Automatic ICD-10 classification of cancers from free-text death certificates

Objective Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates – an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates. Methods Detailed features, including terms, n-grams and SNOMED CT concepts were extracted from a collection of 447,336 death certificates. These features were used to train Support Vector Machine classifiers (one classifier for each cancer type). The classifiers were deployed in a cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identified the type of cancer (according to the ICD-10 classification system). A held-out test set was used to evaluate the effectiveness of the classifiers according to precision, recall and F-measure. In addition, detailed feature analysis was performed to reveal the characteristics of a successful cancer classification model. Results The system was highly effective at identifying cancer as the underlying cause of death (F-measure 0.94). The system was also effective at determining the type of cancer for common cancers (F-measure 0.7). Rare cancers, for which there was little training data, were difficult to classify accurately (F-measure 0.12). Factors influencing performance were the amount of training data and certain ambiguous cancers (e.g., those in the stomach region). The feature analysis revealed a combination of features were important for cancer type classification, with SNOMED CT concept and oncology specific morphology features proving the most valuable. Conclusion The system proposed in this study provides automatic identification and characterisation of cancers from large collections of free-text death certificates. This allows organisations such as Cancer Registries to monitor and report on cancer mortality in a timely and accurate manner. In addition, the methods and findings are generally applicable beyond cancer classification and to other sources of medical text besides death certificates.

Impact of working conditions on the quality of working life: Case manufacturing sector colombian Caribbean Region [Impacto de las Condiciones de Trabajo en Calidad de Vida Laboral: Caso del Sector Manufacturero de la Región Caribe Colombiana]

La presenta investigación centra su atención en evaluar el impacto de las Condiciones de Trabajo en la Calidad de Vida Laboral del talento humano de sector manufacturero de la región Caribe colombiana. Para analizar este proceso se entrevistaron a 518 empleados del sector. El diseño utilizado fue no experimental de tipo transversal descriptivo, puesto que a cada participante se le aplicó una entrevista con el instrumento de Condiciones de Trabajo y la Herramienta de Calidad de Vida Laboral (Condiciones Salariales y Subjetivas). Los datos fueron analizados mediante análisis de correlación y modelos de regresión logística. Los resultados mostraron que el ambiente térmico y las normas de seguridad en el trabajo afectan de forma positiva la Calidad de Vida Laboral de los empleados del sector. Estos resultados ponen de manifiesto que la relación entre las condiciones de trabajo y la CVL se basa en la competencia y distan de ser una relación lineal y simple relacionada con la consideración de la presencia o la ausencia de las condiciones de trabajo. Ello tiene implicaciones a la hora de formular políticas, programas e intervenciones para prevenir, erradicar y amortiguar los efectos negativos de las condiciones de trabajo y mejorar la seguridad industrial dentro de las empresas.

Fine mapping of variants associated with endometriosis in the WNT4 region on chromosome 1p36

Genome-wide association studies show strong evidence of association with endometriosis for markers on chromosome 1p36 spanning the potential candidate genes WNT4, CDC42 and LINC00339. WNT4 is involved in development of the uterus, and the expression of CDC42 and LINC00339 are altered in women with endometriosis. We conducted fine mapping to examine the role of coding variants in WNT4 and CDC42 and determine the key SNPs with strongest evidence of association in this region. We identified rare coding variants in WNT4 and CDC42 present only in endometriosis cases. The frequencies were low and cannot account for the common signal associated with increased risk of endometriosis. Genotypes for five common SNPs in the region of chromosome 1p36 show stronger association signals when compared with rs7521902 reported in published genome scans. Of these, three SNPs rs12404660, rs3820282, and rs55938609 were located in DNA sequences with potential functional roles including overlap with transcription factor binding sites for FOXA1, FOXA2, ESR1, and ESR2. Functional studies will be required to identify the gene or genes implicated in endometriosis risk.

Familial isolated hyperparathyroidism is linked to a 1.7 Mb region on chromosome 2p13.3-14

BACKGROUND: Familial isolated hyperparathyroidism (FIHP) is an autosomal dominantly inherited form of primary hyperparathyroidism. Although comprising only about 1% of cases of primary hyperparathyroidism, identification and functional analysis of a causative gene for FIHP is likely to advance our understanding of parathyroid physiology and pathophysiology. METHODS: A genome-wide screen of DNA from seven pedigrees with FIHP was undertaken in order to identify a region of genetic linkage with the disorder. RESULTS: Multipoint linkage analysis identified a region of suggestive linkage (LOD score 2.68) on chromosome 2. Fine mapping with the addition of three other families revealed significant linkage adjacent to D2S2368 (maximum multipoint LOD score 3.43). Recombination events defined a 1.7 Mb region of linkage between D2S2368 and D2S358 in nine pedigrees. Sequencing of the two most likely candidate genes in this region, however, did not identify a gene for FIHP. CONCLUSIONS: We conclude that a causative gene for FIHP lies within this interval on chromosome 2. This is a major step towards eventual precise identification of a gene for FIHP, likely to be a key component in the genetic regulation of calcium homeostasis.

