OpenClinical logo

Clinical demonstrators

Methods and tools for the development of computer-interpretable guidelines

GUIDE logo
GUIDE is a component-based multi-level architecture designed to integrate a formalized model of the medical knowledge contained in clinical guidelines and protocols with both workflow management systems and Electronic Patient Record technologies.
keywords Computer-interpretable guidelines, knowledge representation, Workflow, patient workflow management systems, Petri Nets, Careflow, allied health practitioners, organisational knowledge, organisational impact, organisational change
developed by Laboratory for Medical Informatics, Department of Computer and System Science, University of Pavia, Italy
introduced 1998.

Re-engineered in 2002.
status In use / under continued development.
support FIRB (Fondo per gli investimenti in ricerca di base) project, supported by the Ministero dell'Istruzione, dell'Università e della Ricerca
in use Research prototypes have been developed that implement (i) protocols for the management of breast cancer in hospital and (ii) health care pathways to support breast cancer home-care.

Two larger scale applications have been built in two clinical domains:
  1. An application (based on the American Heart Association stroke and TIA guidelines) to support the management of stroke patients has been used and evaluated in four hospitals in the Lombardia region [Quaglini et al, 2004, Micieli et al, 2002]. The system is currently being re-engineered.
  2. An application to support the management of patients with heart failure is being evaluated by general practitioners in the Trentino Alto Adige region. The system is designed in particular to help GPs with ACE-inhibitor treatment.
The Guide environment (figure 1) integrates three main independent modules:
  1. Guideline Management System (GlMS) (providing clinical decision support)
  2. Electronic Patient Record (EPR)
  3. Workflow Management System (WfMS) or Careflow Management System (CfMS) (providing organisational support).

GUIDE architecture overview
Figure 1: GUIDE architecture

The Common Ground (figure 1) is fundamental for supporting communication between modules. The interaction between GUIDE modules is message-based and defined by specific contracts. The paradigm employed ('Separation of Concerns' - SoC) means that one domain doesn't need to know anything more than current contract details and the shared terminologies and ontologies in order to communicate with another domain. This approach reduces crosstalk and supports parallelization. Further, the strong separation between medical and organizational issues helps improve interaction between experts of different skills and backgrounds and the system.


Guide aims to provide an integrated medical knowledge management infrastructure, providing support for:
  • Computerized knowledge representation
  • Different views of the formalized knowledge to allow different people with different roles (e.g. clinicians, patients, adminsitrators...) to have their own context-specific interactions with the system (for example, if a guideline for a chronic condition suggests taking a blood sample every fifteen days, the physician view would incorporate the interpretation of the examination results, while the patient view would provide a reminder and a facility to book the blood examination)
  • The use of formalized knowledge for generating health care processes able to respond to environment stimuli and patient condition mutations (connection to the electronic patient record and to the workflow system)
  • The generation of new knowledge (elicitation of tacit knowledge) through continuous feedback on guideline acceptance, usability and compliance. Since this is a crucial aspect of the system, Guide is able to manage flexible health care pathways and user interaction
  • Reuse and sharing of statically and dynamically generated knowledge components.

A broader view of the architecture of the Guide system, highlighting medical decision support features, is depicted in figure 2. The multi-level architecture shown consists of two levels: the formalization (or national) and the health organization levels. At the formalization level, the system aims to represent, disseminate and manage guidelines validated by a health authority or scientific organization, for example. At the local level, healthcare organizations (HCOs) may decide to adopt a guideline to increase the quality of their care services. Site-specific specification may be performed by individual HCOs. Using Guide, versioning, dissemination, managing, adapting guidelines can take place aither at the formalization or health organization levels.

detailed view of Guide architecture
Figure 2: Detailed view of Guide architecture highlighting support for medical decision support

The Guide framework includes a Virtual Medical Record (VMR) and a powerful logging system that allows all the details of the health care process to be traced, facilitating process mining.

