Cecilia Dias Flores

A multi-agent intelligent environment for medical knowledge

AMPLIA is a multi-agent intelligent learning environment designed to support training of diagnostic reasoning and modelling of domains with complex and uncertain knowledge. AMPLIA focuses on the medical area. It is a system that deals with uncertainty under the Bayesian network approach, where learner-modelling tasks will consist of creating a Bayesian network for a problem the system will present. The construction of a network involves qualitative and quantitative aspects. The qualitative part concerns the network topology, that is, causal relations among the domain variables. After it is ready, the quantitative part is specified. It is composed of the distribution of conditional probability of the variables represented. A negotiation process (managed by an intelligent MediatorAgent) will treat the differences of topology and probability distribution between the model the learner built and the one built-in in the system. That negotiation process occurs between the agents that represent the expert knowledge domain (DomainAgent) and the agent that represents the learner knowledge (LearnerAgent).

A model of pedagogical negotiation

This paper presents a model of pedagogical negotiation developed for the AMPLIA, an Intelligent Probabilistic Multi-agent Learning Environment. Three intelligent software agents: Domain Agent, Learner Agent and Mediator Agent were developed using Bayesian Networks and Influence Diagrams. The goal of the negotiation model is to increase, as much as possible: (a) the performance of the model the students build; (b) the confidence that teachers and tutors have in the students’ ability to diagnose cases; and the students’ confidence on their own ability to diagnose cases; and (c) the students’ confidence on their own ability to diagnose diseases.

Formal analysis of a probabilistic knowledge communication framework

This paper introduces a new formal model, which generalizes current agent communication theories (basically the FIPA version of these theories) to handle probabilistic knowledge communication. Several questions about communication of probabilistic knowledge are discussed in the light of current theories of agent communication and it is argued that exists a semantic gap between these theories and research areas related to probabilistic knowledge representation and communication. This gap creates serious theoretical problems if agents that reason probabilistically try to use communication framework provided by these theories. To diminish this gap it is proposed a modal probabilistic logic and a new communication framework composed of communication principles and acts for probabilistic knowledge communication.

Content's Personalized Recommendation for Implementing Ubiquitous Learning in Health 2.0

This paper proposes a content recommendation mechanism as part of a model for implementing ubiquitous learning for supporting people with chronic diseases who are treated at home, so that they can learn more about treatments for their disease. The proposed approach is supported by the Situated Learning Theory, in which learning takes place based on day-to-day activities and real situations. In this case, the model supports the development of tools that can learn about the users context, based on data obtained via sensors installed on users or in their home, as well as data supplied directly by the user interface of their mobile devices, and data provided by the healthcare team, and, after that, recommend contents about their diseases.

Training Clinical Decision-Making through Simulation

Clinical decision making faces relevant uncertainties, outcomes and trade-offs. It has to deal with diagnosis uncertainties, the choice of diagnostic tests, the selection of prescriptions and procedures, and the treatment follow up, many times facing severe budget limitations and lack of sophisticated equipment. This paper presents a multi-agent learning system for health care practitioners: SimDeCS (Simulation for Decision Making in the Health Care Service). This system relies on simulations of complex clinical cases integrated in a virtual learning environment, and has been developed within a program offering continuous education, training and qualification to professionals in the Brazilian health care service. SimDeCS will be made available on the Internet, thus providing access to professionals working throughout the country. The main contribution is the system architecture and the model knowledge.The learning environment has been designed as a multi-agent system where three intelligent agents are included: Domain Agent, Learner Agent, and Mediator Agent. The knowledge model is implemented by the Domain Agent through probabilistic reasoning, relying on expert human knowledge encoded in Bayesian networks. A clinical case is presented and discussed.

Formal Analysis of the Communication of Probabilistic Knowledge

This paper discusses questions about communication of probabilistic knowledge in the light of current theories of agent communication. It will argue that there is a semantic gap between these theories and research areas related to probabilistic knowledge representation and communication, that creates very serious theoretical problems if agents that reason probabilistically try to use the communication framework provided by these theories. The paper proposes a new formal model, which generalizes current agent communication theories (at least the standard FIPA version of these theories) to handle probabilistic knowledge communication. We propose a new probabilistic logic as the basis for the model and new communication principles and communicative acts to support this kind of communication.

Impact of video game genre on surgical skills development: a feasibility study

BACKGROUND The playing of video games (VGs) was previously shown to improve surgical skills. This is the first randomized, controlled study to assess the impact of VG genre on the development of basic surgical skills. MATERIALS AND METHODS Twenty first-year, surgically inexperienced medical students attended a practical course on surgical knots, suturing, and skin-flap technique. Later, they were randomized into four groups: control and/or nongaming (ContG), first-person-shooter game (ShotG), racing game (RaceG), and surgery game (SurgG). All participants had 3 wk of Nintendo Wii training. Surgical and VG performances were assessed by two independent, blinded surgeons who evaluated basal performance (time 0) and performance after 1 wk (time 1) and 3 wk (time 2) of training. RESULTS The training time of RaceG was longer than that of ShotG and SurgG (P = 0.045). Compared to SurgG and RaceG, VG scores for ShotG improved less between times 0 and 1 (P = 0.010) but more between times 1 and 2 (P = 0.004). Improvement in mean surgical performance scores versus time differed in each VG group (P = 0.011). At time 2, surgical performance scores were significantly higher in ShotG (P = 0.002) and SurgG (P = 0.022) than in ContG. The surgical performance scores of RaceG were not significantly different from the score achieved by ContG (P = 0.279). CONCLUSIONS Different VG genres may differentially impact the development of surgical skills by medical students. More complex games seem to improve performance even if played less. Although further studies are needed, surgery-related VGs with sufficient complexity and playability could be a feasible adjuvant to improving surgical skills.

Influence Diagram for Selection of Pedagogical Strategies in a Multi-Agent System Learning

An Influence Diagram is a simple visual representation of a decision problem that provides an intuitive way to identify and display the essential elements, including decisions, uncertainties, and objectives, and on how they influence each other. This paper discusses its use in the selection of pedagogical strategies in a multi-agent learning system for the health care practitioners: SimDeCS (Simulation for Decision Making in the Health Care Service). A clinical case is also presented and discussed.

An approach for recommending personalized contents for homecare users in the context of health 2.0

This paper proposes a content recommendation mechanism as part of a model for implementing ubiquitous learning for supporting people with chronic diseases who are treated at home, so that they can learn more about treatments for their disease. In the proposed approach, the learning takes place based on day-to-day activities and real situations. In this case, the model supports the development of tools that can learn about the users context, based on data obtained via sensors installed on users or in their home, as well as data supplied directly by the user interface of their mobile devices, and data provided by the healthcare team, and, after that, recommend contents about their diseases.

UM SIMULADOR DE CASOS CLÍNICOS COMPLEXOS NO PROCESSO DE APRENDIZAGEM EM SAÚDE

Este artigo apresenta o projeto SimDeCS, que representa uma importante oportunidade para estabelecer uma nova forma de relacao entre educador e educando, inserindo ferramentas informatizadas na forma de simuladores de casos clinicos complexos no processo de aprendizado. A experiencia tem como objetivo apresentar um processo mais atrativo e proximo das situacoes do mundo real reduzindo as distâncias entre a teoria e a pratica clinica, atraves da utilizacao de simulacoes. O sistema encontra-se em fase de prototipacao, porem os primeiros testes realizados mostraram-se bastante promissores.