Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

Genome-wide meta-analysis of common variant differences between men and women.

The male-to-female sex ratio at birth is constant across world populations with an average of 1.06 (106 male to 100 female live births) for populations of European descent. The sex ratio is considered to be affected by numerous biological and environmental factors and to have a heritable component. The aim of this study was to investigate the presence of common allele modest effects at autosomal and chromosome X variants that could explain the observed sex ratio at birth. We conducted a large-scale genome-wide association scan (GWAS) meta-analysis across 51 studies, comprising overall 114 863 individuals (61 094 women and 53 769 men) of European ancestry and 2 623 828 common (minor allele frequency >0.05) single-nucleotide polymorphisms (SNPs). Allele frequencies were compared between men and women for directly-typed and imputed variants within each study. Forward-time simulations for unlinked, neutral, autosomal, common loci were performed under the demographic model for European populations with a fixed sex ratio and a random mating scheme to assess the probability of detecting significant allele frequency differences. We do not detect any genome-wide significant (P < 5 × 10(-8)) common SNP differences between men and women in this well-powered meta-analysis. The simulated data provided results entirely consistent with these findings. This large-scale investigation across ~115 000 individuals shows no detectable contribution from common genetic variants to the observed skew in the sex ratio. The absence of sex-specific differences is useful in guiding genetic association study design, for example when using mixed controls for sex-biased traits.

Fast analysis of doping agents in urine by ultra-high-pressure liquid chromatography-quadrupole time-of-flight mass spectrometry. II: Confirmatory analysis.

For doping control, analyses of samples are generally achieved in two steps: a rapid screening and, in the case of a positive result, a confirmatory analysis. A two-step methodology based on ultra-high-pressure liquid chromatography coupled to a quadrupole time-of-flight mass spectrometry (UHPLC-QTOF-MS) was developed to screen and confirm 103 doping agents from various classes (e.g., beta-blockers, stimulants, diuretics, and narcotics). The screening method was presented in a previous article as part I (i.e., Fast analysis of doping agents in urine by ultra-high-pressure liquid chromatography-quadrupole time-of-flight mass spectrometry. Part I: screening analysis). For the confirmatory method, basic, neutral and acidic compounds were extracted by a dedicated solid-phase extraction (SPE) in a 96-well plate format and detected by MS in the tandem mode to obtain precursor and characteristic product ions. The mass accuracy and the elemental composition of precursor and product ions were used for compound identification. After validation including matrix effect determination, the method was considered reliable to confirm suspect results without ambiguity according to the positivity criteria established by the World Anti-Doping Agency (WADA). Moreover, an isocratic method was developed to separate ephedrine from its isomer pseudoephedrine and cathine from phenylpropanolamine in a single run, what allowed their direct quantification in urine.

Liver Transplantation for Neuroendocrine Tumors in Europe-Results and Trends in Patient Selection: A 213-Case European Liver Transplant Registry Study.

OBJECTIVE:: The purpose of this study was to assess outcomes and indications in a large cohort of patients who underwent liver transplantation (LT) for liver metastases (LM) from neuroendocrine tumors (NET) over a 27-year period. BACKGROUND:: LT for NET remains controversial due to the absence of clear selection criteria and the scarcity and heterogeneity of reported cases. METHODS:: This retrospective multicentric study included 213 patients who underwent LT for NET performed in 35 centers in 11 European countries between 1982 and 2009. One hundred seven patients underwent transplantation before 2000 and 106 after 2000. Mean age at the time of LT was 46 years. Half of the patients presented hormone secretion and 55% had hepatomegaly. Before LT, 83% of patients had undergone surgical treatment of the primary tumor and/or LM and 76% had received chemotherapy. The median interval between diagnosis of LM and LT was 25 months (range, 1-149 months). In addition to LT, 24 patients underwent major resection procedures and 30 patients underwent minor resection procedures. RESULTS:: Three-month postoperative mortality was 10%. At 5 years after LT, overall survival (OS) was 52% and disease-free survival was 30%. At 5 years from diagnosis of LM, OS was 73%. Multivariate analysis identified 3 predictors of poor outcome, that is, major resection in addition to LT, poor tumor differentiation, and hepatomegaly. Since 2000, 5-year OS has increased to 59% in relation with fewer patients presenting poor prognostic factors. Multivariate analysis of the 106 cases treated since 2000 identified the following predictors of poor outcome: hepatomegaly, age more than 45 years, and any amount of resection concurrent with LT. CONCLUSIONS:: LT is an effective treatment of unresectable LM from NET. Patient selection based on the aforementioned predictors can achieve a 5-year OS between 60% and 80%. However, use of overly restrictive criteria may deny LT to some patients who could benefit. Optimal timing for LT in patients with stable versus progressive disease remains unclear.