The Guide model

The Guide model is based on Petri Nets, a rigorous formalism invented by Carl Adam Petri in the 1960s, for modelling concurrent processes [Peterson, 1981]. The strength of the formalism, when applied to healthcare, is its ability to support the modelling of complex concurrent processes (sequential, parallel and iterative logic flows). The formalism has been extended to support improved modelling of time, data and hierarchies.

The Guide Editor

The Guide Editor is a tool for formalizing medical knowledge. The approach adopted, again strongly inluenced by Petri Nets, resembles flow-chart development as this forms a good theoretical basis for the management of processes. Health care paths are typically very complicated so the Guide method has adopted a multi-level representation where, for example, the sub-level includes detail describing concepts expressed in the higher level. Health care processes specified in the Guide method consist of a sequence of blocks, on different levels, each of them having a precise medical meaning or a precise flow management function.

Workflow processes in a guideline for stroke
Figure 3: Illustration of workflow processes in a fragment from a guideline for the stroke patients management. A diagnostic strategy is represented, where choice has to be made among different image-based examinations.


Ciccarese P, Caffi E, Boiocchi L, Quaglini S, Stefanelli M. A guideline management system. Medinfo. 2004;2004:28-32.

[PubMed]   [U Pavia]

" This paper describes the architecture of NewGuide, a guide-line management system for handling the whole life cycle of a computerized clinical practice guideline. NewGuide compo-nents are organized in a distributed architecture: an editor to formalize guidelines, a repository to store them, an inference engine to implement guidelines instances in a multi-user envi-ronment, and a reporting system storing the guidelines logs in order to be able to completely trace any individual physician guideline-based decision process. There is a system "central level" that maintains official versions of the guidelines, and local Healthcare Organizations may download and implement them according to their needs. The architecture has been im-plemented using the Java 2 Enterprise Edition (J2EE) plat-form. Simple Object Access Protocol (SOAP) and a set of con-tracts are the key factors for the integration of NewGuide with healthcare legacy systems. They allow maintaining unchanged legacy user interfaces and connecting the system with what-ever electronic patient record. The system functionality will be illustrated in three different contexts: homecare-based pres-sure ulcer prevention, acute ischemic stroke treatment and heart failure management by general practitioners. "

Quaglini S, Ciccarese P, Micieli G, Cavallini A. Non-Compliance with Guidelines: Motivations and Consequences in a case study. In: Eds Kaiser K, Miksch S, Tu SW, Proceedings of the Symposium on Computerised Guidelines and Protocols (CPG 2004), pp75-87, IOS Press, 2004

[]   []

" Guidelines are often based on a mixture of evidence-based and consensus-based recommendations. It is not straightforward that providing a series of "good" recommendations result in a guideline that is easily applicable, and it is not straightforward that acting according to such recommendations leads to an effective and efficient clinical practice. In this paper we summarize our experience in evaluating both the usability and the impact of a guideline for the acute/subacute stroke management. A computerised version of the guideline has been implemented and linked to the electronic patient record. We collected data on 386 patients. Our analysis highlighted a number of non-compliances. Some of them can be easily justified, while others depend only on physician resistance to behavioural changes and on cultural biases. From our results, health outcomes and costs are related to guideline compliance: a unit increase in the number of non-compliance results in a 7% increase of mortality at six months. Patients treated according to guidelines showed a 13% increase in treatment effectiveness at discharge, and an average cost of 2929 € vs 3694 € for the others. "

Micieli G, Cavallini A, Quaglini S. Guideline Compliance Improves Stroke Outcome - A Preliminary Study in 4 Districts in the Italian Region of Lombardia. Stroke 2002; 33:1341-1347.

