In the field of aviation forecasting is used, among other things, to determine the number of passengers to expect for each flight. This is beneficial in the practice of revenue management, as the forecast is used as a base when setting the price for each flight. In this study, a forecast evaluation has been done on seven different routes with a total of 61 different flights, using four different methods. These are: Mean Absolute Scaled Error (MASE), Mean Absolute Percentage Error (MAPE), Tracking Signal, and a goodness of fit test to determine if the forecast errors are normally distributed. The MASE has been used to determine if the passenger forecasts are better or worse than a naïve forecast, while the MAPE provides an error value for internal comparisons between the flights. The Tracking Signal and the normal distribution test have been used in order to determine whether a flight has bias or not towards under- or overforecasting. The results point towards a general underforecast across all studied flights. A total of 89 % of the forecasts perform better than the naïve forecast, with an average MASE value of 0,78. As such, the forecast accuracy is better than that of the naïve forecast. There are however large error values among the observed flights, affecting the MAPE average. The MAPE average is 38,53 % while the median is 30,60 %. The measure can be used for internal comparisons, and one such way is to use the average value as a benchmark in order to focus on improving those forecasts with a higher than average MAPE. The authors have found that the MASE and MAPE are useful in measuring forecast accuracy and as such the recommendation of the authors is that these two error measures can be used together to evaluate forecast accuracy at frequent intervals. In addition to this there is value in examining the error distribution in conjunction with the Mean Error when searching for bias, as this will indicate if there is systematic error present.

La politique des transports dans le monde et en Europe évolue vers une vision co-modale. Cette nouvelle politique n’oppose plus la voiture au transport public mais encourage une combinaison de tous les modes de transport en espérant ainsi assurer un développement rentable et durable.Nous focalisons notre étude sur le service transport de personnes qui s’inscrit au cœur des politiques co-modales en combinant tous les modes de transport en commun (métro, bus..) et promeut de nouveaux modes d’utilisation de la voiture particulière comme le covoiturage (partage d’un véhicule personnel) ou l’AutoPartage (voiture en libre-service).Toutefois, pour générer un itinéraire exploitant les services de plusieurs opérateurs de transport, il faut consulter plusieurs sites internet. Selon le déplacement à réaliser, cette tâche de planification complexe peut être très difficile à réaliser et ne garantit pas l’optimalité de l’itinéraire sélectionné.Nous nous sommes donc intéressés à la conception d’un système d’aide au déplacement capable de fournir une information voyageur (co-modale) en mettant en relation plusieurs opérateurs de transport (en commun et individuel). Le système en question doit être capable d’assister l’utilisateur dans la phase de planification par la constitution d’un carnet de voyage proposant plusieurs itinéraires multi-opérateurs. De plus, il assiste l’utilisateur en cas de perturbation en l’informant et en lui proposant des itinéraires de secours. Ce travail est basé sur des avancées technologiques qui facilitent l’optimisation dans un environnement distribué (Multi-agent - SOA) et rendent l’information accessible grâce à un grand nombre de médias (téléphone, PDA..) / Today's transport policy in the world, and more specifically in Europe, is moving towards a co-modal vision. This new policy does not oppose private to public transport but encourages a combination of all modes of transportation in the hope of assuring a lasting development.We focus our study on one special service: people transport which combines all modes of public transport (train, subway, tram, bus ..) and integrates new ways of car use such as carpooling (sharing a personal vehicle and the travel cost between drivers and passengers) and the EcoPartage (self-service cars in town).However, to generate a route using several transport operators, we have to check different Internet websites. This complex planning task can be very difficult and does not guarantee the optimality of the selected route.We are therefore interested in designing a support information system capable of providing comodal information linking several transport operators (public and individual).The system in question must be able to assist the user in the planning phase by offering a travelogue suggesting several possible routes; each route may include one or more transport operator (public or individual ones).In addition, it assists the user during the trip by informing him in case of disturbance and by proposing alternatives routes if necessary.This work is based on various technological developments in order to facilitate the information optimization in a distributed environment (Multi-agent - SOA) and make the information accessible to the user through a large number of media (telephone, mobile, PDA ...)

