Implementação de alertas de interações medicamentosas na construção de uma farmácia online

Os sistemas de apoio à decisão clinica têm-se revelado essenciais no dia-a-dia da população, nomeadamente dos profissionais e dos pacientes. Estes sistemas podem ser aplicados com diferentes objetivos: como sistemas de alerta; de prevenção de doenças; sistemas para dosagem de medicação e prescrição; entre outras. Atualmente é notório o aumento de interesse por parte da população em entender e em possuir um papel ativo nas decisões médicas. Para conseguirem fazê-lo necessitam de procurar informação. O meio mais utilizado para obter essa informação é a internet, onde a informação se encontra em grande quantidade e muito dispersa. Para além da quantidade é imprescindível encontrar informação credível, para que não haja indução da pessoa em erro. Para ajudar a solucionar estes problemas surgiram os sistemas de recomendação na saúde. Estes sistemas foram idealizados para fornecer informações às quais os utilizadores podem recorrer para tomar decisões conscientes e seguras sobre a sua saúde. Também os sistemas de alerta se têm revelado importantes na área da saúde. Estes sistemas podem ser usados em diferentes contextos e sobre diferentes assuntos, como por exemplo, a alteração do estado clínico de um paciente monitorizado, em tempo real, ou em interações medicamentosas. As interações medicamentosas podem advir da automedicação do utente ou da larga quantidade de medicação que, a partir de determinada idade, os utentes ingerem. Pode ter como causa medicação que administrem regularmente, ou até mesmo diariamente, ou doenças/estados que o utente possua que, em simultâneo com determinada medicação pode causar reações adversas. Neste trabalho foi desenvolvido um protótipo de uma farmácia online (FoAM) que fornece, ao utilizador, alertas quando há possibilidade de interações. As causas de interações consideradas foram os medicamentos que o utilizador consuma e/ou doenças/estados que possua. O objetivo é alertar para o caso das causas que o utilizador possui interagirem com o(s) medicamento(s) que este deseja adquirir. Para alcançar esse objetivo foi necessário selecionar os medicamentos a disponibilizar assim como as suas interações. Essa seleção foi baseada no prontuário terapêutico 2013 disponibilizado pelo INFARMED. Depois de recolhida e analisada a informação, foi possível compreender que informações clínicas o sistema necessita para que consiga identificar os medicamentos que não são aconselháveis adquirir. Para isso, é necessário que o utilizador forneça essas informações clínicas pessoais, necessidade que vai de encontro à posição defendida por diversos autores que apontam o uso de registos eletrónicos de saúde muito benéfico para conseguir alertas mais personalizados suprindo assim as necessidades do utilizador. É também preponderante que o utilizador perceba o porquê de determinado medicamento não ser aconselhável, por isso, ao ser emitido o alerta é também apresentada a justificação do mesmo, ou seja, é disponibilizado ao utilizador qual a causa que indicou no formulário responsável pela interação.

Formal Contracts for Runtime Verification Support in the Ada Programming Language

Poster presented in The 28th GI/ITG International Conference on Architecture of Computing Systems (ARCS 2015). 24 to 26, Mar, 2015. Porto, Portugal.

Architecture to Support Quality of Service in Arrowhead Systems

Presented at INForum - Simpósio de Informática (INFORUM 2015). 7 to 8, Sep, 2015. Covilhã, Portugal.

Real-Time Support in the Proposal for Fine-Grained Parallelism in Ada

Presented at Work in Progress Session, IEEE Real-Time Systems Symposium (RTSS 2015). 1 to 3, Dec, 2015. San Antonio, U.S.A..

Real-Time Support in the Proposal for Fine-Grained Parallelism in Ada

Presented at Work in Progress Session, IEEE Real-Time Systems Symposium (RTSS 2015). 1 to 3, Dec, 2015. San Antonio, U.S.A..