[]   []

" *Background and Purpose*—Guidelines for medical practice in stroke have been proposed in different countries, but their impact on stroke outcome has not been verified to date. The aim of this study was to evaluate the impact of the American Heart Association guidelines for acute stroke and for transient ischemic attack on first-ever stroke patients. *Methods*—Three hundred eighty-six first-ever ischemic stroke patients were admitted to the study. Those observed within 6 hours from stroke onset were eligible for the acute clinical phase of the study, while all were admitted to the early clinical phase. The follow-up lasted 6 months. Primary end points were survival and the effectiveness of treatment on disability, measured as the proportion of potential improvement in the Barthel Index score achieved during treatment. A rating of noncompliance with the guideline recommendations was calculated for each patient, and its association with the end points was investigated. The Kaplan-Meier method and log-rank test were used to estimate and compare survival curves between groups; Cox proportional hazards model and logistic regression were used to identify risk factors for mortality; and correlation tests and regression analysis were used to evaluate the influence of guideline compliance on disability. Both univariate and multivariate statistical analyses were performed. *Results—*Survival and treatment effectiveness were directly correlated with guideline compliance. ... *Conclusions*—This study demonstrates an association between adherence to guidelines and stroke outcome, and it can be viewed as a study that prepares the way for a randomized controlled trial in this area. It also emphasizes the need to develop personnel and structures devoted to stroke care because an evidence-based clinical approach could significantly reduce the risk of death. (Stroke. 2002;33:1341-1347.) "
Quaglini S, Stefanelli M, Cavallini A, Micieli G, Fassino C, Mossa C. Guideline-based careflow systems. Artif Intell Med 2000 Aug;20(1):5-22.

[PubMed]   []

" This paper describes a methodology for achieving an efficient implementation of clinical practice guidelines. Three main steps are illustrated: knowledge representation, model simulation and implementation within a health care organisation. The resulting system can be classified as a 'guideline-based careflow management system'. It is based on computational formalisms representing both medical and health care organisational knowledge. This aggregation allows the implementation of a guideline, not only as a simple reminder, but also as an 'organiser' that facilitates health care processes. As a matter of fact, the system not only suggests the tasks to be performed, but also the resource allocation. The methodology initially comprehends a graphical editor, that allows an unambiguous representation of the guideline. Then the guideline is translated into a high-level Petri net. The resources, both human and technological necessary for performing guideline-based activities, are also represented by means of an organisational model. This allows the running of the Petri net for simulating the implementation of the guideline in the clinical setting. The purpose of the simulation is to validate the careflow model and to suggest the optimal resource allocation before the careflow system is installed. The final step is the careflow implementation. In this phase, we show that the 'workflow management' technology, widely used in business process automation, may be transferred to the health care setting. This requires augmenting the typical workflow management systems with the flexibility and the uncertainty management, typical of the health care processes. For illustrating the proposed methodology, we consider a guideline for the management of patients with acute ischemic stroke. "
Ciccarese P, Caffi E, Boiocchi L et al. The NewGuide Project: guidelines, information sharing and learning from exceptions. In: Dojat M, Keravnou ET, Barahona P (Eds.): Artificial Intelligence in Medicine, 9th Conference on Artificial Intelligence in Medicine in Europe, AIME 2003, Protaras, Cyprus, October 18-22, 2003, Proceedings. Lecture Notes in Computer Science 2780 Springer 2003.

[]   [U leipzig]

" Among the well agreed-on benefits of a guideline computerisation, with respect to the traditional text format, there are the disambiguation, the possibility of looking at the guideline at different levels of detail and the possibility of generating patient-tailored suggestions. Nevertheless, the connection of guidelines with patient records is still a challenging problem, as well as their effective integration into the clinical workflow. In this paper, we describe the evolution of our environment for representing and running guidelines. The main new features concern the choice of a commercial product as the middle layer with the electronic patient record, the consequent possibility of gathering information from different legacy systems, and the extension of this virtual medical record to the storage of process data. This last feature allows managing exceptions, i.e. decisions that do not comply with guidelines. "
Quaglini S, Stefanelli M, Lanzola G, Caporusso V, Panzarasa S. Flexible guideline-based patient careflow systems. Artif Intell Med. 2001 Apr;22(1):65-80.

