenges, and proposed
solutions. It then turns to a wide-ranging discussion of
intelligent and autonomous agents, with particular
reference to safety and hazard management. The final
section provides a detailed discussion of the knowledge
representation and other aspects of the agent model
developed in the book, along with a formal logical
semantics for the language."
|
| Fox J., Johns N. & Rahmanzadeh A. Disseminating Medical
Knowledge-The PROforma Approach. Artificial Intelligence in Medicine, 14,
1998, 157-181.
[PubMed]
[CRUK - paper]
|
"Medical knowledge is traditionally disseminated via the publication of documents and through participation in clinical practice. Information technology offers to extend both modes of dissemination, via electronic publishing and virtual reality training, for example. AI promises even more radical changes through the possibility of publishing clinical expertise in the form of expert systems, which assist patient care through active decision support and workflow management. PROforma is a knowledge
representation language that is designed to support this
new mode of dissemination. It is based on an intuitive
model of the processes of care and well-understood
logical semantics. This paper provides a description of
the language and associated software tools, and
discusses its potential roles in, and implications for,
medical knowledge publishing."
|
| Bury J., Fox J., & Sutton D. The PROforma guideline specification language: progress and prospects.
Proceedings of the First European Workshop, Computer-based Support for Clinical Guidelines and Protocols (EWGLP 2000), Leipzig 13-14 Nov. 2000.
[CRUK abstract]
[CRUK paper]
|
"PROforma is a formal knowledge representation language designed to capture the content and structure of a clinical guideline in a form that can be interpreted by a computer. The language embodies many contemporary themes in machine enactable guideline representation whilst retaining some distinctive features. This paper describes the key features of the PROforma language in the context of recent trends and developments in the field of electronic guideline representation formats. We describe our experiences in applying PROforma to a range of clinical decision making and workflow problems, and the benefits and limitations of the current language specification are discussed. Finally, we outline plans for the further refinement of PROforma."
|
|
| references: evaluation |
Fox J, Patkar V, Thomson R.
Decision Support for Healthcare: the PROforma evidence base
Informatics in Primary Care 2006; 14:49-54
[]
[CRUK]
"
Cancer Research UK has developed PROforma, a formal language for modelling clinical processes, along with associated tools for creating decision support, care planning, clinical workflow management and other applications. The PROforma method has been evaluated in a variety of settings: primary healthcare (prescribing, referral of suspected cancer patients, genetic risk assessment) and in specialist care of patients with breast cancer, leukaemia, HIV infection and other conditions. About nine years of experience have been gained with PROforma technologies. Seven trials of decision support applications have been published or are in preparation. Each of these has shown significant positive effects on a variety of measures of quality and/or outcomes of care. This paper reviews the evidence base for the clinical effectiveness of these PROforma applications, and previews the CREDO project - a multi-centre trial of a complex PROforma application for supporting integrated breast cancer care across primary and secondary care settings.
"
|
Sutton DR, Taylor P, Earle K. Evaluation of PROforma as a language for implementing medical guidelines in a practical context.
BMC Med Inform Decis Mak. 2006 Apr 5;6(1):20
[PubMed]
[BioMed Central]
|
"
ABSTRACT: BACKGROUND: PROforma is one of several languages that allow clinical guidelines to be expressed in a
computer-interpretable manner. How these languages should be compared, and what requirements they should meet, are
questions that are being actively addressed by a community of interested researchers. METHODS: We have developed a
system to allow hypertensive patients to be monitored and assessed without visiting their GPs (except in the most
urgent cases). Blood pressure measurements are performed at the patients pharmacies and a web-based system, created
using PROforma, makes recommendations for continued monitoring, and/or changes in medication. The recommendations
and measurements are transmitted electronically to a practitioner with authority to issue and change prescriptions.
We evaluated the use of PROforma during the knowledge acquisition, analysis, design and implementation of this
system. The analysis focuses on the logical adequacy, heuristic power, notational convenience, and explanation support
provided by the PROforma language. RESULTS: PROforma proved adequate as a language for the implementation
of the clinical reasoning required by this project. However a lack of notational convenience led us to use UML activity
diagrams, rather than PROforma process descriptions, to create the models that were used during the knowledge
acquisition and analysis phases of the project. These UML diagrams were translated into PROforma during the
implementation of the project. CONCLUSIONS: The experience accumulated during this study highlighted the importance of
structure preserving design, that is to say that the models used in the design and implementation of a knowledge-based
system should be structurally similar to those created during knowledge acquisition and analysis. Ideally the same
language should be used for all of these models. This means that great importance has to be attached to the notational
convenience of these languages, by which we mean the ease with which they can be read, written, and understood by human beings. The importance of notational convenience arises from the fact that a language
used during knowledge acquisition and analysis must be intelligible to the potential users of a system, and to the domain experts who provide the knowledge that will be used in its construction.
"
|
|
|
| contact |
Prof. John Fox
Advanced Computation Laboratory
Cancer Research UK
PO Box 123
Lincoln's Inn Fields
London WC2A 3PX UK
E: john.fox cancer.org.uk
|
| links |
|
|
| acknowledgements |
| John Fox, Cancer Research UK; Robert Dunlop, InferMed Ltd. |
| page history |
Entry on OpenClinical: 2001
Last main updates: 06 December 2003; 10 June 2004; 09 May 2006 |
|
|
|
|
Description - OpenClinical