A tecnologia de agentes tem sido reconhecida como um paradigma promissor em sistemas educacionais da nova geração. Entretanto, o esforço e inflexibilidade de algumas metodologias próprias para agentesacarretam num alto custo, tempo e adaptação de escopo. Este trabalho visaavaliar alternativas de desenvolvimento de um jogo educacional médico orientado a agentes, através da aplicação de um estudo de caso, com o intuito de verificar se metodologias próprias para implementação de sistemas multiagentes trazem benefícios no resultado final da implementação do jogo, e também se os resultados alcançados na comparação de processos de desenvolvimento de cunho tradicional e ágil fazem diferença no resultado final. Desta forma, este trabalho compara três metodologias baseadas nos conceitos da Engenharia de Software através de um estudo de caso, sendo elas: O-MaSE que é uma metodologiatradicional de desenvolvimento de sistemas multiagentes e utiliza um processo de desenvolvimento tradicional; AgilePASSI que é baseada no processo de desenvolvimento ágil e específica para sistemas multiagentes; e, por último, Scrum que é uma metodologia ágil, não sendo específica para implementação de sistemas multiagentes / The agent technology has been recognized as a promising paradigm in educational systems of the new generation. However, the effort and inflexibility of some specific methodologies entail a high cost, time and adaptation scope. This work aims to validate options for developing an educational medical game oriented agents by applying an experiment in order to verify that methodologies specific to implement multi-agent systems provide benefits in the result of the implementation of the game, and also the results achieved by comparison of traditional and agile development processes makes a difference in the outcome. Thus, this paper compares three approaches based on the concepts of software engineering through an experiment, as follows: O-MaSE is a traditional methodology for the development of multi-agent systems and uses a traditional development process; AgilePASSI which is based on agile and specific development for multi-agent systems; and finally, Scrum that is an agile methodology, not specific to implementation of multi-agent systems.

A tecnologia de agentes tem sido reconhecida como um paradigma promissor em sistemas educacionais da nova geração. Entretanto, o esforço e inflexibilidade de algumas metodologias próprias para agentesacarretam num alto custo, tempo e adaptação de escopo. Este trabalho visaavaliar alternativas de desenvolvimento de um jogo educacional médico orientado a agentes, através da aplicação de um estudo de caso, com o intuito de verificar se metodologias próprias para implementação de sistemas multiagentes trazem benefícios no resultado final da implementação do jogo, e também se os resultados alcançados na comparação de processos de desenvolvimento de cunho tradicional e ágil fazem diferença no resultado final. Desta forma, este trabalho compara três metodologias baseadas nos conceitos da Engenharia de Software através de um estudo de caso, sendo elas: O-MaSE que é uma metodologiatradicional de desenvolvimento de sistemas multiagentes e utiliza um processo de desenvolvimento tradicional; AgilePASSI que é baseada no processo de desenvolvimento ágil e específica para sistemas multiagentes; e, por último, Scrum que é uma metodologia ágil, não sendo específica para implementação de sistemas multiagentes / The agent technology has been recognized as a promising paradigm in educational systems of the new generation. However, the effort and inflexibility of some specific methodologies entail a high cost, time and adaptation scope. This work aims to validate options for developing an educational medical game oriented agents by applying an experiment in order to verify that methodologies specific to implement multi-agent systems provide benefits in the result of the implementation of the game, and also the results achieved by comparison of traditional and agile development processes makes a difference in the outcome. Thus, this paper compares three approaches based on the concepts of software engineering through an experiment, as follows: O-MaSE is a traditional methodology for the development of multi-agent systems and uses a traditional development process; AgilePASSI which is based on agile and specific development for multi-agent systems; and finally, Scrum that is an agile methodology, not specific to implementation of multi-agent systems.