A Clinical Support System Based on Quality of Life Estimation

Quality of life is a concept influenced by social, economic, psychological, spiritual or medical state factors. More specifically, the perceived quality of an individual's daily life is an assessment of their well-being or lack of it. In this context, information technologies may help on the management of services for healthcare of chronic patients such as estimating the patient quality of life and helping the medical staff to take appropriate measures to increase each patient quality of life. This paper describes a Quality of Life estimation system developed using information technologies and the application of data mining algorithms to access the information of clinical data of patients with cancer from Otorhinolaryngology and Head and Neck services of an oncology institution. The system was evaluated with a sample composed of 3013 patients. The results achieved show that there are variables that may be significant predictors for the Quality of Life of the patient: years of smoking (p value 0.049) and size of the tumor (p value < 0.001). In order to assign the variables to the classification of the quality of life the best accuracy was obtained by applying the John Platt's sequential minimal optimization algorithm for training a support vector classifier. In conclusion data mining techniques allow having access to patients additional information helping the physicians to be able to know the quality of life and produce a well-informed clinical decision.

Decision Support for Energy Contracts Negotiation with Game Theory and Adaptive Learning

This paper presents a decision support methodology for electricity market players’ bilateral contract negotiations. The proposed model is based on the application of game theory, using artificial intelligence to enhance decision support method’s adaptive features. This model is integrated in AiD-EM (Adaptive Decision Support for Electricity Markets Negotiations), a multi-agent system that provides electricity market players with strategic behavior capabilities to improve their outcomes from energy contracts’ negotiations. Although a diversity of tools that enable the study and simulation of electricity markets has emerged during the past few years, these are mostly directed to the analysis of market models and power systems’ technical constraints, making them suitable tools to support decisions of market operators and regulators. However, the equally important support of market negotiating players’ decisions is being highly neglected. The proposed model contributes to overcome the existing gap concerning effective and realistic decision support for electricity market negotiating entities. The proposed method is validated by realistic electricity market simulations using real data from the Iberian market operator—MIBEL. Results show that the proposed adaptive decision support features enable electricity market players to improve their outcomes from bilateral contracts’ negotiations.

Six thinking hats: A novel metalearner for intelligent decision support in electricity markets

The energy sector has suffered a significant restructuring that has increased the complexity in electricity market players' interactions. The complexity that these changes brought requires the creation of decision support tools to facilitate the study and understanding of these markets. The Multiagent Simulator of Competitive Electricity Markets (MASCEM) arose in this context, providing a simulation framework for deregulated electricity markets. The Adaptive Learning strategic Bidding System (ALBidS) is a multiagent system created to provide decision support to market negotiating players. Fully integrated with MASCEM, ALBidS considers several different strategic methodologies based on highly distinct approaches. Six Thinking Hats (STH) is a powerful technique used to look at decisions from different perspectives, forcing the thinker to move outside its usual way of thinking. This paper aims to complement the ALBidS strategies by combining them and taking advantage of their different perspectives through the use of the STH group decision technique. The combination of ALBidS' strategies is performed through the application of a genetic algorithm, resulting in an evolutionary learning approach.

Impact of sensor nodes scaling and velocity on handover mechanisms for healthcare wireless sensor networks with mobility support

Health promotion in hospital environments can be improved using the most recent information and communication technologies. The Internet connectivity to small sensor nodes carried by patients allows remote access to their bio-signals. To promote these features the healthcare wireless sensor networks (HWSN) are used. In these networks mobility support is a key issue in order to keep patients under realtime monitoring even when they move around. To keep sensors connected to the network, they should change their access points of attachment when patients move to a new coverage area along an infirmary. This process, called handover, is responsible for continuous network connectivity to the sensors. This paper presents a detailed performance evaluation study considering three handover mechanisms for healthcare scenarios (Hand4MAC, RSSI-based, and Backbone-based). The study was performed by simulation using several scenarios with different number of sensors and different moving velocities of sensor nodes. The results show that Hand4MAC is the best solution to guarantee almost continuous connectivity to sensor nodes with less energy consumption.

