Using self organizing maps on compositional data

Self-organizing maps (Kohonen 1997) is a type of artificial neural network developedto explore patterns in high-dimensional multivariate data. The conventional versionof the algorithm involves the use of Euclidean metric in the process of adaptation ofthe model vectors, thus rendering in theory a whole methodology incompatible withnon-Euclidean geometries.In this contribution we explore the two main aspects of the problem:1. Whether the conventional approach using Euclidean metric can shed valid resultswith compositional data.2. If a modification of the conventional approach replacing vectorial sum and scalarmultiplication by the canonical operators in the simplex (i.e. perturbation andpowering) can converge to an adequate solution.Preliminary tests showed that both methodologies can be used on compositional data.However, the modified version of the algorithm performs poorer than the conventionalversion, in particular, when the data is pathological. Moreover, the conventional ap-proach converges faster to a solution, when data is \well-behaved".Key words: Self Organizing Map; Artificial Neural networks; Compositional data

Scoring Methods for Ordinal Multidimensional Forced-Choice Items

In most psychological tests and questionnaires, a test score is obtained bytaking the sum of the item scores. In virtually all cases where the test orquestionnaire contains multidimensional forced-choice items, this traditionalscoring method is also applied. We argue that the summation of scores obtained with multidimensional forced-choice items produces uninterpretabletest scores. Therefore, we propose three alternative scoring methods: a weakand a strict rank preserving scoring method, which both allow an ordinalinterpretation of test scores; and a ratio preserving scoring method, whichallows a proportional interpretation of test scores. Each proposed scoringmethod yields an index for each respondent indicating the degree to whichthe response pattern is inconsistent. Analysis of real data showed that withrespect to rank preservation, the weak and strict rank preserving methodresulted in lower inconsistency indices than the traditional scoring method;with respect to ratio preservation, the ratio preserving scoring method resulted in lower inconsistency indices than the traditional scoring method

Comparing methods for dimensionality reduction when data are density functions

Functional Data Analysis (FDA) deals with samples where a whole function is observedfor each individual. A particular case of FDA is when the observed functions are densityfunctions, that are also an example of infinite dimensional compositional data. In thiswork we compare several methods for dimensionality reduction for this particular typeof data: functional principal components analysis (PCA) with or without a previousdata transformation and multidimensional scaling (MDS) for diferent inter-densitiesdistances, one of them taking into account the compositional nature of density functions. The difeerent methods are applied to both artificial and real data (householdsincome distributions)

Dynamic graphics of parametrically linked multivariate methods used in compositional data analysis

Many multivariate methods that are apparently distinct can be linked by introducing oneor more parameters in their definition. Methods that can be linked in this way arecorrespondence analysis, unweighted or weighted logratio analysis (the latter alsoknown as "spectral mapping"), nonsymmetric correspondence analysis, principalcomponent analysis (with and without logarithmic transformation of the data) andmultidimensional scaling. In this presentation I will show how several of thesemethods, which are frequently used in compositional data analysis, may be linkedthrough parametrizations such as power transformations, linear transformations andconvex linear combinations. Since the methods of interest here all lead to visual mapsof data, a "movie" can be made where where the linking parameter is allowed to vary insmall steps: the results are recalculated "frame by frame" and one can see the smoothchange from one method to another. Several of these "movies" will be shown, giving adeeper insight into the similarities and differences between these methods

Statistical treatment of grain-size curves and empirical distributions: densities as compositions?

The preceding two editions of CoDaWork included talks on the possible considerationof densities as infinite compositions: Egozcue and D´ıaz-Barrero (2003) extended theEuclidean structure of the simplex to a Hilbert space structure of the set of densitieswithin a bounded interval, and van den Boogaart (2005) generalized this to the setof densities bounded by an arbitrary reference density. From the many variations ofthe Hilbert structures available, we work with three cases. For bounded variables, abasis derived from Legendre polynomials is used. For variables with a lower bound, westandardize them with respect to an exponential distribution and express their densitiesas coordinates in a basis derived from Laguerre polynomials. Finally, for unboundedvariables, a normal distribution is used as reference, and coordinates are obtained withrespect to a Hermite-polynomials-based basis.To get the coordinates, several approaches can be considered. A numerical accuracyproblem occurs if one estimates the coordinates directly by using discretized scalarproducts. Thus we propose to use a weighted linear regression approach, where all k-order polynomials are used as predictand variables and weights are proportional to thereference density. Finally, for the case of 2-order Hermite polinomials (normal reference)and 1-order Laguerre polinomials (exponential), one can also derive the coordinatesfrom their relationships to the classical mean and variance.Apart of these theoretical issues, this contribution focuses on the application of thistheory to two main problems in sedimentary geology: the comparison of several grainsize distributions, and the comparison among different rocks of the empirical distribution of a property measured on a batch of individual grains from the same rock orsediment, like their composition