Les établissements de santé sont confrontés à de nouveaux défis tels que le vieillissement de la population, la hausse des coûts des soins et les progrès rapides des technologies médicales. Les nouvelles politiques de contrôle du budget des soins ont été introduites pour augmenter l'efficacité, réduire les déchets et remodeler le système de santé.Ces établissements cibles présentent des réseaux complexes incluant de ressources humaines,financières, structurelles et technologiques visant à garantir les meilleurs soins. Ces enjeux concernent d’autant plus les services d’urgence engorgés par l’afflux massif des passages, qui doivent fournir des décisions rapides et assurer le dimensionnement de ses ressources afin de réduire les délais d’attente des patients sans compromettre la qualité de soin.L’objectif de cette thèse est de proposer des solutions appropriées aux services d’urgences permettant d’améliorer la prise en charge des patients en termes de temps d’attente. Nous avons commencé par analyser les problématiques de la filière des urgences afin d’engager une démarche d’amélioration. Par la suite, nous avons modélisé le processus de prise en charge des patients au service d’accueil des urgences à l’aide d’un système multi-agent ouvert et dynamique. Le système proposé permet de fournir une aide à la décision sur la planification de l’activité médicale et l’affectation des ressources humaines dans une unité où on se trouve souvent face à une situation d’urgence nécessitant une prise en charge rapide et efficace. Dans ce contexte, nous abordons le problème réactif d’optimisation de l’ordonnancement des opérations de soin et le problème de coordination du personnel médical. Nous nous intéressons au dimensionnement des ressources humaines au SU en adoptant une approche de prise en compte des compétences maîtrisées dans le but de trouver une adéquation avec celles requises par l’activité médicale afin avant tout d’accroitre la qualité, réduire les délais d’attente et permettre de dégager des gains de gestion / Health-care organizations are facing new challenges such as the aging population, the rise of health care costs and the rapid progress of medical technologies. New policies of health care budget control have been introduced to increase efficiency, reduce waste and reshape the entire health care system. Targeted organizations are complex networks of human,financial, structural and technological resources aiming at guarantying best public health care.These issues concern all the more Emergency Departments (ED) congested by the massive influx of passages and which must provide quick decisions and ensure the sizing of its resources to reduce waiting times for patients with out compromising quality of care.The objective of this thesis is to propose appropriate solutions to ED to improve carefor patients in terms of waiting time. We began by analyzing the problems of the emergency department in order to initiate a process of improvement. Subsequently, we modeled the process of care for patients at ED by using an open and dynamic multi-agent system. The proposed system can provide decision support on business planning and allocation of medical resources in a unit where one is often faced with an emergency situation requiring rapid and effective response. In this context, we study the reactive problem for optimizing scheduling of operations care and the coordination problem of medical staff. We take into account the skills mastered by human resources at ED in order to find a match with those required by the medical activity. This approach aims to increase quality, reduce time of expectation and provide pointers gains management

