A Learning Algorithm for Multimodal Grammar Inference.

The high costs of development and maintenance of multimodal grammars in integrating and understanding input in multimodal interfaces lead to the investigation of novel algorithmic solutions in automating grammar generation and in updating processes. Many algorithms for context-free grammar inference have been developed in the natural language processing literature. An extension of these algorithms toward the inference of multimodal grammars is necessary for multimodal input processing. In this paper, we propose a novel grammar inference mechanism that allows us to learn a multimodal grammar from its positive samples of multimodal sentences. The algorithm first generates the multimodal grammar that is able to parse the positive samples of sentences and, afterward, makes use of two learning operators and the minimum description length metrics in improving the grammar description and in avoiding the over-generalization problem. The experimental results highlight the acceptable performances of the algorithm proposed in this paper since it has a very high probability of parsing valid sentences.

Is workflow technology suitable to represent and manage clinical trials?

The clinical trial has to be rigidly followed because it identifies a uniform clinical behaviour, which has to be adopted by the different physicians carrying out the test. The life cycle of the clinical trial is therefore based on a planning and definition phase, a next experimental phase connected with its diffusion to the involved centres and finally an evaluation phase of the results. An information system, which supports the users in the different phases of the clinical trial life cycle, has to take into account the different characteristics of each phase. The aim of this paper is to illustrate the role of WF technology as a component of an information system which supports the life cycle of a clinical trial also on the basis of the experience of the Italian Group for Haematological Disease of Adults (GIMEMA).

A system for the description of healthcare guidelines.

Contained costs and quality of treatment are two elements which have to be considered when planning and controlling both clinical and managerial activities of healthcare structures (HCSs). Each structure has to be marked by a high level of quality of treatment and by specific professional competencies and skills of its operators. It is therefore fundamental to provide a system which supports the management of processes and of guidelines which characterise an healthcare structure. In this paper we present a system able to describe processes of an HCS and in particular clinical guidelines. This system is based on a workflow conceptual model, able to represent clinical and managerial activities carried out in HCSs (the Atreus model).

A conceptual representation of clinical and managerial guidelines: the ATREUS workflow model.

In this paper we propose a workflow conceptual model able to represent clinical and managerial activities within healthcare structures, the ATREUS model. This model uses: a) a graphical representation which models the activities and the events that activate them; b) a textual representation of information related to: a set of conditions used for the control of activity execution; the actors who undertake the activity; the resources and tools necessary for its enactment, the clinical and managerial data generated by the activity execution; c) a state diagram which allows the control of the activity execution. The model allows modularity, activity nesting and temporal flexibility using a top-down refinement of processes. This model, unlike others, makes it possible to highlight the different types of decision involved in the performance of an activity.

Modeling the management of protocols as the kernel of a healthcare information system.

A conceptual model of a health care structure is described. The management of protocols viewed as structured, flexible, and coherent descriptions of activities aimed to solve specific problems in the system is the kernel of the model. A global approach to the protocols is proposed. Each protocol is modeled from two points of view: the nature of the actions (clinical, administrative, programming, and control) and the life cycle of protocols (theoretical, customized, and performed). In our approach the patient folder not only records information about the patient, but also contains and controls the execution of the protocols planned to be performed on the patient. As a consequence, all aspects related to protocol execution are chronologically reported in the folder in a federated manner. In this way the patient folder becomes a complex, multifaceted object, able to capture all information needed to evaluate the patient evolution in a given period.

ADAMS: Aggregate Data Management System for epidemiologists and health-care managers.

An effective health-care policy is supported by the availability of data in the form of statistical tables for epidemiologists and health-care managers. Creation, analysis and exploitation of these data strongly support the monitoring of trends in mortality and morbidity phenomena and the evaluation of offered health services. This might imply the transformation of statistical tables to more suitable formats. A successful management, manipulation and querying of a statistical table is a complex activity requiring a considerable knowledge of statistical problems. Computerised support can be precious in this task and this led to the development of several data management systems. In this paper we sketch out the features of ADAMS (Aggregate Data Management System), a system conceived to allow an easy interaction with statistical tables, reshaping and browsing of their descriptive part. ADAMS aims at simplifying the problem of extracting information from a statistical database and performing statistical table manipulation. The following functionalities are provided: definition of a statistical database at descriptive level; storage of data in the database; manipulation of data according to the summarisation and reclassification operators; browsing between data and their descriptive part. It also supports different manipulation styles according to different user profiles.