Dataset of fundus images for the diagnosis of ocular toxoplasmosis.

Toxoplasmosis chorioretinitis is commonly diagnosed by an ophthalmologist through the evaluation of the fundus images of a patient. Early detection of these lesions may help to prevent blindness. In this article we present a data set of fundus images labeled into three categories: healthy eye, inactive and active chorioretinitis. The dataset was developed by three ophthalmologists with expertise in toxoplasmosis detection using fundus images. The dataset will be of great use to researchers working on ophthalmic image analysis using artificial intelligence techniques for the automatic detection of toxoplasmosis chorioretinitis.

Cloud architecture for electronic health record systems interoperability.

BACKGROUND: Current Electronic Health Record (EHR) systems are built using different data representation and information models, which makes difficult achieving information exchange. OBJECTIVE: Our aim was to propose a scalable architecture that allows the integration of information from different EHR systems. METHODS: A cloud-based EHR interoperable architecture is proposed through the standardization and integration of patient electronic health records. The data is stored in a cloud repository with high availability features. Stakeholders can retrieve the patient EHR by requesting only to the integrated data repository. The OpenEHR two-level approach is applied according to the HL7-FHIR standards. We validated our architecture by comparing it with 5 different works (CHISTAR, ARIEN, DIRAYA, LLPHR and INEHRIS) using a set of selected axes and a scoring method. RESULTS: The problem was reduced to a single point of communication between each EHR system and the integrated data repository. By combining cloud computing paradigm with selected health informatics standards, we obtained a generic and scalable architecture that complies 100% with interoperability requisites according to the evaluation framework applied. CONCLUSIONS: The architecture allowed the integration of several EHR systems, adapting them with the use of standards and ensuring the availability thanks to cloud computing features.

A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images.

In the automatic diagnosis of ocular toxoplasmosis (OT), Deep Learning (DL) has arisen as a powerful and promising approach for diagnosis. However, despite the good performance of the models, decision rules should be interpretable to elicit trust from the medical community. Therefore, the development of an evaluation methodology to assess DL models based on interpretability methods is a challenging task that is necessary to extend the use of AI among clinicians. In this work, we propose a novel methodology to quantify the similarity between the decision rules used by a DL model and an ophthalmologist, based on the assumption that doctors are more likely to trust a prediction that was based on decision rules they can understand. Given an eye fundus image with OT, the proposed methodology compares the segmentation mask of OT lesions labeled by an ophthalmologist with the attribution matrix produced by interpretability methods. Furthermore, an open dataset that includes the eye fundus images and the segmentation masks is shared with the community. The proposal was tested on three different DL architectures. The results suggest that complex models tend to perform worse in terms of likelihood to be trusted while achieving better results in sensitivity and specificity.

Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images with Residual Neural Networks.

Ocular toxoplasmosis (OT) is commonly diagnosed through the analysis of fundus images of the eye by a specialist. Despite Deep Learning being widely used to process and recognize pathologies in medical images, the diagnosis of ocular toxoplasmosis(OT) has not yet received much attention. A predictive computational model is a valuable time-saving option if used as a support tool for the diagnosis of OT. It could also help diagnose atypical cases, being particularly useful for ophthalmologists who have less experience. In this work, we propose the use of a deep learning model to perform automatic diagnosis of ocular toxoplasmosis from images of the eye fundus. A pretrained residual neural network is fine-tuned on a dataset of samples collected at the medical center of Hospital de Clínicas in Asunción, Paraguay. With sensitivity and specificity rates equal to 94% and 93%,respectively, the results show that the proposed model is highly promising. In order to replicate the results and advance further in this area of research, an open data set of images of the eye fundus labeled by ophthalmologists is made available.