<p>Hemometrijskim metodama (deskriptivna statistika, analiza glavnih komponenti, ve&scaron;tačke neuronske mreže i fazi optimizacija) analizirani su rezultati procesa osmotske dehidratacije mesa srebrnog kara&scaron;a, sa ciljem unapređenja efikasnosti osmotskog tretmana i pronalaženja optimalnih tehnolo&scaron;kih parametara.<br />Osmotski tretman se odvijao u tri osmotska rastvora (vodeni rastvor natrijum hlorida i<br />saharoze, kombinacija vodenog rastvora natrijum hlorida i saharoze i melase i melasa &scaron;ećerne repe) različitih koncentracija, na četiri temperature (10&deg;C, 20&deg;C, 35&deg;C i 50&deg;C) i pri tri vremena procesa (1, 3 i 5h). Posmatrani su sledeći odzivi sistema: gubitak vode, prira&scaron;taj suve materije, povećanje sadržaja suve materije, sniženje aktivnosti vode i promena sadržaja minerala (Na, K, Ca i Mg). Karakterizacijom osmotski dehidriranog ribljeg polupoizvoda, poja&scaron;njeni su efekti osmotskog tretmana i inovatinog osmotskog rastvora na senzorne osobine, hemijski i mikrobiolo&scaron;ki profil tretiranog mesa ribe. Rezultati ispitivanja pokazuju da se primenom procesa osmotske dehidratacije povećava gubitak vode, prira&scaron;taj suve materije i sadržaj suve materije u svim uzorcima mesa srebrnog kara&scaron;a. Za sva tri osmotska rastvora, najveće vrednosti dobijene su nakon 5 časova, pri najvi&scaron;im temperaturama i u najvećim koncentracijama rastvora.<br />Povećavanjem temperature procesa, koncentracije rastvora i vremena trajanja procesa, povećan je sadržaj posmatranih minerala u tretiranom mesu ribe. Rezultati<br />ANOVA testa pokazali su da na vrednosti posmatranih odziva statistički značajno utiču<br />sva tri parametra: vreme, temperatura i koncentracija. PCA analizom procesa utvrđeno je da su pri izračunavanju prve glavne komponente najveći uticaj imale vrednosti svih odziva osim aw vrednosti, dok je ona najvi&scaron;e uticala na proračun druge glavne komponente. Iako su modeli ve&scaron;tačkih neuronskih mreža kompleksniji od modela polinoma drugog reda, mreže su pokazale bolji učinak usled visoke<br />nelinearnosti razvijenih sistema. Primenom fazi optimizacije postignute optimalne vrednosti procesnih parametara za vodeni rastvor natrijum hlorida i saharoze su bile na nižim temperaturama i nižim koncentracijama rastvora, dok su za rastvore sa melasom &scaron;ećerne repe optimalne vrednosti na maksimumima posmatranih opsega temperature i koncentracije rastvora. Procesom osmotske dehidratacije smanjen je inicijalni broj bakterija u mesu srebrnog kara&scaron;a. Hemijskim i senzorskim analizama utvrđeno je da je melasa &scaron;ećerne repe zbog svog kompleksnog nutritivnog sastava<br />povoljnije je delovala na promenu hemijskog sastava i senzorne osobine uzoraka u odnosu na druga dva rastvora.</p> / <p>Chemometric methods (descriptive statistics, principal components analysis, artificial neural networks and fuzzy optimization) were used to analyze the results of osmotic dehydration of silver crucian carp, with the aim of improving the efficiency of the osmotic treatment and finding the optimal technological parameters.<br />The osmotic treatment was carried out in three osmotic solution (aqueous sodium chloride and sucrose solution, sugar beet molasses and the combination of these two solutions) of varying concentrations, at four temperatures (10&deg;C, 20&deg;C, 35&deg;C and 50&deg;C) and at three processing times (1, 3 and 5 h). The observed system responses were: water loss, solid gain, increase in dry matter content, reduction of water activity<br />and changes in mineral content (Na, K, Ca and Mg). The characterization of dehydrated fish, explained the effects of osmotic treatment on its sensory properties, chemical and microbiological profile. Results have shown that the application of osmotic dehydration increases water loss, solid gain and dry matter content in all samples of fish meat. For all three osmotic solution, the highest values were obtained after 5h, at the highest temperatures and in the highest concentration of the solution. By increasing the process temperature, concentration and time, increased the mineral content in the fish meat. The results of the ANOVA test have shown that the values of the observed responses significantly affect all three parameters: time, temperature and concentration. PCA analysis