The development of software tools supporting physicians in the treatment of comorbid patients is a challenging goal and a “hot topic” in medical informatics and artificial intelligence. Computer interpretable guidelines (CIGs) are consolidated tools to support physicians with evidence-based recommendations in the treatment of patients affected by a specific disease. However, the application of two or more CIGs on comorbid patients is critical, since dangerous interactions between actions from different CIGs may arise. GLARE-SSCPM is the first tool supporting, in an integrated way, the knowledge-based detection of interactions, the management of the interactions, and the final “merge” of (part of) the CIGs operating on the patient. GLARE-SSCPM is characterized by being very supportive to physicians, providing them support for focusing, interaction detection, and for a “hypothesize and test” approach to manage the detected interactions. To achieve such goals, it provides advanced artificial intelligence techniques. Preliminary tests in the educational context, within the RoPHS project, have provided encouraging results.

In traditional medical education, learners are mostly trained to diagnose and treat patients through supervised practice. Artificial Intelligence and simulation techniques can complement such an educational practice. In this paper, we present GLARE-Edu, an innovative system in which AI knowledge-based methodologies and simulation are exploited to train learners “how to act” on patients based on the evidence-based best practices provided by clinical practice guidelines. GLARE-Edu is being developed by a multi-disciplinary team involving physicians and AI experts, within the AI-LEAP (LEArning Personalization of AI and with AI) Italian project. GLARE-Edu is domain-independent: it supports the acquisition of clinical guidelines and case studies in a computer format. Based on acquired guidelines (and case studies), it provides a series of educational facilities: (i) navigation, to navigate the structured representation of the guidelines provided by GLARE-Edu, (ii) automated simulation, to show learners how a guideline would suggest to act, step-by-step, on a specific case, and (iii) (self)verification, asking learners how they would treat a case, and comparing step-by-step the learner’s proposal with the suggestions of the proper guideline. In this paper, we describe GLARE-Edu architecture and general features, and we demonstrate our approach through a concrete application to the melanoma guideline and we propose a preliminary evaluation.

The rationalization of the healthcare processes and organizations is a task of fundamental importance to grant both the quality and the standardization of healthcare services, and the minimization of costs. Clinical Practice Guidelines (CPGs) are one of the major tools that have been introduced to achieve such a challenging task. CPGs are widely used to provide decision support to physicians, supplying them with evidence-based predictive and prescriptive information about patients’ status and treatments, but usually on individual pathologies. This sets up the urgent need for developing decision support methodologies to assist physicians and healthcare managers in the detection of interactions between guidelines, to help them to devise appropriate patterns of treatment for comorbid patients (i.e., patients affected by multiple diseases).

Now-related temporal data play an important role in many applications. Clifford et al.'s approach is a milestone to model the semantics of `now' in temporal relational databases. Several relational representation models for now-related data have been presented; however, the semantics of such representations has not been explicitly studied. Additionally, the definition of a relational algebra to query now-related data is an open problem. We propose the first integrated approach that provides both a neat semantics for now-related data and a compact 1NF representation (data model and relational algebra) for them. Additionally, our approach also extends current approaches to consider (i) domains where it is not always possible to know when changes in the world are recorded in the database and (ii) now-related data with a bound on their persistency in the future. To do so, we explicitly model the notion of temporal indeterminacy in the future for now-related data. The properties of our approach are also analyzed both from a theoretical (semantic correctness and reducibility of the algebra) and from an experimental point of view. Experiments show that, despite the fact that our approach is a major extension to current temporal relational approaches, no significant overhead is added to deal with `now'.

The SCITEPRESS Digital Library offers online access to all papers presented at INSTICC conferences, as well as a few conferences organized by others.