Urban change monitoring using GIS and remote sensing tools in Kathmandu valley (Nepal)

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies

Prognostic modelling of breast cancer patients: a benchmark of predictive models with external validation

Dissertação apresentada para obtenção do Grau de Doutor em Engenharia Electrotécnica e de Computadores – Sistemas Digitais e Percepcionais pela Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia

Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

Contribuição da produção em regime especial na garantia do abastecimento de energia elétrica e o impacto no planeamento da rede

Esta dissertação apresenta um estudo sobre a garantia de fornecimento de energia elétrica por parte dos produtores em regime especial com tecnologia cogeração e o impacto que estes traduzem na fase de planeamento da rede. Este trabalho foi realizado na Energias de Portugal - Distribuição (EDP-D) na direção de planeamento da rede (DPL). Para este estudo foi utilizado o caso de uma subestação com dezoito produtores em regime especial agregados à sua rede, em que dezasseis desses produtores são cogeração. A proposta de estudo para o caso concreto, passa pela análise das condições de funcionamento da subestação e apurar se a mesma necessita de alguma reformulação, tendo em vista as cargas a satisfazer atuais e possível incremento de carga futura. Considerando que a subestação está inserida num ambiente industrial e atendendo que existem diversos produtores de energia elétrica nas imediações da subestação. Para a resolução da garantia do fornecimento de energia por parte da cogeração, estudou-se a possibilidade de prever a energia produzida por estes produtores, através dos seguintes modelos de previsão: árvore de regressão, árvore de regressão com aplicação bagging e uma rede neuronal (unidirecional). Com a implementação destes modelos pretende-se estimar qual a potência que se pode esperar na garantia de abastecimento da carga, prevenindo maior solicitação de potência por parte da subestação. A metodologia utilizada baseia-se em simulações computacionais.

Multi-scale vegetation classification using earth observation data of the Sundarban mangrove forest, Bangladesh.

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Analysing and visualising areal crime data. A case study of residential burglary in San Francisco, USA

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Classificação de sons urbanos usando motifs e MFCC

A classificação automática de sons urbanos é importante para o monitoramento ambiental. Este trabalho apresenta uma nova metodologia para classificar sons urbanos, que se baseia na descoberta de padrões frequentes (motifs) nos sinais sonoros e utiliza-los como atributos para a classificação. Para extrair os motifs é utilizado um método de descoberta multi-resolução baseada em SAX. Para a classificação são usadas árvores de decisão e SVMs. Esta nova metodologia é comparada com outra bastante utilizada baseada em MFCC. Para a realização de experiências foi utilizado o dataset UrbanSound disponível publicamente. Realizadas as experiências, foi possível concluir que os atributos motif são melhores que os MFCC a discriminar sons com timbres semelhantes e que os melhores resultados são conseguidos com ambos os tipos de atributos combinados. Neste trabalho foi também desenvolvida uma aplicação móvel para Android que permite utilizar os métodos de classificação desenvolvidos num contexto de vida real e expandir o dataset.

American Society of Anesthesiologists Score: Still Useful After 60 Years? Results of the EuSOS Study

OBJECTIVE: The European Surgical Outcomes Study described mortality following in-patient surgery. Several factors were identified that were able to predict poor outcomes in a multivariate analysis. These included age, procedure urgency, severity and type and the American Association of Anaesthesia score. This study describes in greater detail the relationship between the American Association of Anaesthesia score and postoperative mortality. METHODS: Patients in this 7-day cohort study were enrolled in April 2011. Consecutive patients aged 16 years and older undergoing inpatient non-cardiac surgery with a recorded American Association of Anaesthesia score in 498 hospitals across 28 European nations were included and followed up for a maximum of 60 days. The primary endpoint was in-hospital mortality. Decision tree analysis with the CHAID (SPSS) system was used to delineate nodes associated with mortality. RESULTS: The study enrolled 46,539 patients. Due to missing values, 873 patients were excluded, resulting in the analysis of 45,666 patients. Increasing American Association of Anaesthesia scores were associated with increased admission rates to intensive care and higher mortality rates. Despite a progressive relationship with mortality, discrimination was poor, with an area under the ROC curve of 0.658 (95% CI 0.642 - 0.6775). Using regression trees (CHAID), we identified four discrete American Association of Anaesthesia nodes associated with mortality, with American Association of Anaesthesia 1 and American Association of Anaesthesia 2 compressed into the same node. CONCLUSION: The American Association of Anaesthesia score can be used to determine higher risk groups of surgical patients, but clinicians cannot use the score to discriminate between grades 1 and 2. Overall, the discriminatory power of the model was less than acceptable for widespread use.