process has found that on calculation of the first principal component all response values except aw value had the greatest impact, while aw value had the most influence on the calculation of the other major component. Although models of artificial neural network models are more complex than second order polynomial, the network showed better performance due to the high nonlinearity of the developed system. Application of fuzzy optimization obtained optimal values of the process parameters for aqueous solution of sodium chloride and sucrose were at lower temperatures and lower concentrations of the solution, while the solutions with molasses optimal values of the maxima observed ranges<br />of temperature and solution concentration. The process of osmotic dehydration has reduced the initial number of bacteria in meat silver carp. Chemical and sensory analyzes have shown that the sugar beet molasses due to its complex nutritional composition has a better effect on changing the chemical composition and sensory characteristics of the samples.</p>

<p>Ispitivan je proces osmotske dehidratacije mesa<br />svinja u tri osmotska rastvora (vodeni rastvor<br />natrijum hlorida i saharoze, kombinacija<br />vodenog rastvora natrijum hlorida i saharoze i<br />melase i melasa &scaron;ećerne repe) različitih<br />koncentracija, na tri temperature (20&deg;C, 35&deg;C i<br />50&deg;C) i pri tri vremena trajanja procesa (1, 3 i<br />5h). Mereni i računati odzivi procesa osmotske<br />dehidratacije bili su: sadržaj suve materije,<br />gubitak vode, prirast suve materije, indeks<br />efiksanosti procesa, vrednost aktivnosti vode.<br />Rezultati ispitivanja pokazuju da povećanje<br />tehnolo&scaron;kih parametara temperature i vremena<br />procesa, kao i koncentracije osmotskih rastvora<br />dovode do intenziviranja prenosa mase u<br />procesu i povećanja vrednosti odzivnih<br />parametara procesa, u oba slučaja, istostrujne i<br />protivstrujne osmotske dehidratacije.<br />Na osnovu dobijenih rezultata razvijeni su<br />modeli zavisnosti odziva procesa od<br />primenjenih tehnolo&scaron;kih parametara za<br />istostrujne i protivstrujne procese osmotske<br />dehidratacije. &ldquo;Score&rdquo; analizom određene su<br />vrednosti tehnolo&scaron;kih parametara koje su za<br />rezultat dale optimalnu efiksanost procesa.<br />U radu je ispitan enegetski bilans procesa<br />osmotske dehidratacije i upoređen sa<br />konvektivnim su&scaron;enjem, gde su se kao<br />energentski najefikasniji pokazali procesi na<br />temperaturi od 20&deg;C.<br />Karakteristike osmotski dehidriranog svinjskog<br />mesa su pokazale da dolazi do pobolj&scaron;anja<br />mikrobiolo&scaron;kog, hemijskog i nutritivnog profila<br />mesa nakon procesa, kao i promene boje i<br />teksture, gde je melasa &scaron;ećerne repe kao<br />osmotski rastvor, iskazala najbolje uticaje na<br />promene karakteristika dehidiranog mesa.<br />Na osnovu svih ispitanih uticaja variranih<br />parametara kao optimalni parametri procesa<br />mogu da se defini&scaron;u: protivstrujni proces, u<br />trajanju od 5 časova na temperaturi od 20&deg;C, u<br />melasi kao osmotskom rastvoru. Ovakav proces<br />dovodi do sveukupnog pobolj&scaron;anja<br />karakteristika svinjskog mesa uvodeći nutritivna<br />pobolj&scaron;anja iz hemijskog sastava melase u<br />ljudsku ishranu.</p> / <p>Process of osmotic dehydration of pork meat in<br />three different osmotic solutions (sodium<br />chloride and sucrose dissolved in water, mixture<br />of sodium chloride, sucrose dissolved in water<br />and molasses and sugar beet molasses) of<br />different concentrations, at three temperatures<br />(20&deg;C, 35&deg;C &amp; 50&deg;C) and three different times<br />of duration of the process (1, 3 &amp; 5h) was<br />investigated.<br />Measured and calculated responses of the<br />osmotic dehydration process were: dry matter<br />content, water loss, solid gain, dehydration<br />efficiency index and value of water activity.