Towards a comprehensive treatment of repetitions, periodicity and temporal constraints in clinical guidelines

Anselma, Luca; Terenziani, Paolo; Montani, Stefania; Bottrighi, Alessio

doi:10.1016/j.artmed.2006.03.007

Cited by 70 publications

(97 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Es wird alsoüberprüft ob Der erste Teil der Gleichung kann positiv entschieden werden, da ⊥ + 5 = ⊥ und damit die Disjunktion erfüllt ist. Für den zweiten Teil muss geprüft werden, ob der Wert 5 + hour(5) kleiner ist als 5 + hour (6). Dies ist der Fall, da hour eine Funktion ist, die von int nach int abbildet und deren steigende Monotonie bekannt ist.…”

Section: Definitionunclassified

See 1 more Smart Citation

Modellierung und Verifikation medizinischer Leitlinien

Schmitt¹

2010

It - Information Technology

View full text Add to dashboard Cite

Zusammenfassung Medizinische Leitlinien sind ein Instrument zur Steigerung der Effizienz und Qualität medizinischer Behandlungen. Um dies zu erreichen, bündeln Leitlinien alles verfügbare Wissen zur Behandlung einer bestimmten Krankheit in einem kompakten Dokument, nach dem dann tausende von Patienten behandelt werden. Dies eröffnet die Frage, wie die Qualität der Leitlinien selbst sichergestellt werden kann. Der hier vorgestellte Ansatz überträgt Methoden der strukturierten Softwareentwicklung auf medizinische Leitlinien. Dadurch ist es erstmals möglich, Garantien bezüglich der Korrektheit von medizinischen Leitlinien zu geben.

show abstract

Section: Definitionunclassified

“…GLARE wird in [6,69] [70] selbst grenzt sich von dem hier vorgestellten Ansatz zur automatischen Modellprüfung dadurch ab, dass der dort verwendete Modellprüfer SPIN Aussagen in LTL prüft, während hier der Modellprüfer SMV verwendet wird um Aussagen in ACTL zu beweisen.…”

Section: Glareunclassified

Modellierung und Verifikation medizinischer Leitlinien

Schmitt¹

2010

It - Information Technology

View full text Add to dashboard Cite

show abstract

“…These languages provide formalisms for specifying knowledge related to these protocols, such as decision criteria and time-oriented aspects of treatment. Nonetheless, although CIG languages are quite user-friendly for the guideline acquisition phase, their runtime engines usually do not include support for the automated generation of patient-tailored treatment plans, and even less are they able to incorporate temporal [8,9] and resource constraints in the application of such protocols. As a result, care plans-known as multidisciplinary clinical pathways, or simply care pathways [10]-remain paper-based and limited in their application.…”

Section: Background and Motivationmentioning

confidence: 99%

“…Accuracy in this realm is crucial to ensure that the original clinical protocol is retained in automatically generated care pathways. This subsection shows how the multiple temporal constraints that can be described in Asbru can be represented with HPDL (supported by the formalism of [9]), in order to introduce the translation algorithm later presented in section 4.…”

Section: Analysis Of Temporal Knowledgementioning

confidence: 99%

“…To that end, we employ a high-level formalism developed by Anselma et al [9]. This formalism shares some similarities with Asbru cyclical time annotations and can Listing 2: An abstract cyclical plan for drug administration <plan name='CicloAdministrar'> <arguments> <argument name='drug' s-or-not='set' type='Drug'/> <argument name='dose' s-or-not='set' type='amount'/> <argument name='mindur' s-or-not='scalar' type='time'/> <argument name='maxdur' s-or-not='scalar' type='time'/> <argument name='fromstart' s-or-not='scalar' type='time'/> <argument name='freq' s-or-not='scalar' type='time'/> <argument name='nrep' s-or-not='scalar' type='amount'/> <argument name='partof' s-or-not='set' type='CycleType'/> </arguments> <plan-body> <cyclical-plan> <cyclical-plan-body> <plan-activation>…”

