Quality of process modeling using BPMN: a model-driven approach

Dissertação para obtenção do Grau de Doutor em Engenharia Informática

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.

An integrated system for human action recognition from video using hidden Markov model

In this paper, we present an integrated system for real-time automatic detection of human actions from video. The proposed approach uses the boundary of humans as the main feature for recognizing actions. Background subtraction is performed using Gaussian mixture model. Then, features are extracted from silhouettes and Vector Quantization is used to map features into symbols (bag of words approach). Finally, actions are detected using the Hidden Markov Model. The proposed system was validated using a newly collected real- world dataset. The obtained results show that the system is capable of achieving robust human detection, in both indoor and outdoor environments. Moreover, promising classification results were achieved when detecting two basic human actions: walking and sitting.

Child abuse monitor system model: a health care critical knowledge monitor system

The Childhood protection is a subject with high value for the society, but, the Child Abuse cases are difficult to identify. The process from suspicious to accusation is very difficult to achieve. It must configure very strong evidences. Typically, Health Care services deal with these cases from the beginning where there are evidences based on the diagnosis, but they aren’t enough to promote the accusation. Besides that, this subject it’s highly sensitive because there are legal aspects to deal with such as: the patient privacy, paternity issues, medical confidentiality, among others. We propose a Child Abuses critical knowledge monitor system model that addresses this problem. This decision support system is implemented with a multiple scientific domains: to capture of tokens from clinical documents from multiple sources; a topic model approach to identify the topics of the documents; knowledge management through the use of ontologies to support the critical knowledge sensibility concepts and relations such as: symptoms, behaviors, among other evidences in order to match with the topics inferred from the clinical documents and then alert and log when clinical evidences are present. Based on these alerts clinical personnel could analyze the situation and take the appropriate procedures.

Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables

Lecture Notes in Computer Science, 9273

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.

Poker learner: modelação de jogadores através de data mining

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

Modelling tyre-road noise with data mining techniques

The research aimed to establish tyre-road noise models by using a Data Mining approach that allowed to build a predictive model and assess the importance of the tested input variables. The data modelling took into account three learning algorithms and three metrics to define the best predictive model. The variables tested included basic properties of pavement surfaces, macrotexture, megatexture, and uneven- ness and, for the first time, damping. Also, the importance of those variables was measured by using a sensitivity analysis procedure. Two types of models were set: one with basic variables and another with complex variables, such as megatexture and damping, all as a function of vehicles speed. More detailed models were additionally set by the speed level. As a result, several models with very good tyre-road noise predictive capacity were achieved. The most relevant variables were Speed, Temperature, Aggregate size, Mean Profile Depth, and Damping, which had the highest importance, even though influenced by speed. Megatexture and IRI had the lowest importance. The applicability of the models developed in this work is relevant for trucks tyre-noise prediction, represented by the AVON V4 test tyre, at the early stage of road pavements use. Therefore, the obtained models are highly useful for the design of pavements and for noise prediction by road authorities and contractors.

The Data Mining applied for the prediction of highway roughness due to overloaded trucks

Currently, the quality of the Indonesian national road network is inadequate due to several constraints, including overcapacity and overloaded trucks. The high deterioration rate of the road infrastructure in developing countries along with major budgetary restrictions and high growth in traffic have led to an emerging need for improving the performance of the highway maintenance system. However, the high number of intervening factors and their complex effects require advanced tools to successfully solve this problem. The high learning capabilities of Data Mining (DM) are a powerful solution to this problem. In the past, these tools have been successfully applied to solve complex and multi-dimensional problems in various scientific fields. Therefore, it is expected that DM can be used to analyze the large amount of data regarding the pavement and traffic, identify the relationship between variables, and provide information regarding the prediction of the data. In this paper, we present a new approach to predict the International Roughness Index (IRI) of pavement based on DM techniques. DM was used to analyze the initial IRI data, including age, Equivalent Single Axle Load (ESAL), crack, potholes, rutting, and long cracks. This model was developed and verified using data from an Integrated Indonesia Road Management System (IIRMS) that was measured with the National Association of Australian State Road Authorities (NAASRA) roughness meter. The results of the proposed approach are compared with the IIRMS analytical model adapted to the IRI, and the advantages of the new approach are highlighted. We show that the novel data-driven model is able to learn (with high accuracy) the complex relationships between the IRI and the contributing factors of overloaded trucks

A Data mining approach to indirect inference

Consider a model with parameter phi, and an auxiliary model with parameter theta. Let phi be a randomly sampled from a given density over the known parameter space. Monte Carlo methods can be used to draw simulated data and compute the corresponding estimate of theta, say theta_tilde. A large set of tuples (phi, theta_tilde) can be generated in this manner. Nonparametric methods may be use to fit the function E(phi|theta_tilde=a), using these tuples. It is proposed to estimate phi using the fitted E(phi|theta_tilde=theta_hat), where theta_hat is the auxiliary estimate, using the real sample data. This is a consistent and asymptotically normally distributed estimator, under certain assumptions. Monte Carlo results for dynamic panel data and vector autoregressions show that this estimator can have very attractive small sample properties. Confidence intervals can be constructed using the quantiles of the phi for which theta_tilde is close to theta_hat. Such confidence intervals are found to have very accurate coverage.