<br />The results showed that the increase of<br />technological parameters: time and temperature<br />of the process, as well as the concentration of<br />the osmotic solutions led to the intensified mass<br />transfer in the process and increased values of<br />process responses, in either co-counter or<br />current processes of osmotic solutions.<br />Based on obtained results mathematical models<br />of dependence of process responses from<br />applied technological parameters for co- and<br />counter-current processes of osmotic<br />dehydrations were developed. By the means of<br />&ldquo;Score&rdquo; analyses the values of technological<br />parameters which produced optimal efficiency<br />of the process were calculated.<br />In this research process energy balance was<br />investigated by comparison to the convective<br />drying, where the highest energy efficiency was<br />determined in the processes at the temperature<br />of 20&deg;C.<br />Characteristics of osmo-dehydrated pork meat<br />were also investigated, pointing at the<br />improvement of microbiological, chemical and<br />nutritive profile of the meat after the process, as<br />well as the change of color and texture, where<br />sugar beet molasses, as an osmotic solution, had<br />shown the best effects on changes of dehydrated<br />meat characteristics.<br />Based on all investigated effects of varied<br />parameters, the optimal process parameters can<br />be defined as: counter-current process, of 5<br />hours duration, at 20&deg;C, in molasses as an<br />osmotic solution. Process like that leads to the<br />total improvement of pork meat characteristics<br />introducing nutritive benefit from molasses<br />chemical composition into human nutrition.</p>

La politique des transports dans le monde et en Europe évolue vers une vision co-modale. Cette nouvelle politique n'oppose plus la voiture au transport public mais encourage une combinaison de tous les modes de transport en espérant ainsi assurer un développement rentable et durable.Nous focalisons notre étude sur le service transport de personnes qui s'inscrit au cœur des politiques co-modales en combinant tous les modes de transport en commun (métro, bus..) et promeut de nouveaux modes d'utilisation de la voiture particulière comme le covoiturage (partage d'un véhicule personnel) ou l'AutoPartage (voiture en libre-service).Toutefois, pour générer un itinéraire exploitant les services de plusieurs opérateurs de transport, il faut consulter plusieurs sites internet. Selon le déplacement à réaliser, cette tâche de planification complexe peut être très difficile à réaliser et ne garantit pas l'optimalité de l'itinéraire sélectionné.Nous nous sommes donc intéressés à la conception d'un système d'aide au déplacement capable de fournir une information voyageur (co-modale) en mettant en relation plusieurs opérateurs de transport (en commun et individuel). Le système en question doit être capable d'assister l'utilisateur dans la phase de planification par la constitution d'un carnet de voyage proposant plusieurs itinéraires multi-opérateurs. De plus, il assiste l'utilisateur en cas de perturbation en l'informant et en lui proposant des itinéraires de secours. Ce travail est basé sur des avancées technologiques qui facilitent l'optimisation dans un environnement distribué (Multi-agent - SOA) et rendent l'information accessible grâce à un grand nombre de médias (téléphone, PDA..)

The main goal of my diploma thesis was to review the amount of iodine in meat of foodanimals. This diploma thesis brings current information about the iodine content in meat in The Czech Republic. The samples were extracted during the years 2004 to 2007. On the whole 63 samples, in which the content of iodine was set by Sandell - Kollthof method, were taken. The average content of iodine in meat was as follows : rabbits 19,2; domestic pigs 16,17; market pigs 16,96; wild pigs 57,72 and deer 38,31 &#61549;g I &#61655; kg-1 wet matter. Regional and seasonal differences were proved.