Section: Cyclical Time Annotationsmentioning

confidence: 99%

See 1 more Smart Citation

Automated generation of patient-tailored electronic care pathways by translating computer-interpretable guidelines into hierarchical task networks

González-Ferrer¹,

Teije²,

Fdez-Olivares³

et al. 2013

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objective: This paper describes a methodology which enables computer-aided support for the planning, visualization and execution of personalized patient treatments in a specific healthcare process, taking into account complex temporal constraints and the allocation of institutional resources. To this end, a translation from a time-annotated computerinterpretable guideline (CIG) model of a clinical protocol into a temporal hierarchical task network (HTN) planning domain is presented.Methods and Material: The proposed method uses a knowledge-driven reasoning process to translate knowledge previously described in a CIG into a corresponding HTN Planning and Scheduling domain, taking advantage of HTNs known ability to i) dynamically cope with temporal and resource constraints, and ii) automatically generate customized plans. The proposed method, focusing on the representation of temporal knowledge and based on the identification of workflow and temporal patterns in a CIG, makes it possible to automatically generate time-annotated and resource-based care pathways tailored to the needs of any possible patient profile.Results: The proposed translation is illustrated through a case study based on a 70 pages long clinical protocol to manage Hodgkin's disease, developed by the Spanish Society of Pediatric Oncology. We show that an HTN planning domain can be generated from the corresponding specification of the protocol in the Asbru language, providing a running example of this translation. Furthermore, the correctness of the translation is checked and also the management of ten di↵erent types of temporal patterns represented in the protocol. By interpreting the automatically generated domain with a state-of-art HTN planner, a time-annotated care pathway is automatically obtained, customized for the patient's and institutional needs. The generated care pathway can then be used by clinicians to plan and manage the patients long-term care.Conclusion: The described methodology makes it possible to automatically generate patient-tailored care pathways, leveraging an incremental knowledge-driven engineering process that starts from the expert knowledge of medical professionals. The presented approach makes the most of the strengths inherent in both CIG languages and HTN planning and scheduling techniques: for the former, knowledge acquisition and representation of the original clinical protocol, and for the latter, knowledge reasoning capabilities and an ability to deal with complex temporal and resource constraints. Moreover, the proposed approach provides immediate access to technologies such as business process management (BPM) tools, which are increasingly being used to support healthcare processes.

show abstract

Reasoning and querying bounds on differences with layered preferences

et al. 2021

Self Cite

View full text Add to dashboard Cite

Bounds on differences are widely used in AI to model binary constraints regarding different dimensions, such as time, space, costs, calories, etc. Representing and reasoning with them is an important task in several areas such as knowledge representation, scheduling and planning. Researchers are increasingly focusing on the treatment of fuzzy or probabilistic constraints, to deal with preferences and/or uncertainty. Current approaches to constraints with preferences focus on the evaluation of the optimal (i.e., with highest preference) solutions for the set of constraints and propose a wide range of alternative operators to combine preferences within constraint propagation. However, in decision support tasks, finding a specific (though optimal) solution is not the main goal, but rather it is more important to identify the "space of solutions" (i.e., the minimal network) with their preferences, and to provide users with query answering mechanisms to explore it. We propose the first approach that addresses such a need by (i) supporting user-defined layered scales of preferences (e.g., Low, Medium, High, Very High), (ii) proposing a family of extensions of bounds on differences constraints to deal with such layered preferences, (iii) defining a family of reasoning algorithms to evaluate the minimal network, which is parametric with respect to the basic operations to combine preferences (and the scale of preferences), and (iv) providing suitable query-answering facilities. The properties of the family of approaches are also analyzed.

show abstract

Towards a comprehensive treatment of repetitions, periodicity and temporal constraints in clinical guidelines

Cited by 70 publications

References 30 publications

Modellierung und Verifikation medizinischer Leitlinien

Modellierung und Verifikation medizinischer Leitlinien

Automated generation of patient-tailored electronic care pathways by translating computer-interpretable guidelines into hierarchical task networks

Reasoning and querying bounds on differences with layered preferences

Contact Info

Product

Resources

About