Revisiting the compositional data. Some fundamental questions and new prospects in Archaeometry and Archaeology

In this paper we examine the problem of compositional data from a different startingpoint. Chemical compositional data, as used in provenance studies on archaeologicalmaterials, will be approached from the measurement theory. The results will show, in avery intuitive way that chemical data can only be treated by using the approachdeveloped for compositional data. It will be shown that compositional data analysis is aparticular case in projective geometry, when the projective coordinates are in thepositive orthant, and they have the properties of logarithmic interval metrics. Moreover,it will be shown that this approach can be extended to a very large number ofapplications, including shape analysis. This will be exemplified with a case study inarchitecture of Early Christian churches dated back to the 5th-7th centuries AD

Vertebrates Limb Geometry in the Simplex space

A novel metric comparison of the appendicular skeleton (fore and hind limb) ofdifferent vertebrates using the Compositional Data Analysis (CDA) methodologicalapproach it’s presented.355 specimens belonging in various taxa of Dinosauria (Sauropodomorpha, Theropoda,Ornithischia and Aves) and Mammalia (Prothotheria, Metatheria and Eutheria) wereanalyzed with CDA.A special focus has been put on Sauropodomorpha dinosaurs and the Aitchinsondistance has been used as a measure of disparity in limb elements proportions to infersome aspects of functional morphology

Robust Factor Analysis for Compositional Data

Factor analysis as frequent technique for multivariate data inspection is widely used also for compositional data analysis. The usual way is to use a centered logratio (clr)transformation to obtain the random vector y of dimension D. The factor model istheny = Λf + e (1)with the factors f of dimension k & D, the error term e, and the loadings matrix Λ.Using the usual model assumptions (see, e.g., Basilevsky, 1994), the factor analysismodel (1) can be written asCov(y) = ΛΛT + ψ (2)where ψ = Cov(e) has a diagonal form. The diagonal elements of ψ as well as theloadings matrix Λ are estimated from an estimation of Cov(y).Given observed clr transformed data Y as realizations of the random vectory. Outliers or deviations from the idealized model assumptions of factor analysiscan severely effect the parameter estimation. As a way out, robust estimation ofthe covariance matrix of Y will lead to robust estimates of Λ and ψ in (2), seePison et al. (2003). Well known robust covariance estimators with good statisticalproperties, like the MCD or the S-estimators (see, e.g. Maronna et al., 2006), relyon a full-rank data matrix Y which is not the case for clr transformed data (see,e.g., Aitchison, 1986).The isometric logratio (ilr) transformation (Egozcue et al., 2003) solves thissingularity problem. The data matrix Y is transformed to a matrix Z by usingan orthonormal basis of lower dimension. Using the ilr transformed data, a robustcovariance matrix C(Z) can be estimated. The result can be back-transformed tothe clr space byC(Y ) = V C(Z)V Twhere the matrix V with orthonormal columns comes from the relation betweenthe clr and the ilr transformation. Now the parameters in the model (2) can beestimated (Basilevsky, 1994) and the results have a direct interpretation since thelinks to the original variables are still preserved.The above procedure will be applied to data from geochemistry. Our specialinterest is on comparing the results with those of Reimann et al. (2002) for the Kolaproject data

Validation of the spanish version of the multiple sclerosis international quality of life (musiqol) questionnaire