Municipal solid waste management system: decision support through systems analysis

Thesis submitted to the Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia for the degree of Doctor of Philosophy in Environmental Engineering

Ankle antagonist coactivation in the double-support phase of walking: Stroke vs. healthy subjects

Introduction: Lesions at ipsilateral systems related to postural control at ipsilesional side, may justify the lower performance of stroke subjects during walking. Purpose: To analyse bilateral ankle antagonist coactivation during double-support in stroke subjects. Methods: Sixteen (8 females; 8 males) subjects with a first isquemic stroke, and twenty two controls (12 females; 10 males) participated in this study. The double support phase was assessed through ground reaction forces and electromyography of ankle muscles was assessed in both limbs. Results: Ipsilesional limb presented statistical significant differences from control when assuming specific roles during double support, being the tibialis anterior and soleus pair the one in which this atypical behavior was more pronounced. Conclusion: The ipsilesional limb presents a dysfunctional behavior when a higher postural control activity was demanded.

Cross-Layer Admission Control to Enhance the Support of Real-Time Applications in WSN

Real-time monitoring applications may be used in a wireless sensor network (WSN) and may generate packet flows with strict quality of service requirements in terms of delay, jitter, or packet loss. When strict delays are imposed from source to destination, the packets must be delivered at the destination within an end-to-end delay (EED) hard limit in order to be considered useful. Since the WSN nodes are scarce both in processing and energy resources, it is desirable that they only transport useful data, as this contributes to enhance the overall network performance and to improve energy efficiency. In this paper, we propose a novel cross-layer admission control (CLAC) mechanism to enhance the network performance and increase energy efficiency of a WSN, by avoiding the transmission of potentially useless packets. The CLAC mechanism uses an estimation technique to preview packets EED, and decides to forward a packet only if it is expected to meet the EED deadline defined by the application, dropping it otherwise. The results obtained show that CLAC enhances the network performance by increasing the useful packet delivery ratio in high network loads and improves the energy efficiency in every network load.

A framework for supporting knowledge representation – an ontological based approach

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica e de Computadores

Using neural networks and support vector regression to relate marchetti dilatometer test parameters and maximum shear modulus

In the last two decades, small strain shear modulus became one of the most important geotechnical parameters to characterize soil stiffness. Finite element analysis have shown that in-situ stiffness of soils and rocks is much higher than what was previously thought and that stress-strain behaviour of these materials is non-linear in most cases with small strain levels, especially in the ground around retaining walls, foundations and tunnels, typically in the order of 10−2 to 10−4 of strain. Although the best approach to estimate shear modulus seems to be based in measuring seismic wave velocities, deriving the parameter through correlations with in-situ tests is usually considered very useful for design practice.The use of Neural Networks for modeling systems has been widespread, in particular within areas where the great amount of available data and the complexity of the systems keeps the problem very unfriendly to treat following traditional data analysis methodologies. In this work, the use of Neural Networks and Support Vector Regression is proposed to estimate small strain shear modulus for sedimentary soils from the basic or intermediate parameters derived from Marchetti Dilatometer Test. The results are discussed and compared with some of the most common available methodologies for this evaluation.

Using neural networks and support vector regression to relate marchetti dilatometer test parameters and maximum shear modulus

In the last two decades, small strain shear modulus became one of the most important geotechnical parameters to characterize soil stiffness. Finite element analysis have shown that in-situ stiffness of soils and rocks is much higher than what was previously thought and that stress-strain behaviour of these materials is non-linear in most cases with small strain levels, especially in the ground around retaining walls, foundations and tunnels, typically in the order of 10−2 to 10−4 of strain. Although the best approach to estimate shear modulus seems to be based in measuring seismic wave velocities, deriving the parameter through correlations with in-situ tests is usually considered very useful for design practice.The use of Neural Networks for modeling systems has been widespread, in particular within areas where the great amount of available data and the complexity of the systems keeps the problem very unfriendly to treat following traditional data analysis methodologies. In this work, the use of Neural Networks and Support Vector Regression is proposed to estimate small strain shear modulus for sedimentary soils from the basic or intermediate parameters derived from Marchetti Dilatometer Test. The results are discussed and compared with some of the most common available methodologies for this evaluation.