Servidor de Terminología Médica para el Hospital de Clínicas de Paraguay utilizando Apache Lucene / Medical Terminology Server for the Hospital de Clínicas de Paraguay using Apache Lucene

Introducción: En el Hospital de Clínicas de Paraguay, el proceso actual de búsqueda de terminologías para la codificación médica en estándares de salud toma mucho tiempo ya que se realiza manualmente. Se propone, optimizar el proceso actual de búsqueda a través de la implementación de un servidor de terminología médica utilizando servicios web y una librería de motor de búsqueda de texto. Método: Se propone una arquitectura cliente - servidor de tres capas (también conocida como arquitectura multi-nivel), organizada de la siguiente manera: capa de presentación, de negocios y capa de datos. Se eligió utilizar este patrón por la independencia entre las capas y la clara definición de cada una de ellas en cuanto al objetivo que persigue. El servidor de terminología se encuentra representado en la capa de negocios. Está compuesta por un conjunto de servicios web de tipo REST y una librería de motor de búsqueda de texto, denominada Apache Lucene. Experimentos y Resultados: Fueron realizados dos experimentos acordes a los objetivos específicos mencionados anteriormente. El servidor de terminología implementado responde hasta 19 veces más rápido que el proceso actual de búsqueda y resultó ser bastante competitivo contra Metamorphosys. Si bien ambas herramientas presentan un tiempo de respuesta promedio similar, el servidor de terminología es hasta 5 veces más rápido que Metamorphosys en sus valores atípicos. Conclusiones: El servidor de terminología implementado reduce el tiempo de búsqueda del proceso actual siendo más rápido que el proceso actual de búsqueda. Finalmente, ante la comparación del servidor implementado contra el buscador Metamorphosys, el servidor implementado se muestra competitivo contra dicho buscador ya que tienen tiempos de respuesta similares(AU)

Introduction: In the Hospital Clínicas of Paraguay, the current process of searching for terminologies for medical coding in health standards takes a long time since it is done manually. It is proposed to optimize the current search process through the implementation of a medical terminology server using web services and a text search engine library. Method: Three layer client-server architecture is proposed (also known as multilevel architecture), organized as follows: presentation layer, business layer and data layer. The use of this pattern was due to its contribution to the independence between the layers and the clear definition of them in terms of the objective pursued. The terminology server is represented in the business layer. It is composed of a set of REST web services and a text search engine library, called Apache Lucene. Experiments and Results: Two experiments were carried out according to the objective mentioned above. The implemented terminology server responds up to 19 times faster than the current search process and proved to be quite competitive against Metamorphosys. While both tools have a similar average response time, the terminology server is up to 5 times faster than Metamorphosys in their outliers. Conclusions: The terminology server implemented reduces the search time of the current process being faster than the current search process. Finally, before the comparison of the server implemented against the Metamorphosys search engine, the implemented server is competitive since they have similar response times(AU)

Servidor de Terminología Médica para el Hospital de Clínicas de Paraguay utilizando Apache Lucene / Medical Terminology Server for the Hospital de Clínicas de Paraguay using Apache Lucene

Introducción: En el Hospital de Clínicas de Paraguay, el proceso actual de búsqueda de terminologías para la codificación médica en estándares de salud toma mucho tiempo ya que se realiza manualmente. Se propone, optimizar el proceso actual de búsqueda a través de la implementación de un servidor de terminología médica utilizando servicios web y una librería de motor de búsqueda de texto. Método: Se propone una arquitectura cliente - servidor de tres capas (también conocida como arquitectura multi-nivel), organizada de la siguiente manera: capa de presentación, de negocios y capa de datos. Se eligió utilizar este patrón por la independencia entre las capas y la clara definición de cada una de ellas en cuanto al objetivo que persigue. El servidor de terminología se encuentra representado en la capa de negocios. Está compuesta por un conjunto de servicios web de tipo REST y una librería de motor de búsqueda de texto, denominada Apache Lucene. Experimentos y Resultados: Fueron realizados dos experimentos acordes a los objetivos específicos mencionados anteriormente. El servidor de terminología implementado responde hasta 19 veces más rápido que el proceso actual de búsqueda y resultó ser bastante competitivo contra Metamorphosys. Si bien ambas herramientas presentan un tiempo de respuesta promedio similar, el servidor de terminología es hasta 5 veces más rápido que Metamorphosys en sus valores atípicos. Conclusiones: El servidor de terminología implementado reduce el tiempo de búsqueda del proceso actual siendo más rápido que el proceso actual de búsqueda. Finalmente, ante la comparación del servidor implementado contra el buscador Metamorphosys, el servidor implementado se muestra competitivo contra dicho buscador ya que tienen tiempos de respuesta similares(AU)