Municipal distribution of bladder cancer mortality in Spain: Possible role of mining and industry

BACKGROUND Spain shows the highest bladder cancer incidence rates in men among European countries. The most important risk factors are tobacco smoking and occupational exposure to a range of different chemical substances, such as aromatic amines. METHODS This paper describes the municipal distribution of bladder cancer mortality and attempts to "adjust" this spatial pattern for the prevalence of smokers, using the autoregressive spatial model proposed by Besag, York and Molliè, with relative risk of lung cancer mortality as a surrogate. RESULTS It has been possible to compile and ascertain the posterior distribution of relative risk for bladder cancer adjusted for lung cancer mortality, on the basis of a single Bayesian spatial model covering all of Spain's 8077 towns. Maps were plotted depicting smoothed relative risk (RR) estimates, and the distribution of the posterior probability of RR>1 by sex. Towns that registered the highest relative risks for both sexes were mostly located in the Provinces of Cadiz, Seville, Huelva, Barcelona and Almería. The highest-risk area in Barcelona Province corresponded to very specific municipal areas in the Bages district, e.g., Suría, Sallent, Balsareny, Manresa and Cardona. CONCLUSION Mining/industrial pollution and the risk entailed in certain occupational exposures could in part be dictating the pattern of municipal bladder cancer mortality in Spain. Population exposure to arsenic is a matter that calls for attention. It would be of great interest if the relationship between the chemical quality of drinking water and the frequency of bladder cancer could be studied.

Proposta d'un model predictiu del risc d'ingrés hospitalari amb l'ús d'algoritmes bayesians

Model predictiu basat en xarxes bayesianes que permet identificar els pacients amb major risc d'ingrés a un hospital segons una sèrie d'atributs de dades demogràfiques i clíniques.

The sandstone-hosted Beverley uranium Deposit, Lake Frome Basin, South Australia: Mineralogy, geochemistry, and a time-constrained model for its genesis

The sandstone-hosted Beverley uranium deposit is located in terrestrial sediments in the Lake Frome basin in the North Flinders Ranges, South Australia. The deposit is 13 km from the U-rich Mesoproterozoic basement of the Mount Painter inlier, which is being uplifted 100 to 200 m above the basin by neotectonic activity that probably initiated in the early Pliocene. The mineralization was deposited mainly in organic matter-poor Miocene lacustrine sands and partly in the underlying reductive strata comprising organic matter-rich clays and silts. The bulk of the mineralization consists of coffinite and/or uraninite nodules, growing around Co-rich pyrite with an S isotope composition (delta S-34 = 1.0 +/- 0.3 parts per thousand), suggestive of an early diagenetic lacustrine origin. In contrast, authigenic sulfides in the bulk of the sediments have a negative S isotope signature (delta S-34 ranges from -26.2 to -35.5 parts per thousand), indicative of an origin via bacterially mediated sulfate reduction. Minor amounts of Zn-bearing native copper and native lead also support the presence of specific, reducing microenvironments in the ore zone. Small amounts of carnotite are associated with the coffinite ore and also occur beneath a paleosoil horizon overlying the uranium deposit. Provenance studies suggest that the host Miocene sediments were derived from the reworking of Early Cretaceous glacial or glaciolacustrine sediments ultimately derived from Paleozoic terranes in eastern Australia. In contrast, the overlying Pliocene strata were in part derived from the Mesoproterozoic basement inlier. Mass-balance and geochemical data confirm that granites of the Mount Painter domain were the ultimate source of U and BEE at Beverley. U-Pb dating of coffinite and carnotite suggest that the U mineralization is Pliocene (6.7-3.4 Ma). The suitability of the Beverley deposit for efficient mining via in situ leaching, and hence its economic value, are determined by the nature of the hosting sand unit, which provides the permeability and low reactivity required for high fluid flow and low chemical consumption. These favorable sedimentologic and geometrical features result from a complex conjunction of factors, including deposition in lacustrine shore environment, reworking of angular sands of glacial origin, deep Pliocene weathering, and proximity to an active fault exposing extremely U rich rocks.