<p>Uvod: Bronhopulmonalna displazija (BPD) je najče&scaron;ća i najteža respiratorna posledica prematuriteta. Utvrđivanje najznačajnijih faktora rizika za nastanak BPD kod novorođenčadi porođajne mase (PM) ispod 1500g može omogućiti procenu rizika za&nbsp; nastanak bolesti i identifikaciju novorođenčadi u visokom riziku, &scaron;to je važno za pružanje informacija roditeljima o prognozi,&nbsp; planiranje preventivnih i terapijskih mera i stratifikovanje novorođenčadi koja su u riziku za sprovođenje budućih istraživanja. Cilj: Utvrđivanje incidencije, stepena težine BPD, smrtnosti, identifikacija najznačajnijih prenatalnih i postnatalnih faktora rizika za nastanak BPD, konstrukcije modela predikcije za nastanak BPD. Materijal i metode: Istraživanje je sprovedeno na 504&nbsp; prevremeno rođene novorođenčadi PM&lt;1500g koja su rođena u porodili&scaron;tima u AP Vojvodini i lečena u tercijarnom Centru za neonatologiju i intenzivnu negu i terapiju, na Institutu za zdravstvenu za&scaron;titu dece i omladine Vojvodine u periodu od&nbsp; 2006.-2011. godine. Retrospektivno je analizirano prisustvo BPD, prema stepenima težine, smrtnost. Podaci su izdvojeni iz&nbsp; istorija bolesti za svako novorođenče, 30 potencijalnih prenatalnih i postnatalnih faktora je opisano deskriptivnom i univarijantnom statistikom. Statstički najznačajniji faktori su uneti u multifaktorsku logističku regresionu analizu u cilju&nbsp; konstrukcije prediktivnih modela za nastanak BPD u 1.,14. i 21. danu neonatalnog života. Podaci su obrađeni u StatSoft-ovom&nbsp; programskom paketu Statistica 10.0.&nbsp; Validacija modela predikcije je sprovedena u prospektivnom delu istraživanja, na 100&nbsp;&nbsp;&nbsp; prevremeno rođene novorođenčadi&lt;1500g, u periodu od 2012-2013. godine. Rezultati: U retrospektivnom delu&nbsp; istraživanja,&nbsp; od 504&nbsp; novorođenčeta PM&lt;1500 grama, umrlo je 17.65%, BPD je imalo 45.43% (blagu BPD 19.44%, srednje te&scaron;ku 19.84%,&nbsp; te&scaron;ku&nbsp; 6.15%), srednje te&scaron;ku i&nbsp; te&scaron;ku 25.99%.Antenatalna primena kortikosteroida je zastupljena u 47.02%, surfaktant&nbsp;&nbsp; je&nbsp;&nbsp; primenjen kod 69.78% novorođenčadi. Najznačajniji prenatalni prediktivni faktor rizika za nastanak BPD/smrtnog ishoda je horioamnionitis (OR 5.72; 95% CI 3.42-9.62), dok su protektivni faktori: prenatalna primene kortikosteroida (OR&nbsp; 0.41;&nbsp; 95%CI&nbsp; 0.29-0.60), porođaj carskim rezom (OR&nbsp; 0.24; 95% CI 0.16-0.36). Najznačajniji&nbsp; postnatalni prediktivni faktori rizika su: GS&nbsp; (p&asymp;0.00), PM (p&asymp;0.00), reanimacija u porođajnoj sali (OR 7.01; 95% CI 4.12-12.01), rana&nbsp; neonatalna&nbsp; sepsa&nbsp; (OR&nbsp; 7.35;&nbsp; 95%CI&nbsp; 3.79-14.58), RDS&nbsp; (p&asymp;0.00), primena surfaktanta (OR13,3;95%CI 8,2 - 21,67), DAP (OR 4.12; 95%CI&nbsp; 2.47-6.89),&nbsp; dok&nbsp; je&nbsp; ženski&nbsp; pol&nbsp; protektivan (OR&nbsp; 0.61; 95% CI 0.42-0.89). FiO2 i IPPV su u svim posmatranim danima značajni faktori rizika. Primena IPPV u 1. danu (OR 10.71;&nbsp; 95% CI 6.67-17.26); u ostalim danima rizik od BPD raste prema rastućoj invazivnosti respiratorne&nbsp; potpore.&nbsp; Konstruisani su modeli&nbsp; predikcije za 1, 14 i 21. dan života, modeli imaju visoku prediktivnu vrednost: ukupan procenat uspe&scaron;nosti&nbsp; modela je 84.26%-90.80%, modeli sa ne&scaron;to većim uspehom predviđaju&nbsp;&nbsp; prisustvo (85.36%-94.12%), nego odusustvo BPD (81.72-86.56%). OR modela je 28.07-103.04. Modeli su uspe&scaron;no validirani&nbsp; na 102 pacijenta sa ukupnim procentom uspe&scaron;nosti (82-90%), PPV (0.86-0.94) i NPV (0.76-0.87). Zaključak:&nbsp; Kori&scaron;ćenjem&nbsp; prenatalnih i postnatalnih kliničkih podataka moguće je predvideti nastanak BPD ili smrtnog ishoda.