Step towards a patient timeline in intensive care units

In Intensive Medicine, the presentation of medical information is done in many ways, depending on the type of data collected and stored. The way in which the information is presented can make it difficult for intensivists to quickly understand the patient's condition. When there is the need to cross between several types of clinical data sources the situation is even worse. This research seeks to explore a new way of presenting information about patients, based on the timeframe in which events occur. By developing an interactive Patient Timeline, intensivists will have access to a new environment in real-time where they can consult the patient clinical history and the data collected until the moment. The medical history will be available from the moment in which patients is admitted in the ICU until discharge, allowing intensivist to examine data regarding vital signs, medication, exams, among others. This timeline also intends to, through the use of information and models produced by the INTCare system, combine several clinical data in order to help diagnose the future patients’ conditions. This platform will help intensivists to make more accurate decision. This paper presents the first approach of the solution designed

Intelligent decision support to predict patient barotrauma risk in intensive care units

The occurrence of Barotrauma is identified as a major concern for health professionals, since it can be fatal for patients. In order to support the decision process and to predict the risk of occurring barotrauma Data Mining models were induced. Based on this principle, the present study addresses the Data Mining process aiming to provide hourly probability of a patient has Barotrauma. The process of discovering implicit knowledge in data collected from Intensive Care Units patientswas achieved through the standard process Cross Industry Standard Process for Data Mining. With the goal of making predictions according to the classification approach they several DM techniques were selected: Decision Trees, Naive Bayes and Support Vector Machine. The study was focused on identifying the validity and viability to predict a composite variable. To predict the Barotrauma two classes were created: “risk” and “no risk”. Such target come from combining two variables: Plateau Pressure and PCO2. The best models presented a sensitivity between 96.19% and 100%. In terms of accuracy the values varied between 87.5% and 100%. This study and the achieved results demonstrated the feasibility of predicting the risk of a patient having Barotrauma by presenting the probability associated.

Benchmarking sobre técnicas de otimização para modelos de apoio à decisão na medicina intensiva

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

Estudo das necessidades de médicos especialistas na Região Norte de Portugal

Dissertação de mestrado em Engenharia Industrial

Pervasive patient timeline for intensive care units

This research work explores a new way of presenting and representing information about patients in critical care, which is the use of a timeline to display information. This is accomplished with the development of an interactive Pervasive Patient Timeline able to give to the intensivists an access in real-time to an environment containing patients clinical information from the moment in which the patients are admitted in the Intensive Care Unit (ICU) until their discharge This solution allows the intensivists to analyse data regarding vital signs, medication, exams, data mining predictions, among others. Due to the pervasive features, intensivists can have access to the timeline anywhere and anytime, allowing them to make decisions when they need to be made. This platform is patient-centred and is prepared to support the decision process allowing the intensivists to provide better care to patients due the inclusion of clinical forecasts.

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.

Chest Pain Units: A Modern Way of Managing Patients with Chest Pain in the Emergency Department

It is estimated that 5 to 8 million individuals with chest pain or other symptoms suggestive of myocardial ischemia are seen each year in emergency departments (ED) in the United States 1,2, which corresponds to 5 to 10% of all visits 3,4. Most of these patients are hospitalized for evaluation of possible acute coronary syndrome (ACS). This generates an estimated cost of 3 - 6 thousand dollars per patient 5,6. From this evaluation process, about 1.2 million patients receive the diagnosis of acute myocardial infarction (AMI), and just about the same number have unstable angina. Therefore, about one half to two thirds of these patients with chest pain do not have a cardiac cause for their symptoms 2,3. Thus, the emergency physician is faced with the difficult challenge of identifying those with ACS - a life-threatening disease - to treat them properly, and to discharge the others to suitable outpatient investigation and management.

The unbounded dead-end depth propertie is not a group invariant

Vegeu el resum a l'inici del document del fitxer adjunt

Inverse Problems for multiple invariant curves

Planar polynomial vector fields which admit invariant algebraic curves, Darboux integrating factors or Darboux first integrals are of special interest. In the present paper we solve the inverse problem for invariant algebraic curves with a given multiplicity and for integrating factors, under generic assumptions regarding the (multiple) invariant algebraic curves involved. In particular we prove, in this generic scenario, that the existence of a Darboux integrating factor implies Darboux integrability. Furthermore we construct examples where the genericity assumption does not hold and indicate that the situation is different for these.