Separate and interacting effects within the catechol-O-methyltransferase (COMT) are associated with schizophrenia

Several lines of evidence have implicated the catechol-O-methyltransferase (COMT) gene as a candidate for schizophrenia (SZ) susceptibility, not only because it encodes a key dopamine catabolic enzyme but also because it maps to the velocardiofacial syndrome region of chromosome 22q11 which has long been associated with SZ predisposition. The interest in COMT as a candidate SZ risk factor has led to numerous case-control and family-based studies, with the majority placing emphasis on examining a functional Val/Met polymorphism within this enzyme. Unfortunately, these studies have continually produced conflicting results. To assess the genetic contribution of other COMT variants to SZ susceptibility, we investigated three single-nucleotide polymorphisms (SNPs) (rs737865, rs4633, rs165599) in addition to the Val/Met variant (rs4680) in a highly selected sample of Australian Caucasian families containing 107 patients with SZ. The Val/Met and rs4633 variants showed nominally significant associations with SZ (P<0.05), although neither of the individual SNPs remained significant after adjusting for multiple testing (most significant P=0.1174). However, haplotype analyses showed strong evidence of an association; the most significant being the three-marker haplotype rs737865-rs4680-rs165599 (global P=0.0022), which spans more than 26 kb. Importantly, conditional analyses indicated the presence of two separate and interacting effects within this haplotype, irrespective of gender. In addition, our results indicate the Val/Met polymorphism is not disease-causing and is simply in strong linkage disequilibrium with a causative effect, which interacts with another as yet unidentified variant approximately 20 kb away. These results may help explain the inconsistent results reported on the Val/Met polymorphism and have important implications for future investigations into the role of COMT in SZ susceptibility.

Optimal adaptive sequential spatial sampling of soil using pair-copulas

A spatial sampling design that uses pair-copulas is presented that aims to reduce prediction uncertainty by selecting additional sampling locations based on both the spatial configuration of existing locations and the values of the observations at those locations. The novelty of the approach arises in the use of pair-copulas to estimate uncertainty at unsampled locations. Spatial pair-copulas are able to more accurately capture spatial dependence compared to other types of spatial copula models. Additionally, unlike traditional kriging variance, uncertainty estimates from the pair-copula account for influence from measurement values and not just the configuration of observations. This feature is beneficial, for example, for more accurate identification of soil contamination zones where high contamination measurements are located near measurements of varying contamination. The proposed design methodology is applied to a soil contamination example from the Swiss Jura region. A partial redesign of the original sampling configuration demonstrates the potential of the proposed methodology.

Association of FOXE1 Polyalanine Repeat Region with Papillary Thyroid Cancer

CONTEXT: Polyalanine tract variations in transcription factors have been identified for a wide spectrum of developmental disorders. The thyroid transcription factor forkhead factor E1 (FOXE1) contains a polymorphic polyalanine tract with 12-22 alanines. Single-nucleotide polymorphisms (SNP) close to this locus are associated with papillary thyroid cancer (PTC), and a strong linkage disequilibrium block extends across this region. OBJECTIVE: The objective of the study was to assess whether the FOXE1 polyalanine repeat region was associated with PTC and to assess the effect of polyalanine repeat region variants on protein expression, DNA binding, and transcriptional function on FOXE1-responsive promoters. DESIGN: This was a case-control study. SETTING: The study was conducted at a tertiary referral hospital. PATIENTS AND METHODS: The FOXE1 polyalanine repeat region and tag SNP were genotyped in 70 PTC, with a replication in a further 92 PTC, and compared with genotypes in 5767 healthy controls (including 5667 samples from the Wellcome Trust Case Control Consortium). In vitro studies were performed to examine the protein expression, DNA binding, and transcriptional function for FOXE1 variants of different polyalanine tract lengths. RESULTS: All the genotyped SNP were in tight linkage disequilibrium, including the FOXE1 polyalanine repeat region. We confirmed the strong association of rs1867277 with PTC (overall P = 1 × 10(-7), odds ratio 1.84, confidence interval 1.31-2.57). rs1867277 was in tight linkage disequilibrium with the FOXE1 polyalanine repeat region (r(2) = 0.95). FOXE1(16Ala) was associated with PTC with an odds ratio of 2.23 (confidence interval 1.42-3.50; P = 0.0005). Functional studies in vitro showed that FOXE1(16Ala) was transcriptionally impaired compared with FOXE1(14Ala), which was not due to differences in protein expression or DNA binding. CONCLUSIONS: We have confirmed the previous association of FOXE1 with PTC. Our data suggest that the coding polyalanine expansion in FOXE1 may be responsible for the observed association between FOXE1 and PTC.

