Luca Piovesan

An ontological knowledge and multiple abstraction level decision support system in healthcare

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).We identify different levels of abstractions in the analysis of interactions, based on both the hierarchical organization of clinical guidelines (in which composite actions are refined into their components) and the hierarchy of drug categories. We then propose a general methodology (data/knowledge structures and reasoning algorithms operating on them) supporting user-driven and flexible interaction detection over the multiple levels of abstraction. Finally, we discuss the impact of the adoption of computerized clinical guidelines in general, and of our methodology in particular, for patients (quality of the received healthcare services), physicians (decision support and quality of provided services), and healthcare managers and organizations (quality and optimization of provided services).

Temporal detection and analysis of guideline interactions

BACKGROUND Clinical practice guidelines (CPGs) are assuming a major role in the medical area, to grant the quality of medical assistance, supporting physicians with evidence-based information of interventions in the treatment of single pathologies. The treatment of patients affected by multiple diseases (comorbid patients) is one of the main challenges for the modern healthcare. It requires the development of new methodologies, supporting physicians in the treatment of interactions between CPGs. Several approaches have started to face such a challenging problem. However, they suffer from a substantial limitation: they do not take into account the temporal dimension. Indeed, practically speaking, interactions occur in time. For instance, the effects of two actions taken from different guidelines may potentially conflict, but practical conflicts happen only if the times of execution of such actions are such that their effects overlap in time. OBJECTIVES We aim at devising a methodology to detect and analyse interactions between CPGs that considers the temporal dimension. METHODS In this paper, we first extend our previous ontological model to deal with the fact that actions, goals, effects and interactions occur in time, and to model both qualitative and quantitative temporal constraints between them. Then, we identify different application scenarios, and, for each of them, we propose different types of facilities for user physicians, useful to support the temporal detection of interactions. RESULTS We provide a modular approach in which different Artificial Intelligence temporal reasoning techniques, based on temporal constraint propagation, are widely exploited to provide users with such facilities. We applied our methodology to two cases of comorbidities, using simplified versions of CPGs. CONCLUSION We propose an innovative approach to the detection and analysis of interactions between CPGs considering different sources of temporal information (CPGs, ontological knowledge and execution logs), which is the first one in the literature that takes into account the temporal issues, and accounts for different application scenarios.

A 1NF temporal relational model and algebra coping with valid-time temporal indeterminacy

In the real world, many phenomena are time related and in the last three decades the database community has devoted much work in dealing with “time of facts” in databases. While many approaches incorporating time in the relational model have been already devised, most of them assume that the exact time of facts is known. However, this assumption does not hold in many practical domains, in which temporal indeterminacy of facts occurs. The treatment of valid-time indeterminacy requires in-depth extensions to the current relational approaches. In this paper, we propose a theoretically grounded approach to cope with this issue, overcoming the limitations of related approaches in the literature. In particular, we present a 1NF temporal relational model and propose a new temporal relational algebra to query it. We also formally study the properties of the new data model and algebra, thus granting that our approach is interoperable with pre-existent temporal and non-temporal relational approaches, and is implementable on top of them. Finally, we consider computational complexity, showing that only a limited overhead is added when moving from determinate to indeterminate time.

A General Approach to Represent and Query Now-Relative Medical Data in Relational Databases

Now-related temporal data play an important role in the medical context. Current relational temporal database (TDB) approaches are limited since (i) they (implicitly) assume that the span of time occurring between the time when facts change in the world and the time when the changes are recorded in the database is exactly known, and (ii) do not explicitly provide an extended relational algebra to query now-related data. We propose an approach that, widely adopting AI symbolic manipulation techniques, overcomes the above limitations.

Adopting STP for Diet Management

We devise a scenario the interaction between the man and the food is mediated by an intelligent recommendation system that, on the basis of various factors, encourages (or discourages) the user to eat a specific course. The main factors that the system need to account for are (1) the diet that the user intends to follow, (2) the food that s/he has eaten in the last days or that s/he intends to eat in the next days, and (3) the nutritional values of the courses and their specific recipes. Automatic reasoning and Natural Language Generation (NLG) play a fundamental role in this project: the compatibility of a food with a diet is formalized as a Simple Temporal Problem (STP), while the NLG tries to motivate the user. In this paper we briefly sketch the formalization and the related reasoning facilities that we intend to devise.

Temporal Conformance Analysis and Explanation on Comorbid Patients.