Intravenous Busulfan for Autologous Stem Cell Transplantation in Adult Patients with Acute Myeloid Leukemia: a Survey of 952 Patients on Behalf of the Acute Leukemia Working Party of the European Group for Blood and Marrow Transplantation

Oral busulfan is the historical backbone of the busulfan+cyclophosphamide regimen for autologous stem cell transplantation. However intravenous busulfan has more predictable pharmacokinetics and less toxicity than oral busulfan; we, therefore, retrospectively analyzed data from 952 patients with acute myeloid leukemia who received intravenous busulfan for autologous stem cell transplantation. Most patients were male (n=531, 56%), and the median age at transplantation was 50.5 years. Two-year overall survival, leukemia-free survival, and relapse incidence were 67±2%, 53±2%, and 40±2%, respectively. The non-relapse mortality rate at 2 years was 7±1%. Five patients died from veno-occlusive disease. Overall leukemia-free survival and relapse incidence at 2 years did not differ significantly between the 815 patients transplanted in first complete remission (52±2% and 40±2%, respectively) and the 137 patients transplanted in second complete remission (58±5% and 35±5%, respectively). Cytogenetic risk classification and age were significant prognostic factors: the 2-year leukemia-free survival was 63±4% in patients with good risk cytogenetics, 52±3% in those with intermediate risk cytogenetics, and 37 ± 10% in those with poor risk cytogenetics (P=0.01); patients ≤50 years old had better overall survival (77±2% versus 56±3%; P<0.001), leukemia-free survival (61±3% versus 45±3%; P<0.001), relapse incidence (35±2% versus 45±3%; P<0.005), and non-relapse mortality (4±1% versus 10±2%; P<0.001) than older patients. The combination of intravenous busulfan and high-dose melphalan was associated with the best overall survival (75±4%). Our results suggest that the use of intravenous busulfan simplifies the autograft procedure and confirm the usefulness of autologous stem cell transplantation in acute myeloid leukemia. As in allogeneic transplantation, veno-occlusive disease is an uncommon complication after an autograft using intravenous busulfan.

Heritages, Identities, and Policy in the Metropolitan Area of Lisbon

In a world that has moved away from narratives based on the idea of progress, the past has established itself as a place of reference: confirming to ourselves that what we were is indispensible for sustaining what we think we are. The recovery of the past is thus one of the most common symbolic instruments used in negotiating identities. The cultural practices that have recourse to representation mechanisms that call on the past in order to consider the present always end up translating themselves, insofar as they fragment, reorganize and interpret it in their transformation, or, to use a formula that has become unavoidable, in their “invention”. Patrimonialization is one such practice. It associates the notion of heritage – which is not a given fact, but rather a socially constructed classification, and therefore one that is constantly being negotiated – with specific objects that come to serve as cultural representations of the groups who consider themselves to be their rightful owners. In the Lisbon Metropolitan Area, as in other ethnographic contexts, patrimonialization encompasses things as diverse as landscapes, monuments, popular architecture, handicrafts, local feast days/processions/pilgrimages and people; all things that can, once transformed into material representations of the past, serve as arguments for the identity fictions of the people who inhabit them.

Concordance between expected and observed bacilloscopy results of clinical forms of leprosy: a 6-year retrospective study in Recife, State of Pernambuco, Brazil

INTRODUCTION: Operational classification of leprosy based on the number of skin lesions was conceived to screen patients presenting severe forms of the disease to enable their reception of a more intense multidrug regimen without having to undergo lymph smear testing. We evaluated the concordance between operational classification and bacilloscopy to define multibacillary and paucibacillary leprosy. METHODS: We selected 1,213 records of individuals with leprosy, who were untreated (new cases) and admitted to a dermatology clinic in Recife, Brazil, from 2000 to 2005, and who underwent bacteriological examination at diagnosis for ratification of the operational classification. RESULTS: Compared to bacilloscopy, operational classification demonstrated 88.6% sensitivity, 76.9% specificity, a positive predictive value of 61.8%, and a negative predictive value of 94.1%, with 80% accuracy and a moderate kappa index. Among the bacilloscopy-negative cases, 23% had more than 5 skin lesions. Additionally, 11% of the bacilloscopy-positive cases had up to 5 lesions, which would have led to multibacillary cases being treated as paucibacillary leprosy if the operational classification had not been confirmed by bacilloscopy. CONCLUSIONS: Operational classification has limitations that are more obvious in borderline cases, suggesting that in these cases, lymph smear testing is advisable to enable the selection of true multibacillary cases for more intense treatment, thereby contributing to minimization of resistant strain selection and possible relapse.