Introduction: In the Hospital Clínicas of Paraguay, the current process of searching for terminologies for medical coding in health standards takes a long time since it is done manually. It is proposed to optimize the current search process through the implementation of a medical terminology server using web services and a text search engine library. Method: Three layer client-server architecture is proposed (also known as multilevel architecture), organized as follows: presentation layer, business layer and data layer. The use of this pattern was due to its contribution to the independence between the layers and the clear definition of them in terms of the objective pursued. The terminology server is represented in the business layer. It is composed of a set of REST web services and a text search engine library, called Apache Lucene. Experiments and Results: Two experiments were carried out according to the objective mentioned above. The implemented terminology server responds up to 19 times faster than the current search process and proved to be quite competitive against Metamorphosys. While both tools have a similar average response time, the terminology server is up to 5 times faster than Metamorphosys in their outliers. Conclusions: The terminology server implemented reduces the search time of the current process being faster than the current search process. Finally, before the comparison of the server implemented against the Metamorphosys search engine, the implemented server is competitive since they have similar response times(AU).

Civic Competence of Youth in Europe: Measuring Cross National Variation Through the Creation of a Composite Indicator.

This article develops a composite indicator to monitor the levels of civic competence of young people in Europe using the IEA ICCS 2009 study. The measurement model combines the traditions in Europe of liberal, civic republican and critical/cosmopolitan models of citizenship. The results indicate that social justice values and citizenship knowledge and skills of students are facilitated within the Nordic system that combines a stable democracy and economic prosperity with a democratically based education systems in which teachers prioritise promoting autonomous critical thinking in citizenship education. In contrast, medium term democracies with civic republican tradition, such as Italy and Greece gain more positive results on citizenship values and participatory attitudes. This is also the case for some recent former communist countries that retain ethnic notions of citizenship. In a final step we go on to argue that the Nordic teachers' priority on developing critical and autonomous citizens perhaps facilitates 14 years olds qualities of cognition on citizenship and the values of equality but may not be the most fruitful approach to enhance participatory attitudes or concepts of a good citizen which may be better supported by the Italian teachers' priority on civic responsibility.

Towards Improving Hypertensive Patients Care: Pervasive Monitoring and Diagnosis Support.

Hypertension is the most common chronic condition dealt with by primary care physicians and other health practitioners. It usually has no symptoms, causing a delay in diagnosis. Moreover, around 20% of the global population suffers from "white-coat syndrome", which can lead to misdiagnosing hypertension. When diagnosed, patients find it difficult to constantly monitor their blood pressure to ensure it is within acceptable levels. In this work, we propose a pervasive solution model for ambulatory monitoring of hypertensive patients and for supporting a clinician with the task of diagnosing hypertension. It contributes to the selection of attributes and techniques for assisting hypertension diagnosis, and also to an implementation which dynamically adjusts itself to each patient's average blood pressure.