The treatment of comorbid patients is one of the main challenges of modern health care, and many Medical Informatics approaches have been devoted to it in the last years. In this paper, we propose the first approach in the literature that analyses the conformance of execution traces with multiple Computer-Interpretable Guidelines (CIGs), as needed in the treatment of comorbid patients. This is a fundamental task, to support physicians in an a-posteriori analysis of the treatments that have been provided. Notably, the conformance problem is very complex in this context, since CIGs may have negative interactions, so that in specific circumstances full conformance to individual CIGs may be dangerous for patients. We thus complement our conformance analysis with an explanation approach, aimed at justifying deviations in case they can be explained in terms of interaction management, e.g., some possible undesired interaction has been avoided. Our approach is based on Answer Set Programming, and, to face realistic problems, devotes specific attention to the temporal dimension.

Managing Temporal Constraints with Preferences: Representation, Reasoning, and Querying

Representing and managing temporal knowledge, in the form of temporal constraints, is a crucial task in many areas, including knowledge representation, planning, and scheduling. The current literature in the area is moving from the treatment of “crisp” temporal constraints to fuzzy or probabilistic constraints, to account for preferences and\or uncertainty. Given a set of temporal constraints, the evaluation of the <italic>tightest</italic> implied constraints is a fundamental task, which is essential also to provide <italic>reliable query-answering facilities</italic>. However, while such tasks have been widely addressed for “crisp” temporal constraints, they have not attracted enough attention in the “non-crisp” context yet. We overcome such a limitation, by (i) extending quantitative temporal constraints to cope with <italic>preferences</italic>, (ii) defining a <italic>temporal reasoning algorithm</italic> which evaluates the <italic>tightest</italic> temporal constraints, and (iii) providing suitable <italic>query-answering facilities</italic> based on it.

A General Framework for the Distributed Management of Exceptions and Comorbidities.

In the last decades, many different computer-assisted management systems for Computer Interpretable Guidelines (CIGs) have been developed. While CIGs propose a “standard” evidence-based treatments of “typical” patients, exceptions may arise, as well the need to cope with comorbidities. The treatment of deviation from “standard” execution has attracted a lot of attention in the recent literature, but the approaches proposed are focused on the treatment either of exceptions or of comorbities. However, this is a clear limitation, since during a CIG execution, both these issues can occur. In this paper, we propose the first approach which supports the integrated treatment of both exceptions and comorbidities. To achieve such a goal, we propose a modular client-server architecture supporting the concurrent execution of multiple guidelines. The architecture proposed has been designed as a further layer building upon “traditional” execution engines for a single CIG. Thus, our methodology is general and can be used to extend the CIG systems in the literature. Finally, we describe our approach in action on a case study, in which a comorbid patient is treated for Peptic Ulcer and for deep Venous Thrombosis and, during the treatment, she manifests a heart failure.

Supporting Multiple Agents in the Execution of Clinical Guidelines.

Clinical guidelines (GLs) exploit evidence-based medicine to enhance the quality of patient care, and to optimize it. To achieve such goals, in many GLs different agents have to interact and cooperate in an effective way. In many cases (e.g. in chronic disorders) the GLs recommend that the treatment is not performed/completed in the hospital, but is continued in different contexts (e.g. at home, or in the general practitioner’s ambulatory), under the responsibility of different agents. Delegation of responsibility between agents is also important, as well as the possibility, for a responsible, to select the executor of an action (e.g., a physician main retain the responsibility of an action, but delegate to a nurse its execution). To manage such phenomena, proper support to agent interaction and communication must be provided, providing them with facilities for (1) treatment continuity (2) contextualization, (3) responsibility assignment and delegation (4) check of agent “appropriateness”. In this paper we extend GLARE, a computerized GL management system, to support such needs. We illustrate our approach by means of a practical case study.

ASP for Conformance Analysis and Explanation of Clinical Guidelines Execution

In this paper, we present an approach where Answer Set Programming is used for analyzing the conformance of execution traces, describing the treatment of individual patients, to Computer-Interpretable Guidelines (CIGs) in the medical domain. The problem is challenging because the CIG for a given pathology describes the most typical treatments for that pathology and cannot take into account all the specific cases that may occur for a specific patient, being them contraindications, temporary conditions of the patient, or other major pathologies. Deviations (also in the timing) from a single guideline may then be explainable using general medical knowledge or knowledge about the interaction between pathologies or treatments.