Asia literate schooling in the Asian century [Book review]

In her introduction to this edited collection, Christine Halse lays out the purpose of the book as being about addressing three questions for education in contemporary times: What does Asia literacy mean?; Why is it important?; and How might or ought schools do Asia literacy? As a literacy educator it was these three questions that led to my interest in first reading and then reviewing the book. On numerous occasions I’ve felt the expectation that an expertise in Asia literacy should be a part of my toolbox. And yet I’ve always considered Asia literacy to be the responsibility of those who profess to know about – or have some expertise in – history, politics, or studies of society. But here was an edited collection with chapters from a variety of scholars who have informed my work over many years, framing schooling as a noun that could be described qualitatively as more or less Asia literate. As such, I took on the challenge to open up to these ideas and to the opportunity to think again about literacy and the use of this term in pairings such as Asia literacy. I had my own question to add to those of the editor. Can, or even should, literacy be used to describe the skills, capacities and understandings required for citizens to “reflect and explore cultural differences in the Asian region” (Asia Literacy Teachers’ Association of Australia, n.d.) in ways that support engagement within and with Asian peoples and their cultures?

Forecasting day-ahead electricity load using a multiple equation time series approach

The quality of short-term electricity load forecasting is crucial to the operation and trading activities of market participants in an electricity market. In this paper, it is shown that a multiple equation time-series model, which is estimated by repeated application of ordinary least squares, has the potential to match or even outperform more complex nonlinear and nonparametric forecasting models. The key ingredient of the success of this simple model is the effective use of lagged information by allowing for interaction between seasonal patterns and intra-day dependencies. Although the model is built using data for the Queensland region of Australia, the method is completely generic and applicable to any load forecasting problem. The model’s forecasting ability is assessed by means of the mean absolute percentage error (MAPE). For day-ahead forecast, the MAPE returned by the model over a period of 11 years is an impressive 1.36%. The forecast accuracy of the model is compared with a number of benchmarks including three popular alternatives and one industrial standard reported by the Australia Energy Market Operator (AEMO). The performance of the model developed in this paper is superior to all benchmarks and outperforms the AEMO forecasts by about a third in terms of the MAPE criterion.

A pilot study of the Social Water Assessment Protocol in a mining region of Ghana

The Social Water Assessment Protocol (SWAP) is a tool consisting of a series of questions on fourteen themes designed to capture the social context of water around a mine site. A pilot study of the SWAP, conducted in Prestea-Huni Valley, Ghana, showed that some communities were concerned about whether the groundwater was potable. The mining company’s concern was that there was a cycle of dependency amongst communities that received treated water from the mining company. The pilot identified potential data sources and stakeholder groups for each theme, gaps in themes and suggested refinements to questions to improve the SWAP.

Analysis of cool roof coatings for residential demand side management in tropical Australia

Cool roof coatings have a beneficial impact on reducing the heat load of a range of building types, resulting in reduced cooling energy loads. This study seeks to understand the extent to which cool roof coatings could be used as a residential demand side management (DSM) strategy for retrofitting existing housing in a constrained network area in tropical Australia where peak electrical demand is heavily influenced by residential cooling loads. In particular this study seeks to determine whether simulation software used for building regulation purposes can provide networks with the ‘impact certainty’ required by their DSM principles. The building simulation method is supported by a field experiment. Both numerical and experimental data confirm reductions in total consumption (kWh) and energy demand (kW). The nature of the regulated simulation software, combined with the diverse nature of residential buildings and their patterns of occupancy, however, mean that simulated results cannot be extrapolated to quantify benefits to a broader distribution network. The study suggests that building data gained from regulatory simulations could be a useful guide for potential impacts of widespread application of cool roof coatings in this region. The practical realization of these positive impacts, however, would require changes to the current business model for the evaluation of DSM strategies. The study provides seven key recommendations that encourage distribution networks to think beyond their infrastructure boundaries, recognising that the broader energy system also includes buildings, appliances and people.