Predicting preterm birth in maternity care by means of data mining

Worldwide, around 9% of the children are born with less than 37 weeks of labour, causing risk to the premature child, whom it is not prepared to develop a number of basic functions that begin soon after the birth. In order to ensure that those risk pregnancies are being properly monitored by the obstetricians in time to avoid those problems, Data Mining (DM) models were induced in this study to predict preterm births in a real environment using data from 3376 patients (women) admitted in the maternal and perinatal care unit of Centro Hospitalar of Oporto. A sensitive metric to predict preterm deliveries was developed, assisting physicians in the decision-making process regarding the patients’ observation. It was possible to obtain promising results, achieving sensitivity and specificity values of 96% and 98%, respectively.

Uma ferramenta para cálculo da máxima intensidade da ilha de calor noturna

O objetivo deste artigo é verificar a influência da geometria urbana na intensidade de ilhas de calor noturnas com uso de uma ferramenta computacional desenvolvida como extensão de um SIG. O método deste trabalho está dividido em três principais etapas: desenvolvimento da ferramenta, calibração do modelo e simulação de cenários hipotéticos com diferentes geometrias urbanas. Um modelo simplificado que relaciona as intensidades máximas de ilha de calor urbana (ICUmáx) com a geometria urbana foi incorporado à subrotina de cálculo e, posteriormente, adaptado para fornecer resultados mais aproximados à realidade de duas cidades brasileiras, as quais serviram de base para a calibração do modelo. A comparação entre dados reais e simulados mostraram uma diferença no aumento da ICUmáx em função da relação H/W e da faixa de comprimento de rugosidade (Z0). Com a ferramenta já calibrada, foi realizada uma simulação de diferentes cenários urbanos, demonstrando que o modelo simplificado original subestima valores de ICUmáx para as configurações de cânions urbanos de Z0 < 2,0 e superestima valores de ICUmáx para as configurações de cânions urbanos de Z0 ≥ 2,0. Além disso, este estudo traz como contribuição à verificação de que cânions urbanos com maiores áreas de fachadas e com alturas de edificações mais heterogêneas resultam em ICUmáx menores em relação aos cânions mais homogêneos e com maiores áreas médias ocupadas pelas edificações, para um mesmo valor de relação H/W. Essa diferença pode ser explicada pelos diferentes efeitos na turbulência dos ventos e nas áreas sombreadas provocados pela geometria urbana.

Critical events in mechanically ventilated patients

Mechanical Ventilation is an artificial way to help a Patient to breathe. This procedure is used to support patients with respiratory diseases however in many cases it can provoke lung damages, Acute Respiratory Diseases or organ failure. With the goal to early detect possible patient breath problems a set of limit values was defined to some variables monitored by the ventilator (Average Ventilation Pressure, Compliance Dynamic, Flow, Peak, Plateau and Support Pressure, Positive end-expiratory pressure, Respiratory Rate) in order to create critical events. A critical event is verified when a patient has a value higher or lower than the normal range defined for a certain period of time. The values were defined after elaborate a literature review and meeting with physicians specialized in the area. This work uses data streaming and intelligent agents to process the values collected in real-time and classify them as critical or not. Real data provided by an Intensive Care Unit were used to design and test the solution. In this study it was possible to understand the importance of introduce critical events for Mechanically Ventilated Patients. In some cases a value is considered critical (can trigger an alarm) however it is a single event (instantaneous) and it has not a clinical significance for the patient. The introduction of critical events which crosses a range of values and a pre-defined duration contributes to improve the decision-making process by decreasing the number of false positives and having a better comprehension of the patient condition.

Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Combining data mining and evolutionary computation for multi-criteria optimization of earthworks

Earthworks tasks aim at levelling the ground surface at a target construction area and precede any kind of structural construction (e.g., road and railway construction). It is comprised of sequential tasks, such as excavation, transportation, spreading and compaction, and it is strongly based on heavy mechanical equipment and repetitive processes. Under this context, it is essential to optimize the usage of all available resources under two key criteria: the costs and duration of earthwork projects. In this paper, we present an integrated system that uses two artificial intelligence based techniques: data mining and evolutionary multi-objective optimization. The former is used to build data-driven models capable of providing realistic estimates of resource productivity, while the latter is used to optimize resource allocation considering the two main earthwork objectives (duration and cost). Experiments held using real-world data, from a construction site, have shown that the proposed system is competitive when compared with current manual earthwork design.

A domain-specific language for ETL patterns specification in Data Warehousing Systems

During the last few years many research efforts have been done to improve the design of ETL (Extract-Transform-Load) systems. ETL systems are considered very time-consuming, error-prone and complex involving several participants from different knowledge domains. ETL processes are one of the most important components of a data warehousing system that are strongly influenced by the complexity of business requirements, their changing and evolution. These aspects influence not only the structure of a data warehouse but also the structures of the data sources involved with. To minimize the negative impact of such variables, we propose the use of ETL patterns to build specific ETL packages. In this paper, we formalize this approach using BPMN (Business Process Modelling Language) for modelling more conceptual ETL workflows, mapping them to real execution primitives through the use of a domain-specific language that allows for the generation of specific instances that can be executed in an ETL commercial tool.

Using relational algebra on the specification of real world ETL processes

Modeling Extract-Transform-Load (ETL) processes of a Data Warehousing System has always been a challenge. The heterogeneity of the sources, the quality of the data obtained and the conciliation process are some of the issues that must be addressed in the design phase of this critical component. Commercial ETL tools often provide proprietary diagrammatic components and modeling languages that are not standard, thus not providing the ideal separation between a modeling platform and an execution platform. This separation in conjunction with the use of standard notations and languages is critical in a system that tends to evolve through time and which cannot be undermined by a normally expensive tool that becomes an unsatisfactory component. In this paper we demonstrate the application of Relational Algebra as a modeling language of an ETL system as an effort to standardize operations and provide a basis for uncommon ETL execution platforms.

