Stefania Rubrichi

A system for the extraction and representation of summary of product characteristics content

OBJECTIVE Information about medications is critical in supporting decision-making during the prescription process and thus in improving the safety and quality of care. In this work, we propose a methodology for the automatic recognition of drug-related entities (active ingredient, interaction effects, etc.) in textual drug descriptions, and their further location in a previously developed domain ontology. METHODS AND MATERIAL The summary of product characteristics (SPC) represents the basis of information for health professionals on how to use medicines. However, this information is locked in free-text and, as such, cannot be actively accessed and elaborated by computerized applications. Our approach exploits a combination of machine learning and rule-based methods. It consists of two stages. Initially it learns to classify this information in a structured prediction framework, relying on conditional random fields. The classifier is trained and evaluated using a corpus of about a hundred SPCs. They have been hand-annotated with different semantic labels that have been derived from the domain ontology. At a second stage the extracted entities are added in the domain ontology corresponding concepts as new instances, using a set of rules manually-constructed from the corpus. RESULTS Our evaluations show that the extraction module exhibits high overall performance, with an average F1-measure of 88% for contraindications and 90% for interactions. CONCLUSION SPCs can be exploited to provide structured information for computer-based decision support systems.

Graphical Representation of Life Paths to Better Convey Results of Decision Models to Patients

The inclusion of patients’ perspectives in clinical practice has become an important matter for health professionals, in view of the increasing attention to patient-centered care. In this regard, this report illustrates a method for developing a visual aid that supports the physician in the process of informing patients about a critical decisional problem. In particular, we focused on interpretation of the results of decision trees embedding Markov models implemented with the commercial tool TreeAge Pro. Starting from patient-level simulations and exploiting some advanced functionalities of TreeAge Pro, we combined results to produce a novel graphical output that represents the distributions of outcomes over the lifetime for the different decision options, thus becoming a more informative decision support in a context of shared decision making. The training example used to illustrate the method is a decision tree for thromboembolism risk prevention in patients with nonvalvular atrial fibrillation.

From Decision to Shared-Decision: Introducing Patients’ Preferences in Clinical Decision Analysis - A Case Study in Thromboembolic Risk Prevention

In the context of the EU project MobiGuide, the development of a patient-centric decision support system based on clinical guidelines is the main focus. The project is addressed to patients with chronic illnesses, including atrial fibrillation (AF). In this paper we describe a shared-decision model framework to address those situations, described in the guideline, where the lack of hard evidence makes it important for the care provider to share the decision with the patient and/or his relatives. To illustrate this subject we focus on an important subject tackled in the AF guideline: thromboembolic risk prevention. We introduce a utility model and a cost model to collect patient’s preferences. On the basis of these preferences and of literature data, a decision model is implemented to compare different therapeutic options. The development of this framework increases the involvement of patients in the process of care focusing on the centrality of individual subjects.

UceWeb: a Web-based Collaborative Tool for Collecting and Sharing Quality of Life Data

OBJECTIVES This work aims at building a platform where quality-of-life data, namely utility coefficients, can be elicited not only for immediate use, but also systematically stored together with patient profiles to build a public repository to be further exploited in studies on specific target populations (e.g. cost/utility analyses). METHODS We capitalized on utility theory and previous experience to define a set of desirable features such a tool should show to facilitate sound elicitation of quality of life. A set of visualization tools and algorithms has been developed to this purpose. To make it easily accessible for potential users, the software has been designed as a web application. A pilot validation study has been performed on 20 atrial fibrillation patients. RESULTS A collaborative platform, UceWeb, has been developed and tested. It implements the standard gamble, time trade-off and rating-scale utility elicitation methods. It allows doctors and patients to choose the mode of interaction to maximize patients’ comfort in answering difficult questions. Every utility elicitation may contribute to the growth of the repository. CONCLUSION UceWeb can become a unique source of data allowing researchers both to perform more reliable comparisons among healthcare interventions and build statistical models to gain deeper insight into quality of life data.

META-GLARE: A Meta-System for Defining Your Own CIG System: Architecture and Acquisition

Clinical practice guidelines (CPGs) play an important role in medical practice, and computerized support to CPGs is now one of the most central areas of research in Artificial Intelligence in medicine. In recent years, many groups have developed different computer-assisted management systems of Computer Interpretable Guidelines (CIGs). From one side, there are several commonalities between different approaches; from the other side, each approach has its own peculiarities and is geared towards the treatment of specific phenomena. In our work, we propose a form of generalization: instead of defining “yet another CIG system”, we propose a META-GLARE, a “meta”-system (or, in other words, a shell) to define new CIG systems. From one side, we try to capture the commonalities, by providing (i) a general tool for the acquisition, consultation and execution of hierarchical directed graphs (representing the control flow of actions in CIGs), parameterized over the types of nodes and of arcs constituting it, and (ii) a library of different elementary components of guidelines nodes (actions) and arcs, in which each type definition involves the specification of how objects of this type can be acquired, consulted and executed. From the other side, we provide generality and flexibility, by allowing free aggregations of such elementary components to define new primitive node and arc types. In this paper, we first propose META-GLARE general architecture and then, for the sake of brevity, we will focus only on the acquisition issue.

Extracting information from summary of product characteristics for improving drugs prescription safety

Information about medications is critical in supporting decision-making during the prescription process and thus in improving the safety and quality of care. The Summary of Product Characteristics (SPC) represents the basis of information for health professionals on how to use medicines. However, this information is locked in free-text and, as such, cannot be actively accessed and elaborated by computerized applications. In this work, we propose a machine learning based system for the automatic recognition of drug-related entities (active ingredient, interaction effects, etc.) in SPCs, focusing on drug interactions. Our approach learns to classify this information in a structured prediction framework, relying on conditional random fields. The classifier is trained and evaluated using a corpus of a hundred SPCs. They have been hand-annotated with thirteen semantic labels that have been derived from a previously developed domain ontology. Our evaluations show that the model exhibits high overall performance, with an average F1-measure of about 90%.