Valoración de la efectividad del soporte nutricional por sonda nasogástrica en sala general / Assessment of the efficacy of nasogastric nutritional support in a general ward / Valorização da efetividade do suportenutricional por sonda nasogástricaem enfermaría

La interrupción de la alimentación enteral conduce a un aporte calórico inadecuado, circunstancia que se agrava debido al estado catabólico que presentan los pacientes internados, contribuyendo ambas situaciones al deterioro de su estado nutricional. La malnutrición calóricoproteica se asocia con un mayor número de complicaciones, con un incremento de la estadía hospitalaria y, por lo tanto, con mayores costos. Objetivos. Evaluar la calidad del soporte nutricional por sonda y cuáles son los factores que influyeron en las diferencias entre la cantidad de nutrientes administrados, pautados y teóricamente requeridos. Material y métodos. Pacientes adultos a quienes se les prescribía nutrición enteral por sonda nasogastro/enteral. Se calcularon diariamente las calorías pautadas y las administradas, mientras que los requerimientos calóricos teóricos se calcularon según la ecuación de Harris-Benedict a la que se le aplicaba un factor de estrés y actividad. Asimismo, se evaluaron las causas por las que se interrumpió la nutrición enteral. Resultados. De un total de 40 pacientes consecutivos que recibieron soporte nutricional enteral un 95% presentó administración inadecuada. Hubo una inadecuación de la prescripción médica de la alimentación enteral en un 70% relacionado con el requerimiento calórico total. El bajo ratio de calorías administradas-pautadas afectaban a la Nutrición Enteral, debido a las causas más importantes de interrupción (que acumulan el 80% de las interrupciones):a) relacionadas al personal de enfermería (32.5%), b) incumplimiento en el horario de entrega del alimento (20%), c) problemas mecánicos (12.5%), d) procedimientos diagnósticos (10%) y e) disfunción gastrointestinal(10%). Conclusiones. En nuestra unidad se observó una diferencia importante entre los requerimientos calóricos teóricos y la cantidad efectivamente administrada. El conocimiento de esta situación permitirá ...

Background. The interruption of enteral feeding leads to inappropriate caloric intake, circumstance aggravated by the catabolic state of inpatients and both factors contributing to the deterioration of their nutritional status.Protein-energy malnutrition is associated with more complications, increased hospital stay, and therefore higher costs.Objective. To evaluate the quality of enteral nutritional support and the factors influencing the differences between the amounts of nutrients managed, scheduled and theoretically required.Materials y methods. Adult patients prescribed enteral nutrition by nasogastric/enteral tube. The calories administered and estimated were daily calculated, while theoretical caloric requirements were calculated according to the Harris-Benedict equation with an applied factor of stress and activity. The reasons leading to enteral nutrition cessationwere also evaluated.Results. Of the 40 consecutive patients who received enteral nutritional support, 95% reported inadequate administration. There was an inadequate medical prescription of enteral feeding by 70%, related to total caloric requirements. The low ratio of calories prescribed-administered affected enteral nutrition due to the following main causes of interruption (which accumulate 80% of interruptions): nurses/' work (32.5%), failure in the delivery of the scheduled food (20%), mechanical problems (12.5%), diagnostic procedures (10%) and gastrointestinal dysfunction (10%). Conclusions. In our unit we could observe an important difference between the theoretical energy requirements and the amounts effectively administered. Acknowledging...

A interrupção da alimentação enteral conduza uma contribuição calórica inadequada, circunstância que se agrava devido o estado catabólico que apresentamos pacientes internados, contribuindo ambas as situaçõespara a deterioração do seu estado nutricional. A má nutriçãocalórica-proteica é associada a um maior número decomplicações, com um incremento da estadia hospitalariae, portanto, com maiores custos.Objetivos. Avaliar a qualidade do suporte nutricional porsonda e quais são os fatores que influenciaram nas diferençasentre a quantidade de nutrientes administrados, determinadose teoricamente requeridos.Material e métodos. Pacientes adultos que recebiam prescriçãonutricional enteral por sonda nasogastroenteral. Foramcalculadas diariamente as calorias determinadas e asadministradas enquanto que os requerimentos calóricoseram calculados segundo a equação de Harris-Benedictna qual se aplicava um fator de estresse e atividade. Alémdisso, foram avaliadas as causas pelas quais a nutriçãoenteral foi interrompida.Resultados. De um total de 40 pacientes ...