Desenvolupament de mesures per comparar transculturalment xarxes personals (USA i Estats Units)

Estudi elaborat a partir d’una estada a la Universitat de Florida durant Abril i Maig de 2006. “Application to Immigrant Populations in South Florida and Northeastern Spain" ha permès recollir les xarxes personals d’immigrants en els dos països mitjançant un qüestionari implementat amb un software desenvolupat ex professo per recollir i presentar visualment les dades. Es van revisar i assemblar les entrevistes i qüestionaris realitzats a Catalunya i a Estats Units (Miami i Nova York, especialment). Fins al moment s’han revisat i analitzat uns 450 casos. Un cop depurada i analitzada la informació obtinguda s’ha pogut disposar per primer cop de mesures globals pels diferents col•lectius estudiats. L'objectiu global del projecte és entendre les implicacions que les estructures de les xarxes personals tenen en relació a un conjunt de conductes (de salut, d'ús de la llengua, etx) i les autoconcepcions. En aquest sentit era necessari desenvolupar un seguit de mesures que permetessin comparar i documentar la variació de les estructures de les xarxes personals a diferents cultures, nivells socioeconòmics, gènere, religió, etc. i incorporar-les com a variables independents als models explicatius.En aquest moments s’està desenvolupant un índex basat en variables estructurals (número de components de la xarxa, densitat, grau d’intermediació, etc.) i variables de composició (proporció de persones diferents del país d’origen, entre d'altres). La idea és disposar d’un índex d’heterogeneïtat de la xarxa social comparable entre els diferents col•lectius. Malgrat que el treball continua, la principal conclusió a la que s’ha arribat és que al menys a Espanya a mida que passa el temps augmenta el nivell d’heterogeneïtat de les xarxes personals. És a dir, que desprès d’un ràpid procés de canvi i una fase de transnacionalitat la tendència és a reduir aquest nivell (pels costos socials i econòmics que comporta) depenent, naturalment, de factors com l’origen temporal (primera onada o successives), el tipus de col•lectiu i el sexe.

Well-posedness and invariant measures for HJM models with deterministic volatility and Lévy noise

We give sufficient conditions for existence, uniqueness and ergodicity of invariant measures for Musiela's stochastic partial differential equation with deterministic volatility and a Hilbert space valued driving Lévy noise. Conditions for the absence of arbitrage and for the existence of mild solutions are also discussed.

A Retail benchmarking approach to eficient two-way access pricing

We study a retail benchmarking approach to determine access prices for interconnected networks. Instead of considering fixed access charges as in the existing literature, we study access pricing rules that determine the access price that network i pays to network j as a linear function of the marginal costs and the retail prices set by both networks. In the case of competition in linear prices, we show that there is a unique linear rule that implements the Ramsey outcome as the unique equilibrium, independently of the underlying demand conditions. In the case of competition in two-part tariffs, we consider a class of access pricing rules, similar to the optimal one under linear prices but based on average retail prices. We show that firms choose the variable price equal to the marginal cost under this class of rules. Therefore, the regulator (or the competition authority) can choose one among the rules to pursue additional objectives such as consumer surplus, network covera.

Desenvolupament de dipòsits institucionals als Estats Units a partir de l'inici del 2005

Aquest article analitza la situació dels dipòsits institucionals als EUA mitjançant una enquesta realitzada per la CNI a les seves institucions acadèmiques. Amb aquesta enquesta s'obtingué informació sobre el grau d'implementació dels dipòsits i la seva extensió, així com del tipus de materials. A més, va servir per conèixer l'opinió de les institucions sobre els dipòsits, i va quedar palès que la major part de les que no en posseeixen, tenen previst posar-ne un en funcionament, tot i que els preocupi el cost de manteniment. L'article també tracta la responsabilitat administrativa dels dipòsits, les polítiques que els gestionen, la possibilitat de compartir dipòsits entre institucions i la procedència dels materials que contenen.

Euclidean geometric invariant of framed knots in manifolds

We present an invariant of a three dimensional manifold with a framed knot in it based on the Reidemeister torsion of an acyclic complex of Euclidean geometric origin. To show its nontriviality, we calculate the invariant for some framed (un)knots in lens spaces. An important feature of our work is that we are not using any nontrivial representation of the manifold fundamental group or knot group.