Community Policing in Switzerland's Major Urban Areas: An Observational Study of the Implementation and Impact Using Geospatial Data Mining

La présente étude est à la fois une évaluation du processus de la mise en oeuvre et des impacts de la police de proximité dans les cinq plus grandes zones urbaines de Suisse - Bâle, Berne, Genève, Lausanne et Zurich. La police de proximité (community policing) est à la fois une philosophie et une stratégie organisationnelle qui favorise un partenariat renouvelé entre la police et les communautés locales dans le but de résoudre les problèmes relatifs à la sécurité et à l'ordre public. L'évaluation de processus a analysé des données relatives aux réformes internes de la police qui ont été obtenues par l'intermédiaire d'entretiens semi-structurés avec des administrateurs clés des cinq départements de police, ainsi que dans des documents écrits de la police et d'autres sources publiques. L'évaluation des impacts, quant à elle, s'est basée sur des variables contextuelles telles que des statistiques policières et des données de recensement, ainsi que sur des indicateurs d'impacts construit à partir des données du Swiss Crime Survey (SCS) relatives au sentiment d'insécurité, à la perception du désordre public et à la satisfaction de la population à l'égard de la police. Le SCS est un sondage régulier qui a permis d'interroger des habitants des cinq grandes zones urbaines à plusieurs reprises depuis le milieu des années 1980. L'évaluation de processus a abouti à un « Calendrier des activités » visant à créer des données de panel permettant de mesurer les progrès réalisés dans la mise en oeuvre de la police de proximité à l'aide d'une grille d'évaluation à six dimensions à des intervalles de cinq ans entre 1990 et 2010. L'évaluation des impacts, effectuée ex post facto, a utilisé un concept de recherche non-expérimental (observational design) dans le but d'analyser les impacts de différents modèles de police de proximité dans des zones comparables à travers les cinq villes étudiées. Les quartiers urbains, délimités par zone de code postal, ont ainsi été regroupés par l'intermédiaire d'une typologie réalisée à l'aide d'algorithmes d'apprentissage automatique (machine learning). Des algorithmes supervisés et non supervisés ont été utilisés sur les données à haute dimensionnalité relatives à la criminalité, à la structure socio-économique et démographique et au cadre bâti dans le but de regrouper les quartiers urbains les plus similaires dans des clusters. D'abord, les cartes auto-organisatrices (self-organizing maps) ont été utilisées dans le but de réduire la variance intra-cluster des variables contextuelles et de maximiser simultanément la variance inter-cluster des réponses au sondage. Ensuite, l'algorithme des forêts d'arbres décisionnels (random forests) a permis à la fois d'évaluer la pertinence de la typologie de quartier élaborée et de sélectionner les variables contextuelles clés afin de construire un modèle parcimonieux faisant un minimum d'erreurs de classification. Enfin, pour l'analyse des impacts, la méthode des appariements des coefficients de propension (propensity score matching) a été utilisée pour équilibrer les échantillons prétest-posttest en termes d'âge, de sexe et de niveau d'éducation des répondants au sein de chaque type de quartier ainsi identifié dans chacune des villes, avant d'effectuer un test statistique de la différence observée dans les indicateurs d'impacts. De plus, tous les résultats statistiquement significatifs ont été soumis à une analyse de sensibilité (sensitivity analysis) afin d'évaluer leur robustesse face à un biais potentiel dû à des covariables non observées. L'étude relève qu'au cours des quinze dernières années, les cinq services de police ont entamé des réformes majeures de leur organisation ainsi que de leurs stratégies opérationnelles et qu'ils ont noué des partenariats stratégiques afin de mettre en oeuvre la police de proximité. La typologie de quartier développée a abouti à une réduction de la variance intra-cluster des variables contextuelles et permet d'expliquer une partie significative de la variance inter-cluster des indicateurs d'impacts avant la mise en oeuvre du traitement. Ceci semble suggérer que les méthodes de géocomputation aident à équilibrer les covariables observées et donc à réduire les menaces relatives à la validité interne d'un concept de recherche non-expérimental. Enfin, l'analyse des impacts a révélé que le sentiment d'insécurité a diminué de manière significative pendant la période 2000-2005 dans les quartiers se trouvant à l'intérieur et autour des centres-villes de Berne et de Zurich. Ces améliorations sont assez robustes face à des biais dus à des covariables inobservées et covarient dans le temps et l'espace avec la mise en oeuvre de la police de proximité. L'hypothèse alternative envisageant que les diminutions observées dans le sentiment d'insécurité soient, partiellement, un résultat des interventions policières de proximité semble donc être aussi plausible que l'hypothèse nulle considérant l'absence absolue d'effet. Ceci, même si le concept de recherche non-expérimental mis en oeuvre ne peut pas complètement exclure la sélection et la régression à la moyenne comme explications alternatives. The current research project is both a process and impact evaluation of community policing in Switzerland's five major urban areas - Basel, Bern, Geneva, Lausanne, and Zurich. Community policing is both a philosophy and an organizational strategy that promotes a renewed partnership between the police and the community to solve problems of crime and disorder. The process evaluation data on police internal reforms were obtained through semi-structured interviews with key administrators from the five police departments as well as from police internal documents and additional public sources. The impact evaluation uses official crime records and census statistics as contextual variables as well as Swiss Crime Survey (SCS) data on fear of crime, perceptions of disorder, and public attitudes towards the police as outcome measures. The SCS is a standing survey instrument that has polled residents of the five urban areas repeatedly since the mid-1980s. The process evaluation produced a "Calendar of Action" to create panel data to measure community policing implementation progress over six evaluative dimensions in intervals of five years between 1990 and 2010. The impact evaluation, carried out ex post facto, uses an observational design that analyzes the impact of the different community policing models between matched comparison areas across the five cities. Using ZIP code districts as proxies for urban neighborhoods, geospatial data mining algorithms serve to develop a neighborhood typology in order to match the comparison areas. To this end, both unsupervised and supervised algorithms are used to analyze high-dimensional data on crime, the socio-economic and demographic structure, and the built environment in order to classify urban neighborhoods into clusters of similar type. In a first step, self-organizing maps serve as tools to develop a clustering algorithm that reduces the within-cluster variance in the contextual variables and simultaneously maximizes the between-cluster variance in survey responses. The random forests algorithm then serves to assess the appropriateness of the resulting neighborhood typology and to select the key contextual variables in order to build a parsimonious model that makes a minimum of classification errors. Finally, for the impact analysis, propensity score matching methods are used to match the survey respondents of the pretest and posttest samples on age, gender, and their level of education for each neighborhood type identified within each city, before conducting a statistical test of the observed difference in the outcome measures. Moreover, all significant results were subjected to a sensitivity analysis to assess the robustness of these findings in the face of potential bias due to some unobserved covariates. The study finds that over the last fifteen years, all five police departments have undertaken major reforms of their internal organization and operating strategies and forged strategic partnerships in order to implement community policing. The resulting neighborhood typology reduced the within-cluster variance of the contextual variables and accounted for a significant share of the between-cluster variance in the outcome measures prior to treatment, suggesting that geocomputational methods help to balance the observed covariates and hence to reduce threats to the internal validity of an observational design. Finally, the impact analysis revealed that fear of crime dropped significantly over the 2000-2005 period in the neighborhoods in and around the urban centers of Bern and Zurich. These improvements are fairly robust in the face of bias due to some unobserved covariate and covary temporally and spatially with the implementation of community policing. The alternative hypothesis that the observed reductions in fear of crime were at least in part a result of community policing interventions thus appears at least as plausible as the null hypothesis of absolutely no effect, even if the observational design cannot completely rule out selection and regression to the mean as alternative explanations.