Insulinoma associated with a case of multiple endocrine neoplasia type I: Functional somatostatin receptors and abnormal glucose-induced insulin secretion.

A sporadic case of multiple endocrine neoplasia type I with coexisting insulinoma and hyperparathyroidism was investigated in vivo and in vitro. The insulinoma was localized by somatostatin receptor scintigraphy and these receptors were functionally active. Octreotide administration decreased the basal insulin and glucagon secretion by 90 and 46%, respectively. Immunocytochemistry of the insulinoma tissue was positive for insulin, chromogranin A and neuropeptide Y. The insulinoma cells were also isolated and cultured in vitro. Incubation experiments revealed that a low glucose concentration (1 mmol/l) was sufficient to increase cytosolic free calcium and to produce a maximal glucose-induced insulin release. Northern blot analysis of RNA obtained from the tumor showed a high abundance of the low Km glucose transporter GLUT1 but no transcript for the high Km glucose transporter GLUT2. The abnormal distribution of glucose transporters probably relates to the abnormal glucose sensing of insulinoma cells, and explains their sustained insulin secretion at low glucose concentrations. Whether these abnormalities share a pathogenetic link with the presence of functionally active somatostatin receptors remains to be elucidated.

Estudi d'eines CASE que suporten OCLper a la generació automàtica de codi Java

Es tracta d'una recerca d'eines CASEque actualment suporten OCL en la generació automàtica de codi Java per estudiar-les ianalitzar-les a través d'un model de proves consistent en un diagrama de classes del modelestàtic de l'UML i una mostra variada d'instruccions OCL, amb l'objectiu de detectar lesseves mancances, analitzant el codi obtingut i determinar si controla o no cada tipus derestricció, i si s'han implementat bé en el codi.

The Politics of Network Governance in Europe: The Case of Energy Regulation

Networks are considered increasingly important for policy-making. The literature on new modes of governance in Europe suggests that their horizontal coordination capacity and flexible and informal structures are particularly suitable for governing the multilevel architecture of the European polity. However, empirical evidence about the effects of networks on policy-making and public policies is still quite limited. This article uses the case of the European network of energy regulators to explore the determinants of the position of network members and, in turn, the domestic adoption of soft rules developed within this network. The empirical analysis, based on multivariate statistics and semi-directive interviews, supports the expectation that institutional complementarities increase actors' centrality in networks, while arguments based on organisational resources and age are disproved. Furthermore, results show that the overall level of adoption is considerable and that centrality might have a small positive effect on domestic adoption.

Large-scale gene-centric analysis identifies novel variants for coronary artery disease.

Coronary artery disease (CAD) has a significant genetic contribution that is incompletely characterized. To complement genome-wide association (GWA) studies, we conducted a large and systematic candidate gene study of CAD susceptibility, including analysis of many uncommon and functional variants. We examined 49,094 genetic variants in ∼2,100 genes of cardiovascular relevance, using a customised gene array in 15,596 CAD cases and 34,992 controls (11,202 cases and 30,733 controls of European descent; 4,394 cases and 4,259 controls of South Asian origin). We attempted to replicate putative novel associations in an additional 17,121 CAD cases and 40,473 controls. Potential mechanisms through which the novel variants could affect CAD risk were explored through association tests with vascular risk factors and gene expression. We confirmed associations of several previously known CAD susceptibility loci (eg, 9p21.3:p<10(-33); LPA:p<10(-19); 1p13.3:p<10(-17)) as well as three recently discovered loci (COL4A1/COL4A2, ZC3HC1, CYP17A1:p<5×10(-7)). However, we found essentially null results for most previously suggested CAD candidate genes. In our replication study of 24 promising common variants, we identified novel associations of variants in or near LIPA, IL5, TRIB1, and ABCG5/ABCG8, with per-allele odds ratios for CAD risk with each of the novel variants ranging from 1.06-1.09. Associations with variants at LIPA, TRIB1, and ABCG5/ABCG8 were supported by gene expression data or effects on lipid levels. Apart from the previously reported variants in LPA, none of the other ∼4,500 low frequency and functional variants showed a strong effect. Associations in South Asians did not differ appreciably from those in Europeans, except for 9p21.3 (per-allele odds ratio: 1.14 versus 1.27 respectively; P for heterogeneity = 0.003). This large-scale gene-centric analysis has identified several novel genes for CAD that relate to diverse biochemical and cellular functions and clarified the literature with regard to many previously suggested genes.