</p> / <p>Introduction: Bronchopulmonary dysplasia (BPD) is the most common serious pulmonary morbidity in very low birth weight (VLBW) infants. It is of clinical importance to determine clinical variables that are associated with BPD in order to identify infants who are at risk of developing BPD; it contributes to BPD prevention, may enable prognostic information for parents and future studies design. Objective: The aim of this study was to determine the incidence and severity of BPD, mortality rate in VLBW infants, to identify prenatal and postnatal predictive risk factors for bronchopulmonary dysplasia and competing outcome of death and to develop predictive models. Materials and Methods: Study was conducted in 504 VLBW infants born in the maternity hospitals in Vojvodina and admitted to tertiary Center for newborn and neonatal intensive care at the Institute for Child and Youth Health Care of Vojvodina, from January 2006. to December 2011. Data were retrospectively collected from clinical records for outcomes BPD or death; prenatal and postnatal factors associated with BPD were collected at three postnatal ages and examined by descriptive and univariate statistics; factors that were significantly associated with BPD and/or death were entered into a multivariate logistic regression analysis for develop predictive models. Data were analyzed using StatSoft&#39;s software package Statistica 10.0. Validation of the models were conducted in a prospective study in 102 VLBW infants born from January 2012. to December 2013. Results: There were 504 very low birth weight infants who were eligible for this study, 17.65% died, 45.43% developed BPD (mild BPD 19.44%, moderate 19.84%, severe 6.15%), moderate and severe 25.99%. The mean birth weight for the cohort was 1125.6&plusmn;280.9g, the mean gestation age was GS 28,78&plusmn;3,01, 49.21% were male. Surfactant received 69.78%, antenatal steroids 47.02% newborns. Key risk factors for BPD and/or death were: chorioamnionitis and maternal infections at delivery (OR 5.72; 95% CI 3.42-9.62); protective prenatal factors were: antenatal corticosteroid therapy (OR 0.41; 95%CI 0.29-0.60), cesarean delivery (OR 0.24; 95% CI 0.16-0.36). Postnatal rick factors were: GS (p&asymp;0.00), birth weight (p&asymp;0.00), delivery room resuscitation (OR 7.01; 95% CI 4.12-12.01), early neonatal sepsis (OR 7.35; 95%CI 3.79-14.58), RDS (p&asymp;0.00), surfactant (OR13,3;95%CI 8,2 - 21,67), DAP (OR4.12; 95% CI 2.47-6.89), while female gender was protective (OR 0.61; 95% CI 0.42-0.89). At each time point studied, FiO2 was significantly higher in BPD/death, as well as respiratory support; on the first day invasive respiratory support was significantly associated with BPD/death (IPPV and HFOV) (OR 10.71; 95% CI 6.67-17.26), in other days BPD was associated with increasing invasiveness of respiratory support. In multifactorial logistic regression analysis separately predictive models were developed at three postnatal ages, at 1st, 14th and 21st day. Models had high predictive performance: total success of the models were 84.26% - 90.80%, models successfully predicted the presence of BPD in 85.36% -94.12%, absence of the BPD in 81.72 - 86.56% cases. OR of models were 28.07-103.04. The models were successfully validated on 102 patients with a total percentage of success 82 - 90%, with PPV 0.86-0.94 and NPV 0.76-0.87. Conclusion: Using prenatal and postnatal clinical data it is possible to predict the development of BPD and/or death in very low birth weight infants. It is very important to identify risk factors for BPD development in order to decrease the incidence of BPD and mortality rate.</p>