MGMT methylation analysis of glioblastoma on the Infinium methylation BeadChip identifies two distinct CpG regions associated with gene silencing and outcome, yielding a prediction model for comparisons across datasets, tumor grades, and CIMP-status.

The methylation status of the O(6)-methylguanine-DNA methyltransferase (MGMT) gene is an important predictive biomarker for benefit from alkylating agent therapy in glioblastoma. Recent studies in anaplastic glioma suggest a prognostic value for MGMT methylation. Investigation of pathogenetic and epigenetic features of this intriguingly distinct behavior requires accurate MGMT classification to assess high throughput molecular databases. Promoter methylation-mediated gene silencing is strongly dependent on the location of the methylated CpGs, complicating classification. Using the HumanMethylation450 (HM-450K) BeadChip interrogating 176 CpGs annotated for the MGMT gene, with 14 located in the promoter, two distinct regions in the CpG island of the promoter were identified with high importance for gene silencing and outcome prediction. A logistic regression model (MGMT-STP27) comprising probes cg1243587 and cg12981137 provided good classification properties and prognostic value (kappa = 0.85; log-rank p < 0.001) using a training-set of 63 glioblastomas from homogenously treated patients, for whom MGMT methylation was previously shown to be predictive for outcome based on classification by methylation-specific PCR. MGMT-STP27 was successfully validated in an independent cohort of chemo-radiotherapy-treated glioblastoma patients (n = 50; kappa = 0.88; outcome, log-rank p < 0.001). Lower prevalence of MGMT methylation among CpG island methylator phenotype (CIMP) positive tumors was found in glioblastomas from The Cancer Genome Atlas than in low grade and anaplastic glioma cohorts, while in CIMP-negative gliomas MGMT was classified as methylated in approximately 50 % regardless of tumor grade. The proposed MGMT-STP27 prediction model allows mining of datasets derived on the HM-450K or HM-27K BeadChip to explore effects of distinct epigenetic context of MGMT methylation suspected to modulate treatment resistance in different tumor types.