Case-control study of factors associated with chronic Chagas heart disease in patients over 50 years of age

A case-control study on chronic Chagas heart disease (CCHD) was carried out between 1997 and 2005. Ninety patients over 50 years of age were examined for factors related to (CCHD). Fourty-six patients (51.1%) with Chagas heart disease (anomalous ECG) were assigned to the case group and 44 (48.9%) were included in the control group as carriers of undetermined forms of chronic disease. Social, demographic (age, gender, skin color, area of origin), epidemiological (permanence within an endemic zone, family history of Chagas heart disease or sudden death, physical strain, alcoholism, and smoking), and clinical (systemic hypertension) variables were analyzed. The data set was assessed through single-variable and multivariate analysis. The two factors independently associated with heart disease were age - presence of heart disease being three times higher in patients over 60 years of age (odds ratio, OR: 2.89; confidence interval of 95%: 1.09-7.61) - and family history of Chagas heart disease (OR: 2.833, CI 95%: 1.11-7.23). Systemic hypertension and gender did not prove to hold any association with heart disease, as neither did skin color, but this variable showed low statistical power due to reduced sample size.

A Method and Tool to Support the Analysis and Enhance the Understanding of Peer-to-Peer Learning Experiences

In this paper we look at how a web-based social software can be used to make qualitative data analysis of online peer-to-peer learning experiences. Specifically, we propose to use Cohere, a web-based social sense-making tool, to observe, track, annotate and visualize discussion group activities in online courses. We define a specific methodology for data observation and structuring, and present results of the analysis of peer interactions conducted in discussion forum in a real case study of a P2PU course. Finally we discuss how network visualization and analysis can be used to gather a better understanding of the peer-to-peer learning experience. To do so, we provide preliminary insights on the social, dialogical and conceptual connections that have been generated within one online discussion group.

Cancer mortality inequalities in urban areas: a Bayesian small area analysis in Spanish cities

Background Intra-urban inequalities in mortality have been infrequently analysed in European contexts. The aim of the present study was to analyse patterns of cancer mortality and their relationship with socioeconomic deprivation in small areas in 11 Spanish cities. Methods It is a cross-sectional ecological design using mortality data (years 1996-2003). Units of analysis were the census tracts. A deprivation index was calculated for each census tract. In order to control the variability in estimating the risk of dying we used Bayesian models. We present the RR of the census tract with the highest deprivation vs. the census tract with the lowest deprivation. Results In the case of men, socioeconomic inequalities are observed in total cancer mortality in all cities, except in Castellon, Cordoba and Vigo, while Barcelona (RR = 1.53 95%CI 1.42-1.67), Madrid (RR = 1.57 95%CI 1.49-1.65) and Seville (RR = 1.53 95%CI 1.36-1.74) present the greatest inequalities. In general Barcelona and Madrid, present inequalities for most types of cancer. Among women for total cancer mortality, inequalities have only been found in Barcelona and Zaragoza. The excess number of cancer deaths due to socioeconomic deprivation was 16,413 for men and 1,142 for women. Conclusion This study has analysed inequalities in cancer mortality in small areas of cities in Spain, not only relating this mortality with socioeconomic deprivation, but also calculating the excess mortality which may be attributed to such deprivation. This knowledge is particularly useful to determine which geographical areas in each city need intersectorial policies in order to promote a healthy environment.

Comprehensive analysis of RET common and rare variant patientsin a series of Spanish Hirschsprung patients confirms a synergistic effect of both kinds of events

Background. RET is the major gene associated to Hirschsprung disease (HSCR) with differential contributions of its rare and common, coding and noncoding mutations to the multifactorial nature of this pathology. In the present study, we have performed a comprehensive study of our HSCR series evaluating the involvement of both RET rare variants (RVs) and common variants (CVs) in the context of the disease. Methods. RET mutational screening was performed by dHPLC and direct sequencing for the identification of RVs. In addition Taqman technology was applied for the genotyping of 3 RET CVs previously associated to HSCR, including a variant lying in an enhancer domain within RET intron 1 (rs2435357). Statistical analyses were performed using the SPSS v.17.0 to analyze the distribution of the variants. Results. Our results confirm the strongest association to HSCR for the "enhancer" variant, and demonstrate a significantly higher impact of it in male versus female patients. Integration of the RET RVs and CVs analysis showed that in 91.66% of cases with both kinds of mutational events, the enhancer allele is in trans with the allele bearing the RET RV. Conclusions. A gender effect exists on both the transmission and distribution of rare coding and common HSCR causing mutations. In addition, these RET CVs and RVs seem to act in a synergistic way leading to HSCR phenotype.

