Maria Chiara Pettenati

Personal Knowledge Management Skills in Web 2.0-Based Learning

The full text of the book chapter is not available on the LRA. DOI: 10.4018/978-1-60566-294-7

Heart failure artificial intelligence-based computer aided diagnosis telecare system

In this paper we present an Artificial Intelligence-based Computer Aided Diagnosis system designed to assist the clinical decision of non-specialist staff in the analysis of Heart Failure patients. The system computes the patients pathological condition and highlights possible aggravations. The system is based on three functional parts: Diagnosis (severity assessing), Prognosis, and Follow-up management. Four Artificial Intelligence-based techniques are used and compared in diagnosis function: a Neural Network, a Support Vector Machine, a Decision Tree and a Fuzzy Expert System whose rules are produced by a Genetic Algorithm. In order to offer a complete HF analysis dashboard, state of the art algorithms are implemented to support a score-based prognosis function. The patients Follow-up is used to refine the diagnosis by adding Heart Failure type information and to detect any worsening of patients clinical status. In the Results section we compared the accuracy of the different implemented techniques.

Heart Failure analysis Dashboard for patient's remote monitoring combining multiple artificial intelligence technologies

In this paper we describe an Heart Failure analysis Dashboard that, combined with a handy device for the automatic acquisition of a set of patients clinical parameters, allows to support telemonitoring functions. The Dashboards intelligent core is a Computer Decision Support System designed to assist the clinical decision of non-specialist caring personnel, and it is based on three functional parts: Diagnosis, Prognosis, and Follow-up management. Four Artificial Intelligence-based techniques are compared for providing diagnosis function: a Neural Network, a Support Vector Machine, a Classification Tree and a Fuzzy Expert System whose rules are produced by a Genetic Algorithm. State of the art algorithms are used to support a score-based prognosis function. The patients Follow-up is used to refine the diagnosis.

Design of Collaborative Learning Environments: bridging the gap between CSCL theories and Open Source Platforms

Starting with the assumption that collaborative learning and working will occupy a strategic role in undergraduate, post-graduate and life-long education as well as in collaborative, fl exible and distant working, in this paper we present a refl ection on how to reduce the gap between constructivist and CSCL/W theories and practices, and open source initiatives for e-learning in universities. The main goal, beyond the production of technologies, is to put forward research directions and to stimulate instructional designers to closely work with open source researchers and developers. In this paper we present a synthetic selection of collaborative features that are usually included in CSCL/W environments but are missing in e-learning platforms. Thereafter, we propose the design and implementation of some of the more relevant features in a very well known open source e-learning platform (Moodle). Finally, we discuss the potentialities and critical aspects of Moodle as a possible solution to the need for the dissemination of collaborative learning experiences in Higher Education contexts

Random forest for automatic assessment of heart failure severity in a telemonitoring scenario

In this study, we describe an automatic classifier of patients with Heart Failure designed for a telemonitoring scenario, improving the results obtained in our previous works. Our previous studies showed that the technique that better processes the heart failure typical telemonitoring-parameters is the Classification Tree. We therefore decided to analyze the data with its direct evolution that is the Random Forest algorithm. The results show an improvement both in accuracy and in limiting critical errors.

A Metadata-Based Approach for Unstructured Document Management in Organizations

Effectively managing documents is a strategic requirement for every organization. Available document management systems DMSs often lack effective functions for automatic document management. One reason is that relevant information frequently is conveyed by unstructured documents, whose content cannot be easily accessed and processed by applications. This article proposes a metadata model, the DMSML Document Management and Sharing Markup Language to enable and to ease unstructured document management by supporting the design of DMSs. We argue that the extensive use of this metadata language will render organizational information explicit, promoting information reuse and interoperability in a more profitable way than what is guaranteed by proprietary DMSs. We also briefly depict the design and deployment phases of a Web-based DMS prototype based on DMSML. Our overall intent is to increase the awareness of what managers should account for when considering the possibility of adopting a DMS.

Performance Assessment of a Clinical Decision Support System for Analysis of Heart Failure

In this paper we compare five machine learning techniques in dealing with typical Heart Failure (HF) data. We developed a Clinical Decision Support System (CDSS) for the analysis of Heart Failure patient that provides various outputs such as an HF severity evaluation, an HF type prediction, as well as a management interface that compares the various patient’s follow-ups. To realize these smart functions we used machine learning techniques and in this paper we compare the performance of a neural network, a support vector machine, a system with fuzzy rules genetically produced, a Classification and regression tree and its direct evolution which is the Random Forest, in analyzing our database. Best performances (intended as accuracy and less critical errors committed) in both HF severity evaluation and HF type prediction functions are obtained by using the Random Forest algorithm.

Design of a RESTful Web Information System for Drug Prescription and Administration

Drug prescription and administration processes strongly impact on the occurrence of risks in medical settings for they can be sources of adverse drug events (ADEs). A properly engineered use of information and communication technologies has proven to be a promising approach to reduce these risks. In this study, we propose PHARMA, a web information system which supports healthcare staff in the secure cooperative execution of drug prescription, transcription and registration tasks. PHARMA allows the easy sharing and management of documents containing drug-related information (i.e., drug prescriptions, medical reports, screening), which is often inconsistent and scattered across different information systems and heterogeneous organization domains (e.g., departments, other hospital facilities). PHARMA enables users to access such information in a consistent and secure way, through the adoption of REST and web-oriented design paradigms and protocols. We describe the implementation of the PHARMA prototype, and we discuss the results of the usability evaluation that we carried out with the staff of a hospital in Florence, Italy.

Individual and social needs motivating trust-enabling intermediation services

The aim of this research is to single out individual and social requisites to be addressed in the design and development of trust-enabling systems providing network-based intermediation services.

Designing, producing and exemplifying videos to support reflection and metacognition for in-service teachers training

In this paper we document a six-phase video production process designed to support teachers’ continuous professional development in three disciplinary areas: scientific, linguistic-literary and foreign languages areas. This production has been carried out within the NOP1 - National Operational Programme funded by European structural funds and conducted by INDIRE between 2007 and 2014.The originality of this work lies in the co-research action performed by the team involved (researchers, teachers, instructional designers, video director, etc.) aimed at capturing meaningful professional practices enacted by teachers in their classes for the achievement of a given educational goal. The documented and exemplified production process can, not only function as a guide for the production of educational videos, but is also strongly characterized by its reflective and meta-reflective functions for Teacher Professional Development or TPD. Several examples of videos are described and referenced in the paper.