Genetic algorithms for the non emergency patients transport service

The authors would like to thank the anonymous reviewers for their valuable comments and suggestions to improve the paper. The authors would like to thank Dr. Elaine DeBock for reviewing the manuscript.

Information systems assessment in pathologic anatomy service

Information technologies changed the way of how the health organizations work, contributing to their effectiveness, efficiency and sustainability. Hospital Information Systems (HIS) are emerging on all of health institutions, helping health professionals and patients. However, HIS are not always implemented and used in the best way, leading to low levels of benefits and acceptance by users of these systems. In order to mitigate this problem, it is essential to take measures able to ensure if the HIS and their interfaces are designed in a simple and interactive way. With this in mind, a study to measure the user satisfaction and their opinion was made. It was applied the Technology Acceptance Model (TAM) on a HIS implemented on various hospital centers (AIDA), being used the Pathologic Anatomy Service. The study identified weakness and strengths features of AIDA and it pointed some solutions to improve the medical record.

OPM3® Portugal project: information systems and technologies organizations: outcome analysis

Increasing the maturity in Project Management (PM) has become a goal for many organizations, leading them to adopt maturity models to assess the current state of its PM practices and compare them with the best practices in the industry where the organization is inserted. One of the main PM maturity models is the Organizational Project Management Maturity Model (OPM3®), developed by the Project Management Institute. This paper presents the Information Systems and Technologies organizations outcome analysis, of the assesses made by the OPM3® Portugal Project, identifying the PM processes that are “best” implemented in this particular industry and those in which it is urgent to improve. Additionally, a comparison between the different organizations’ size analyzed is presented.

Vehicle-to-anything application (v2anything app) for electric vehicles

This paper presents a mobile information system denominated as Vehicle-to-Anything Application (V2Anything App), and explains its conceptual aspects. This application is aimed at giving relevant information to Full Electric Vehicle (FEV) drivers, by supporting the integration of several sources of data in a mobile application, thus contributing to the deployment of the electric mobility process. The V2Anything App provides recommendations to the drivers about the FEV range autonomy, location of battery charging stations, information of the electricity market, and also a route planner taking into account public transportations and car or bike sharing systems. The main contributions of this application are related with the creation of an Information and Communication Technology (ICT) platform, recommender systems, data integration systems, driver profile, and personalized range prediction. Thus, it is possible to deliver relevant information to the FEV drivers related with the electric mobility process, electricity market, public transportation, and the FEV performance.

Non emergency patients transport - a mixed integer linear programming

This work presents a model and a heuristic to solve the non-emergency patients transport (NEPT) service issues given the new rules recently established in Portugal. The model follows the same principle of the Team Orienteering Problem by selecting the patients to be included in the routes attending the maximum reduction in costs when compared with individual transportation. This model establishes the best sets of patients to be transported together. The model was implemented in AMPL and a compact formulation was solved using NEOS Server. A heuristic procedure based on iteratively solving problems with one vehicle was presented, and this heuristic provides good results in terms of accuracy and computation time.

The non-emergency patient transport modelled as a team orienteering problem

This work presents an improved model to solve the non-emergency patients transport (NEPT) service issues given the new rules recently established in Portugal. The model follows the same principle of the Team Orienteering Problem by selecting the patients to be included in the routes attending the maximum reduction in costs when compared with individual transportation. This model establishes the best sets of patients to be transported together. The model was implemented in AMPL and a compact formulation was solved using NEOS Server. A heuristic procedure based on iteratively solving Orienteering Problems is presented, and this heuristic provides good results in terms of accuracy and computation time. Euclidean instances as well as asymmetric real data gathered from Google maps were used, and the model has a promising performance mainly with asymmetric cost matrices.

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Development of an intelligent earthwork optimization system

Tese de Doutoramento em Engenharia Civil.

Optimization techniques to detect early ventilation extubation in intensive care units

The decision support models in intensive care units are developed to support medical staff in their decision making process. However, the optimization of these models is particularly difficult to apply due to dynamic, complex and multidisciplinary nature. Thus, there is a constant research and development of new algorithms capable of extracting knowledge from large volumes of data, in order to obtain better predictive results than the current algorithms. To test the optimization techniques a case study with real data provided by INTCare project was explored. This data is concerning to extubation cases. In this dataset, several models like Evolutionary Fuzzy Rule Learning, Lazy Learning, Decision Trees and many others were analysed in order to detect early extubation. The hydrids Decision Trees Genetic Algorithm, Supervised Classifier System and KNNAdaptive obtained the most accurate rate 93.2%, 93.1%, 92.97% respectively, thus showing their feasibility to work in a real environment.

Design of a case-based reasoner for information security in military organizations

Information security is concerned with the protection of information, which can be stored, processed or transmitted within critical information systems of the organizations, against loss of confidentiality, integrity or availability. Protection measures to prevent these problems result through the implementation of controls at several dimensions: technical, administrative or physical. A vital objective for military organizations is to ensure superiority in contexts of information warfare and competitive intelligence. Therefore, the problem of information security in military organizations has been a topic of intensive work at both national and transnational levels, and extensive conceptual and standardization work is being produced. A current effort is therefore to develop automated decision support systems to assist military decision makers, at different levels in the command chain, to provide suitable control measures that can effectively deal with potential attacks and, at the same time, prevent, detect and contain vulnerabilities targeted at their information systems. The concept and processes of the Case-Based Reasoning (CBR) methodology outstandingly resembles classical military processes and doctrine, in particular the analysis of “lessons learned” and definition of “modes of action”. Therefore, the present paper addresses the modeling and design of a CBR system with two key objectives: to support an effective response in context of information security for military organizations; to allow for scenario planning and analysis for training and auditing processes.