[PubMed]   []

" Workflow Management Systems integrate domain and organisational knowledge to support business processes. When applied to the medical environment, they can be termed "Careflow Management Systems", and may be used to manage care delivery by enhancing co-operation among healthcare professionals. This paper focuses on care delivery based on clinical practice guidelines. Healthcare organisations are very different from industrial or commercial companies: their main goal is not profit, but maintaining and improving the health of the public. Therefore, outcomes are difficult to measure. Firstly, physicians, while playing a variety of roles, are quite independent decision-makers; secondly, the object of the process, i.e. the patient, may be involved in choosing treatment options, and may be treated by different institutions. For these reasons, the standard functionality of typical Workflow Management Systems must be strongly enhanced in order to cope with healthcare delivery needs. A major issue is accounting for exceptions. In most non-clinical settings this is not a problem because processes are very well defined and can often be easily controlled by some higher authority. As explained above, this does not happen in healthcare organisations. Responsibilities are widely shared, and health care professionals may be non-compliant with guidelines for a variety of reasons. The paper presents a classification of possible exceptions, and shows how the sequence of tasks described by a guideline may be altered, at the implementation level, in order to meet actual user needs, while maintaining guideline intentions as much as possible. A terminology server is also exploited towards this end. This work illustrates a prototype of a Careflow Management System based on an international guideline for ischemic stroke treatment, developed by the American Heart Association. "
S. Quaglini, M. Stefanelli, V. Caporusso, S. Panzarasa. Managing Non-Compliance in Guideline-based Careflow Systems. Proc AMIA 2000 Annual Symposium.

[Abstract]   [AMIA]

" The approach to guideline implementation in real clinical setting, presented in this paper, requires to model separately the medical knowledge and the organizational knowledge. Then, the two knowledge types are integrated by means of a patient workflow management system, or careflow. Typical workflow management systems do not care for exceptions, because they usually implement very rigid processes, which often can be easily controlled by some authority. In the medical environment, this is not the case. Responsibilities are widely distributed, and health care professionals may be non-compliant with guidelines and protocols, for a variety of well-founded reasons. We show how the sequence of tasks described by a guideline may be altered, at the implementation level, in order to face the actual user needs, while maintaining as much as possible the guideline intention. This work illustrates a prototype of such a careflow system based on a guideline for ischemic stroke treatment. "
L. Dazzi, C. Fassino, R. Saracco, S. Quaglini, & M. Stefanelli. A Patient Workflow Management System Built on Guidelines. AMIA 1997 Annual Fall Symposium.

[Abstract]   [AMIA]

" To provide high quality, shared, and distributed medical care, clinical and organizational issues need to be integrated. This work describes a methodology for developing a Patient Workflow Management System, based on a detailed model of both the medical work process and the organizational structure. We assume that the medical work process is represented through clinical practice guidelines, and that an ontological description of the organization is available. Thus, we developed tools 1) for acquiring the medical knowledge contained into a guideline, 2) to translate the derived formalized guideline into a computational formalism, precisely a Petri Net, 3) to maintain different representation levels. The high level representation guarantees that the Patient Workflow follows the guideline prescriptions, while the low level takes into account the specific organization characteristics and allow allocating resources for managing a specific patient in daily practice. "
J.L. Peterson. Petri Net Theory and the Modelling of Systems. Prentice Hall, 1981

[]   []

" "
contact Paolo Ciccarese
Laboratorio di Informatica Medica
Università di Pavia
Via Ferrata, 1
27100 Pavia, Italy

T: +39-0382-525121

links  bullet  GUIDE [U Pavia]  bullet  Laboratory for Medical Informatics, Department of Computer and System Science, University of Pavia, Italy  bullet  Petri Nets  bullet  Ministero dell'Istruzione, dell'Università e della Ricerca
Paolo Ciccarese, Università di Pavia
page history
Entry on OpenClinical: 2002
Last main updates: 21 April 2004; 30 September 2004.


Search this site
Privacy policy User agreement Copyright Feedback

Last modified:
© Copyright OpenClinical 2002-2011