BACKGROUND: The Multiple Sclerosis International Quality Of Life (MusiQoL) questionnaire, a 31-item, multidimensional, self-administrated questionnaire that is available in 14 languages including Spanish, has been validated using a large international sample. We investigated the validity and reliability of the Spanish version of MusiQoL in Spain. METHODS: Consecutive patients with different types and severities of multiple sclerosis (MS) were recruited from 22 centres across Spain. All patients completed the MusiQoL questionnaire, the 36-Item Short Form (SF-36) health survey, and a symptoms checklist at baseline and 21 days later. External validity, internal consistency, reliability and reproducibility were tested. RESULTS: A total of 224 Spanish patients were evaluated. Dimensions of MusiQoL generally demonstrated a high internal consistency (Cronbach's alpha: 0.70-0.92 for all but two MusiQoL domain scores). External validity testing revealed that the MusiQoL index score correlated significantly with all SF-36 dimension scores (Pearson's correlation: 0.46-0.76), reproducibility was satisfactory (intraclass correlation coefficient: 0.60-0.91), acceptability was high, and the time taken to complete the 31-item questionnaire was reasonable (mean [standard deviation]: 9.8 [11.8] minutes). CONCLUSIONS: The Spanish version of the MusiQoL questionnaire appears to be a valid and reliable instrument for measuring quality of life in patients with MS in Spain and constitutes a useful instrument to measure health-related quality of life in the clinical setting.

Construcción y validación de un cuestionario para medir conductas, conocimientos y actitudes sobre la higiene de las manos en personal sanitario en formacion.

Background: Hand hygiene in the health context is a complex behaviour. There have been rarely given the role of the knowledge and attitudes as predictors of hand hygiene behaviour. The main objective of this work is the description of the development of a questionnaire on hand hygiene and the analysis of their measurement properties. Method: An instrument which was designed and validated a questionnaire. It was held in January 2009. It finally has had 50 items that assess risk behaviour intention before and after contact with the patient, declarative knowledge and attitudes about hand hygiene. It has been applied to 431 students of health sciences at the University of Granada. Results: There were three factor analysis, ultimately obtaining a general convergence value that explains 46.01% of the total variance and high reliability (a=0,843). There is correlation between knowledge and behavior intentions before and after patient contact (p <0.01).In turn, the attitude correlates only with behavioral intention before (p <0.05). The hand hygiene behavior refers to a higher mean after the completion of various health activities before the same (4.26 and 3.96 respectively). Both declarative knowledge and attitudes significantly predict behavioral intention, in particular the conduct before the contact with the patient (R2 = 0.100, standardized Beta 0.256 for knowledge and 0.145 for attitudes). Conclusions: The questionnaire shows high internal consistency. We have obtained a valid tool for assessing risk behavior, knowledge and attitudes about students’ hand hygiene in health sciences. The tool detects deficiencies in basic skills in students.

Supervivencia en cáncer de mama tras 10 años de seguimiento en las provincias de Granada y Almería

Background: To describe the overall and disease-free survival at five and ten years after breast cancer diagnosis in women from a previous case-control study, and establish related prognostic factors. Methods: We followed up 202 patients diagnosed between 1996 and 1998 in three public hospitals in Granada and Almeria provinces in Spain. Survival rates were calculated using the Kaplan and Meier method, and the Cox proportional hazards model was applied to identify the most significant variables contributing to survival. Results: Mean age at diagnosis was 54.27±10.4 years. Mean follow-up for overall survival was 119.91 months (95%CI 113.65126.17); the five-year survival rate was 83.9% (95%CI: 78.13-89.66) and the ten-year rate was 71% (95%CI: 63.25-78.74). Mean followup for disease-free survival was 118.75 months (95%CI 111.86125.65); the five-year disease-free survival rate was 81% (95%CI: 74.52-87.47) and the ten-year rate was 71.3% (95%CI: 63.33-79.26). The mortality rate of the study population was 33.17%. Conclusions: Disease characteristics are similar in our population to those in other Spanish and European regions, while the overall survival is higher than the mean rate during the same period in Europe (5-yr rate of 79%) and similar to that in Spain (83%).

Nosocomial bacteremia due to an as yet unclassified acinetobacter genomic species 17-like strain.

We describe a case of bacteremia due to an as yet unclassified Acinetobacter genomic species 17-like strain. The recognition of this microorganism as non-Acinetobacter baumannii may have important epidemiological implications, as it relieves the hospital of the implementation of barrier precautions for patients infected or colonized as may be necessary with a multiresistant A. baumannii epidemic.