Predicting type of delivery by identification of obstetric risk factors through data mining

In Maternity Care, a quick decision has to be made about the most suitable delivery type for the current patient. Guidelines are followed by physicians to support that decision; however, those practice recommendations are limited and underused. In the last years, caesarean delivery has been pursued in over 28% of pregnancies, and other operative techniques regarding specific problems have also been excessively employed. This study identifies obstetric and pregnancy factors that can be used to predict the most appropriate delivery technique, through the induction of data mining models using real data gathered in the perinatal and maternal care unit of Centro Hospitalar of Oporto (CHP). Predicting the type of birth envisions high-quality services, increased safety and effectiveness of specific practices to help guide maternity care decisions and facilitate optimal outcomes in mother and child. In this work was possible to acquire good results, achieving sensitivity and specificity values of 90.11% and 80.05%, respectively, providing the CHP with a model capable of correctly identify caesarean sections and vaginal deliveries.

Strategic planning of electricity systems: Integrating renewable energies

Tese de Doutoramento - Programa Doutoral em Engenharia Industrial e Sistemas (PDEIS)

Methodology for real-time adaptation of tunnels support using the observational method

The observational method in tunnel engineering allows the evaluation in real time of the actual conditions of the ground and to take measures if its behavior deviates considerably from predictions. However, it lacks a consistent and structured methodology to use the monitoring data to adapt the support system in real time. The definition of limit criteria above which adaptation is required are not defined and complex inverse analysis procedures (Rechea et al. 2008, Levasseur et al. 2010, Zentar et al. 2001, Lecampion et al. 2002, Finno and Calvello 2005, Goh 1999, Cui and Pan 2012, Deng et al. 2010, Mathew and Lehane 2013, Sharifzadeh et al. 2012, 2013) may be needed to consistently analyze the problem. In this paper a methodology for the real time adaptation of the support systems during tunneling is presented. In a first step limit criteria for displacements and stresses are proposed. The methodology uses graphics that are constructed during the project stage based on parametric calculations to assist in the process and when these graphics are not available, since it is not possible to predict every possible scenario, inverse analysis calculations are carried out. The methodology is applied to the “Bois de Peu” tunnel which is composed by two tubes with over 500 m long. High uncertainty levels existed concerning the heterogeneity of the soil and consequently in the geomechanical design parameters. The methodology was applied in four sections and the results focus on two of them. It is shown that the methodology has potential to be applied in real cases contributing for a consistent approach of a real time adaptation of the support system and highlight the importance of the existence of good quality and specific monitoring data to improve the inverse analysis procedure.

Discrimination of Brazilian propolis according to the seasoning using chemometrics and machine learning based on UV-Vis scanning data

Propolis is a chemically complex biomass produced by honeybees (Apis mellifera) from plant resins added of salivary enzymes, beeswax, and pollen. The biological activities described for propolis were also identified for donor plants resin, but a big challenge for the standardization of the chemical composition and biological effects of propolis remains on a better understanding of the influence of seasonality on the chemical constituents of that raw material. Since propolis quality depends, among other variables, on the local flora which is strongly influenced by (a)biotic factors over the seasons, to unravel the harvest season effect on the propolis chemical profile is an issue of recognized importance. For that, fast, cheap, and robust analytical techniques seem to be the best choice for large scale quality control processes in the most demanding markets, e.g., human health applications. For that, UV-Visible (UV-Vis) scanning spectrophotometry of hydroalcoholic extracts (HE) of seventy-three propolis samples, collected over the seasons in 2014 (summer, spring, autumn, and winter) and 2015 (summer and autumn) in Southern Brazil was adopted. Further machine learning and chemometrics techniques were applied to the UV-Vis dataset aiming to gain insights as to the seasonality effect on the claimed chemical heterogeneity of propolis samples determined by changes in the flora of the geographic region under study. Descriptive and classification models were built following a chemometric approach, i.e. principal component analysis (PCA) and hierarchical clustering analysis (HCA) supported by scripts written in the R language. The UV-Vis profiles associated with chemometric analysis allowed identifying a typical pattern in propolis samples collected in the summer. Importantly, the discrimination based on PCA could be improved by using the dataset of the fingerprint region of phenolic compounds ( = 280-400m), suggesting that besides the biological activities of those secondary metabolites, they also play a relevant role for the discrimination and classification of that complex matrix through bioinformatics tools. Finally, a series of machine learning approaches, e.g., partial least square-discriminant analysis (PLS-DA), k-Nearest Neighbors (kNN), and Decision Trees showed to be complementary to PCA and HCA, allowing to obtain relevant information as to the sample discrimination.

Extreme value Birnbaum-Saunders regression models applied to environmental data

Extreme value models are widely used in different areas. The Birnbaum–Saunders distribution is receiving considerable attention due to its physical arguments and its good properties. We propose a methodology based on extreme value Birnbaum–Saunders regression models, which includes model formulation, estimation, inference and checking. We further conduct a simulation study for evaluating its performance. A statistical analysis with real-world extreme value environmental data using the methodology is provided as illustration.

Poker learner: modelação de jogadores através de data mining

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

A crescente internacionalização do setor do vinho português: o caso da Adega Cooperativa de Vila Real

Relatório de estágio de mestrado em Negócios Internacionais