Development and implementation of clinical guidelines: An artificial intelligence perspective

Abstract

Clinical Practice Guidelines in paper format are still the preferred form of delivery of medical knowledge and recommendations to healthcare professionals. Their current support and development process have well identified limitations to which the healthcare community has been continuously searching solutions. Artificial Intelligence may create the conditions and provide the tools to address many, if not all, of these limitations.. This paper presents a comprehensive and up to date review of Computer-Interpretable Guideline approaches, namely Arden Syntax, GLIF, PROforma, Asbru, GLARE and SAGE. It also provides an assessment of how well these approaches respond to the challenges posed by paper-based guidelines and addresses topics of Artificial Intelligence that could provide a solution to the shortcomings of clinical guidelines. Among the topics addressed by this paper are Expert Systems, Case-Based Reasoning, Medical Ontologies and Reasoning under Uncertainty, with a special focus on methodologies for assessing Quality of Information when managing incomplete information. Finally, an analysis is made of the fundamental requirements of a guideline model and the importance that standard terminologies and models for clinical data have in the semantic and syntactic interoperability between a 1 Corresponding author 2 guideline execution engine and the software tools used in clinical settings. It is also proposed a line of research that includes the development of an ontology for Clinical Practice Guidelines and a decision model for a guideline-based Expert System that manages non-compliance with clinical guidelines and uncertainty

Treating Colon Cancer Survivability Prediction as a Classification Problem

“…In this way, it will be possible for users to dynamically feed new cases to the prediction system and make it change in order to provide better survival predictions. This type of model could also prove to be very useful when integrated in computer-interpretable guideline systems, such as the one described in (Carneiro et al, 2008;Costa et al, 2011;Lima et al, 2011;Oliveira et al, 2013;Oliveira et al, 2014;Novais et al, 2016), as a way to provide dynamic knowledge to rule-based decision support. Future work also includes the development of conditional survivability models that allow the user to get a prediction knowing that the patient has already survived a number of years after diagnosis and treatment.…”

CompGuide: Acquisition and Editing of Computer-Interpretable Guidelines

“…In the CompGuide model all the knowledge elements of CPGs are represented as different tasks [9]. The classes that enable this are Plan, Action, Question and Decision.…”

“…The present work discloses a CIG editing tool, the CompGuide Editor. The underlying model for CIGs used is the CompGuide ontology [9], which is based on Web Ontology Language (OWL). The CompGuide ontology presents a formalisation of guidelines as linked lists of tasks, thus following the Task Network Model (TNM), representing CPGs as workflows.…”

The Role of Ontologies and Decision Frameworks in Computer-Interpretable Guideline Execution

“…There are other relevant approaches such as PROforma [11] or GUIDE [4]. For an insight on these models and a more detailed overview of CIGs, we urge the reader to consult the works in [26] and [30].…”

“…The versions of CPGs in machine-readable formats are called Computer-Interpretable Guidelines (CIGs) [19,30,26]. The advantages of adopting these machine-readable versions over their document counterparts are related with the increased availability of guidelines at the point and moment of care and reduced ambiguity [6].…”