Novel MLPA procedure using self-designed probes allows comprehensive analysis for CNVs of the genes involved in Hirschsprung disease.

Background: Hirschsprung disease is characterized by the absence of intramural ganglion cells in the enteric plexuses, due to a fail during enteric nervous system formation. Hirschsprung has a complex genetic aetiology and mutations in several genes have been related to the disease. There is a clear predominance of missense/nonsense mutations in these genes whereas copy number variations (CNVs) have been seldom described, probably due to the limitations of conventional techniques usually employed for mutational analysis. In this study, we have looked for CNVs in some of the genes related to Hirschsprung (EDNRB, GFRA1, NRTN and PHOX2B) using the Multiple Ligation-dependent Probe Amplification (MLPA) approach. Methods: CNVs screening was performed in 208 HSCR patients using a self-designed set of MLPA probes, covering the coding region of those genes. Results: A deletion comprising the first 4 exons in GFRA1 gene was detected in 2 sporadic HSCR patients and in silico approaches have shown that the critical translation initiation signal in the mutant gene was abolished. In this study, we have been able to validate the reliability of this technique for CNVs screening in HSCR. Conclusions: The implemented MLPA based technique presented here allows CNV analysis of genes involved in HSCR that have not been not previously evaluated. Our results indicate that CNVs could be implicated in the pathogenesis of HSCR, although they seem to be an uncommon molecular cause of HSCR.

Multiple sclerosis risk variant HLA-DRB1*1501 associates with high expression of DRB1 gene in different human populations.

The human leukocyte antigen (HLA) DRB1*1501 has been consistently associated with multiple sclerosis (MS) in nearly all populations tested. This points to a specific antigen presentation as the pathogenic mechanism though this does not fully explain the disease association. The identification of expression quantitative trait loci (eQTL) for genes in the HLA locus poses the question of the role of gene expression in MS susceptibility. We analyzed the eQTLs in the HLA region with respect to MS-associated HLA-variants obtained from genome-wide association studies (GWAS). We found that the Tag of DRB1*1501, rs3135388 A allele, correlated with high expression of DRB1, DRB5 and DQB1 genes in a Caucasian population. In quantitative terms, the MS-risk AA genotype carriers of rs3135388 were associated with 15.7-, 5.2- and 8.3-fold higher expression of DQB1, DRB5 and DRB1, respectively, than the non-risk GG carriers. The haplotype analysis of expression-associated variants in a Spanish MS cohort revealed that high expression of DRB1 and DQB1 alone did not contribute to the disease. However, in Caucasian, Asian and African American populations, the DRB1*1501 allele was always highly expressed. In other immune related diseases such as type 1 diabetes, inflammatory bowel disease, ulcerative colitis, asthma and IgA deficiency, the best GWAS-associated HLA SNPs were also eQTLs for different HLA Class II genes. Our data suggest that the DR/DQ expression levels, together with specific structural properties of alleles, seem to be the causal effect in MS and in other immunopathologies rather than specific antigen presentation alone.

Documento de consenso SENPE/SEGHNP/ANECIPN/SECP sobre vías de acceso en nutrición enteral pediátrica.

Standardization of clinical procedures has become a desirable objective in contemporary medical practice. To this effect, the Spanish Society of Parenteral and Enteral Nutrition (SENPE) has endeavoured to create clinical practice guidelines and/or documents of consensus as well as quality standards in artificial nutrition. As a result, the SENPE´s Standardization Team has put together the "Document of Consensus in Enteral Access for Paediatric Nutritional Support" supported by the Spanish Society of Pediatric Gastroenterology, Hepatology and Nutrition (SEGHNP), the National Association of Pediatric and Neonatal Intensive Care Nursery (ANECIPN), and the Spanish Society of Pediatric Surgery (SECP). The present publication is a reduced version of our work; the complete document will be published as a monographic issue. It analyzes enteral access options in the pediatric patient, reviews the levels of evidence and provides the team-members' experience. Similarly, it details general and specific indications for pediatric enteral support, current techniques, care guidelines, methods of administration and complications of each enteral access. The data published by the American Society for Parenteral and Enteral Nutrition (ASPEN) and several European Societies has also been incorporated.