Adoção e difusão de aplicações das tecnologias da informação: iniciativas lançadas no âmbito de processos de implantação de aplicações em organizações – estudo de práticas profissionais e proposta de ferramenta de suporte

Tese de Doutoramento Tecnologias e Sistemas de Informação

Desenvolvimento e actualização do controlo de um equipamento de prototipagem rápida

Dissertação de mestrado integrado em Engenharia Mecânica

Implementação de um sistema de customer relationship management na broaden information solutions

Dissertação de mestrado em Sistemas de Informação

Abordagem histórica e institucional da mudança em contabilidade de gestão: o caso da normalização nos hospitais públicos portugueses

A teoria institucional constituiu o enquadramento no qual foi suportada a pergunta geral desta investigação: como e porquê a Normalização da Contabilidade de Gestão (NCG) nos hospitais públicos portugueses surgiu e evoluiu? O objetivo geral foi compreender de forma profunda o surgimento e a mudança nas regras de NCG dos hospitais públicos portugueses no período histórico 1954-2011. Face ao enquadramento institucional que justificou uma investigação interpretativa, foi usado como método de investigação um estudo de caso explanatório. A evidência sobre o caso da NCG nos hospitais públicos portugueses foi recolhida em documentos e através de 58 entrevistas realizadas em 47 unidades de análise (nos serviços centrais de contabilidade do Ministério da Saúde e em 46 hospitais públicos, num total de 53 existentes). Quanto aos principais resultados obtidos, no período 1954-1974, as regras criadas pelo poder político para controlo dos gastos públicos e a contabilidade orçamental de base de caixa estiveram na génese dos primeiros conceitos de Contabilidade de Gestão (CG) para os serviços públicos de saúde portugueses. A transição de um regime ditatorial para um regime democrático (25 de Abril de 1974), a criação do Plano Oficial de Contabilidade (POC/77) e a implementação de um estado social com Serviço Nacional de Saúde (SNS) criaram a conjuntura crítica necessária para o surgimento de um Plano Oficial de Contabilidade para os Serviços de Saúde (POCSS/80) que incluiu regras de CG. A primeira edição do Plano de Contabilidade Analítica dos Hospitais (PCAH), aprovada em 1996, não foi uma construção de raiz, mas antes uma adaptação para os hospitais das regras de CG incluídas no POCSS/91 que havia revisto o POCSS/80. Após o início da implementação do PCAH, em 1998, ocorreram sequências de autorreforço institucionalizadoras destas normas, no período 1998-2011, por influência de pressões isomórficas coercivas que delinearam um processo de evolução incremental cujo resultado foi uma reprodução por adaptação, num contexto de dependência de recursos. Vários agentes internos e externos pressionaram, no período 2003-2011, através de sequências reativas para a desinstitucionalização do PCAH em resposta ao persistente fenómeno de loose coupling. Mas o PCAH só foi descontinuado nos hospitais com privatização da governação e rejeição dos anteriores sistemas de informação. Ao nível da extensão da teoria, este estudo de caso adotou o institucionalismo histórico na investigação em CG, quanto se sabe pela primeira vez, que se mostra útil na interpretação dos processos e dos resultados da criação e evolução de instituições de CG num determinado contexto histórico. Na condição de dependência de recursos, as sequências de autorreforço, via isomorfismo coercivo, tendem para uma institucionalização com fenómeno de loose coupling. Como resposta a este fenómeno, ocorrem sequências reativas no sentido da desinstitucionalização. Perante as pressões (políticas, funcionais, sociais e tecnológicas) desinstitucionalizadoras, o fator governação privada acelera o processo de desinstitucionalização, enquanto o fator governação pública impede ou abranda esse processo.

Predicting triage waiting time in maternity emergency care by means of data mining

Healthcare organizations often benefit from information technologies as well as embedded decision support systems, which improve the quality of services and help preventing complications and adverse events. In Centro Materno Infantil do Norte (CMIN), the maternal and perinatal care unit of Centro Hospitalar of Oporto (CHP), an intelligent pre-triage system is implemented, aiming to prioritize patients in need of gynaecology and obstetrics care in two classes: urgent and consultation. The system is designed to evade emergency problems such as incorrect triage outcomes and extensive triage waiting times. The current study intends to improve the triage system, and therefore, optimize the patient workflow through the emergency room, by predicting the triage waiting time comprised between the patient triage and their medical admission. For this purpose, data mining (DM) techniques are induced in selected information provided by the information technologies implemented in CMIN. The DM models achieved accuracy values of approximately 94% with a five range target distribution, which not only allow obtaining confident prediction models, but also identify the variables that stand as direct inducers to the triage waiting times.