The relationship between the education level of successor's and the firm performance in German publicly listed family firms- an empirical analysis

The purpose of this thesis is to investigate how far the education level of the second or third generation of publicly traded German family firms affects the post-succession firm performance. By conducting a correlational and regression design, the aim is to examine how several variables influence the performance of family firms. Performance measures, for example ROA and Tobin’s q and variables, like Education level and succession periods, examine analytically that a positive succession trend will occur. However, with the used model, only a less rigid model shows empirical evidence.

Assessment of Myocardial Infarction by Cardiac Magnetic Resonance Imaging and Long-Term Mortality

Background: Cardiac magnetic resonance imaging provides detailed anatomical information on infarction. However, few studies have investigated the association of these data with mortality after acute myocardial infarction. Objective: To study the association between data regarding infarct size and anatomy, as obtained from cardiac magnetic resonance imaging after acute myocardial infarction, and long-term mortality. Methods: A total of 1959 reports of “infarct size” were identified in 7119 cardiac magnetic resonance imaging studies, of which 420 had clinical and laboratory confirmation of previous myocardial infarction. The variables studied were the classic risk factors – left ventricular ejection fraction, categorized ventricular function, and location of acute myocardial infarction. Infarct size and acute myocardial infarction extent and transmurality were analyzed alone and together, using the variable named “MET-AMI”. The statistical analysis was carried out using the elastic net regularization, with the Cox model and survival trees. Results: The mean age was 62.3 ± 12 years, and 77.3% were males. During the mean follow-up of 6.4 ± 2.9 years, there were 76 deaths (18.1%). Serum creatinine, diabetes mellitus and previous myocardial infarction were independently associated with mortality. Age was the main explanatory factor. The cardiac magnetic resonance imaging variables independently associated with mortality were transmurality of acute myocardial infarction (p = 0.047), ventricular dysfunction (p = 0.0005) and infarcted size (p = 0.0005); the latter was the main explanatory variable for ischemic heart disease death. The MET-AMI variable was the most strongly associated with risk of ischemic heart disease death (HR: 16.04; 95%CI: 2.64-97.5; p = 0.003). Conclusion: The anatomical data of infarction, obtained from cardiac magnetic resonance imaging after acute myocardial infarction, were independently associated with long-term mortality, especially for ischemic heart disease death.

Knowledge, networks of cities and growth in regional urban systems

The objective of this paper is to measure the impact of different kinds of knowledge and external economies on urban growth in an intraregional context. The main hypothesis is that knowledge leads to growth, and that this knowledge is related to the existence of agglomeration and network externalities in cities. We develop a three-tage methodology: first, we measure the amount and growth of knowledge in cities using the OCDE (2003) classification and employment data; second, we identify the spatial structure of the area of analysis (networks of cities); third, we combine the Glaeser - Henderson - De Lucio models with spatial econometric specifications in order to contrast the existence of spatially static (agglomeration) and spatially dynamic (network) external economies in an urban growth model. Results suggest that higher growth rates are associated to higher levels of technology and knowledge. The growth of the different kinds of knowledge is related to local and spatial factors (agglomeration and network externalities) and each knowledge intensity shows a particular response to these factors. These results have implications for policy design, since we can forecast and intervene on local knowledge development paths.

Outcomes of disconnective surgery in intractable pediatric hemispheric and subhemispheric epilepsy.

Objectives: To study the outcome of disconnective epilepsy surgery for intractable hemispheric and sub-hemispheric pediatric epilepsy. Methods: A retrospective analysis of the epilepsy surgery database was done in all children (age <18 years) who underwent a peri-insular hemispherotomy (PIH) or a peri-insular posterior quadrantectomy (PIPQ) from April 2000 to March 2011. All patients underwent a detailed pre surgical evaluation. Seizure outcome was assessed by the Engel's classification and cognitive skills by appropriate measures of intelligence that were repeated annually. Results: There were 34 patients in all. Epilepsy was due to Rasmussen's encephalitis (RE), Infantile hemiplegia seizure syndrome (IHSS), Hemimegalencephaly (HM), Sturge Weber syndrome (SWS) and due to post encephalitic sequelae (PES). Twenty seven (79.4%) patients underwent PIH and seven (20.6%) underwent PIPQ. The mean follow up was 30.5 months. At the last follow up, 31 (91.1%) were seizure free. The age of seizure onset and etiology of the disease causing epilepsy were predictors of a Class I seizure outcome. Conclusions: There is an excellent seizure outcome following disconnective epilepsy surgery for intractable hemispheric and subhemispheric pediatric epilepsy. An older age of seizure onset, RE, SWS and PES were good predictors of a Class I seizure outcome.