Effectiveness of a nurse-led case management home care model in Primary Health Care. A quasi-experimental, controlled, multi-centre study

Background Demand for home care services has increased considerably, along with the growing complexity of cases and variability among resources and providers. Designing services that guarantee co-ordination and integration for providers and levels of care is of paramount importance. The aim of this study is to determine the effectiveness of a new case-management based, home care delivery model which has been implemented in Andalusia (Spain). Methods Quasi-experimental, controlled, non-randomised, multi-centre study on the population receiving home care services comparing the outcomes of the new model, which included nurse-led case management, versus the conventional one. Primary endpoints: functional status, satisfaction and use of healthcare resources. Secondary endpoints: recruitment and caregiver burden, mortality, institutionalisation, quality of life and family function. Analyses were performed at base-line, and at two, six and twelve months. A bivariate analysis was conducted with the Student's t-test, Mann-Whitney's U, and the chi squared test. Kaplan-Meier and log-rank tests were performed to compare survival and institutionalisation. A multivariate analysis was performed to pinpoint factors that impact on improvement of functional ability. Results Base-line differences in functional capacity – significantly lower in the intervention group (RR: 1.52 95%CI: 1.05–2.21; p = 0.0016) – disappeared at six months (RR: 1.31 95%CI: 0.87–1.98; p = 0.178). At six months, caregiver burden showed a slight reduction in the intervention group, whereas it increased notably in the control group (base-line Zarit Test: 57.06 95%CI: 54.77–59.34 vs. 60.50 95%CI: 53.63–67.37; p = 0.264), (Zarit Test at six months: 53.79 95%CI: 49.67–57.92 vs. 66.26 95%CI: 60.66–71.86 p = 0.002). Patients in the intervention group received more physiotherapy (7.92 CI95%: 5.22–10.62 vs. 3.24 95%CI: 1.37–5.310; p = 0.0001) and, on average, required fewer home care visits (9.40 95%CI: 7.89–10.92 vs.11.30 95%CI: 9.10–14.54). No differences were found in terms of frequency of visits to A&E or hospital re-admissions. Furthermore, patients in the control group perceived higher levels of satisfaction (16.88; 95%CI: 16.32–17.43; range: 0–21, vs. 14.65 95%CI: 13.61–15.68; p = 0,001). Conclusion A home care service model that includes nurse-led case management streamlines access to healthcare services and resources, while impacting positively on patients' functional ability and caregiver burden, with increased levels of satisfaction.

Application of compositional data analysis to geochemical data of marine sediments

In an earlier investigation (Burger et al., 2000) five sediment cores near the RodriguesTriple Junction in the Indian Ocean were studied applying classical statistical methods(fuzzy c-means clustering, linear mixing model, principal component analysis) for theextraction of endmembers and evaluating the spatial and temporal variation ofgeochemical signals. Three main factors of sedimentation were expected by the marinegeologists: a volcano-genetic, a hydro-hydrothermal and an ultra-basic factor. Thedisplay of fuzzy membership values and/or factor scores versus depth providedconsistent results for two factors only; the ultra-basic component could not beidentified. The reason for this may be that only traditional statistical methods wereapplied, i.e. the untransformed components were used and the cosine-theta coefficient assimilarity measure.During the last decade considerable progress in compositional data analysis was madeand many case studies were published using new tools for exploratory analysis of thesedata. Therefore it makes sense to check if the application of suitable data transformations,reduction of the D-part simplex to two or three factors and visualinterpretation of the factor scores would lead to a revision of earlier results and toanswers to open questions . In this paper we follow the lines of a paper of R. Tolosana-Delgado et al. (2005) starting with a problem-oriented interpretation of the biplotscattergram, extracting compositional factors, ilr-transformation of the components andvisualization of the factor scores in a spatial context: The compositional factors will beplotted versus depth (time) of the core samples in order to facilitate the identification ofthe expected sources of the sedimentary process.Kew words: compositional data analysis, biplot, deep sea sediments