Automated classification of limb fractures from free-text radiology reports using a clinician-informed gazetteer methodology

Background Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to dispersed information resources and a vast amount of manual processing of unstructured information, accurate point-of-care diagnosis is often difficult. Aims The aim of this research is to report initial experimental evaluation of a clinician-informed automated method for the issue of initial misdiagnoses associated with delayed receipt of unstructured radiology reports. Method A method was developed that resembles clinical reasoning for identifying limb abnormalities. The method consists of a gazetteer of keywords related to radiological findings; the method classifies an X-ray report as abnormal if it contains evidence contained in the gazetteer. A set of 99 narrative reports of radiological findings was sourced from a tertiary hospital. Reports were manually assessed by two clinicians and discrepancies were validated by a third expert ED clinician; the final manual classification generated by the expert ED clinician was used as ground truth to empirically evaluate the approach. Results The automated method that attempts to individuate limb abnormalities by searching for keywords expressed by clinicians achieved an F-measure of 0.80 and an accuracy of 0.80. Conclusion While the automated clinician-driven method achieved promising performances, a number of avenues for improvement were identified using advanced natural language processing (NLP) and machine learning techniques.

Classification of cancer-related death certificates using machine learning

Background Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities. Aims In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated. Method A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes. Results Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall F-measure of 0.9866 when evaluated on a set of 5,000 free-text death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers. Conclusion The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.

The mining boom and Western Australia's changing landscape : towards sustainability or business as usual?

The practices and public reputation of mining have been changing over time. In the past, mining operations frequently stood accused of being socially and environmentally disruptive, whereas mining today invests heavily in ‘socially responsible’ and ‘sustainable’ business practices. Changes such as these can be witnessed internationally as well as in places like Western Australia (WA), where the mining sector has matured into an economic pillar of the state, and indeed the nation in the context of the recent resources boom. This paper explores the role of mining in WA, presenting a multi-disciplinary perspective on the sector's contribution to sustainable development in the state. The perspectives offered here are drawn from community-based research and the associated academic literature as well as data derived from government sources and the not-for-profit sector. Findings suggest that despite noteworthy attitudinal and operational improvements in the industry, social, economic and environmental problem areas remain. As mining in WA is expected to grow in the years to come, these problem areas require the attention of business and government alike to ensure the long-term sustainability of development as well as people and place.

Social ecological influences on preferences for care provided at the end of life amongst Taiwanese city-dwelling adults

Social and cultural elements are an essential part of the contexts within which people understand their word and make end-of-life decisions. A developmental social ecological model was used in this thesis to provide a comprehensive framework for examining influences on end-of-life preferences. The findings support claims made by social ecologists that individual's health-related choices can be influenced by cultural, social contextual and environmental factors over the course of life. The results of this study have implications for health professionals and the practices they can adopt to enhance end-of-life care.

Pitfall (An Opportunistic Cultural Survey)

A pitfall is an unapparent source of trouble or danger; a hidden hazard: Today we all face, or will soon be facing ecological pitfalls of many kinds. ‘Pitfall’ is a continually-evolving artwork built from multiple screens, a tabletop landscape mapped with projections, fibre optics, 3D spatial sound and infrared night imagery. It builds upon ideas, recordings and cross-disciplinary processes developed during my 2012-13 ANAT Synapse Art-Science residency, with the Australian Wildlife Conservancy (AWC), Australia’s largest private-sector conservation organisation.

The re-introduction project

The Re-introduction Project began with an art-science research residency in 2012, funded through the Australian 'Synapse' art-science residency program. It was developed in partnership with the Australian Wildlife Conservancy, Australia's largest private conservation agency and their South-East regional scientist Matt Hayward and conducted through a series of seven high intensity field-trips to AWC’s remote properties in VIC, NSW and SA. These trips coincided with key times at which the AWC’s mobile scientific teams were undertaking intensive scientific activities. The program coincided with specific events that senior scientist collaborator Dr Matt Hayward led in 2012 at Mallee Regions (Yookamurra, Scotia and Buckaringa), Lake Eyre Basin (Kalamurina) and Sydney (North Head). The initial outcome of the project was the work Pitfall (An Opportunistic Survey) - a new media installation created in light, media, object, text and sound presented near the AWC headquarters at Mildura in far NW Victoria. Pitfall built upon ideas and cross disciplinary processes developed during this residency/collaboration with Australian Wildlife Conservancy inspired by working with their ecological scientists during pitfall-trap survey events used to survey small mammals and invertebrates. ‘Pitfall’ was designed in response to a playful survey that I asked the AWC scientists to engage with around ideas of avoiding ecological pitfalls into the future. This continually-evolving artwork was built from multiple screens, a tabletop landscape mapped with projections, fibre optics, 3D spatial sound and infrared night imagery.

Random projections on manifolds of symmetric positive definite matrices for image classification

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance. Taking into account manifold geometry is typically done via (1) embedding the manifolds in tangent spaces, or (2) embedding into Reproducing Kernel Hilbert Spaces (RKHS). While embedding into tangent spaces allows the use of existing Euclidean-based learning algorithms, manifold shape is only approximated which can cause loss of discriminatory information. The RKHS approach retains more of the manifold structure, but may require non-trivial effort to kernelise Euclidean-based learning algorithms. In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved. Specifically, we propose to project SPD matrices using a set of random projection hyperplanes over RKHS into a random projection space, which leads to representing each matrix as a vector of projection coefficients. Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome, Riemannian Locality Preserving Projection and Relational Divergence Classification.

Automatic classification of human epithelial type 2 cell indirect immunofluorescence images using cell pyramid matching

This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol. The IIF protocol on HEp-2 cells has been the hallmark method to identify the presence of ANAs, due to its high sensitivity and the large range of antigens that can be detected. However, it suffers from numerous shortcomings, such as being subjective as well as time and labour intensive. Computer Aided Diagnostic (CAD) systems have been developed to address these problems, which automatically classify a HEp-2 cell image into one of its known patterns (eg. speckled, homogeneous). Most of the existing CAD systems use handpicked features to represent a HEp-2 cell image, which may only work in limited scenarios. We propose a novel automatic cell image classification method termed Cell Pyramid Matching (CPM), which is comprised of regional histograms of visual words coupled with the Multiple Kernel Learning framework. We present a study of several variations of generating histograms and show the efficacy of the system on two publicly available datasets: the ICPR HEp-2 cell classification contest dataset and the SNPHEp-2 dataset.

Improved image set classification via joint sparse approximated nearest subspaces

Existing multi-model approaches for image set classification extract local models by clustering each image set individually only once, with fixed clusters used for matching with other image sets. However, this may result in the two closest clusters to represent different characteristics of an object, due to different undesirable environmental conditions (such as variations in illumination and pose). To address this problem, we propose to constrain the clustering of each query image set by forcing the clusters to have resemblance to the clusters in the gallery image sets. We first define a Frobenius norm distance between subspaces over Grassmann manifolds based on reconstruction error. We then extract local linear subspaces from a gallery image set via sparse representation. For each local linear subspace, we adaptively construct the corresponding closest subspace from the samples of a probe image set by joint sparse representation. We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold. Experiments on Honda, ETH-80 and Cambridge-Gesture datasets show that the proposed method consistently outperforms several other recent techniques, such as Affine Hull based Image Set Distance (AHISD), Sparse Approximated Nearest Points (SANP) and Manifold Discriminant Analysis (MDA).

Ecological risk analysis of transgenic plants

Public concern about the safety of many forms of industrial technology are known to be linked to a range of factors including a perceived lack of confidence in regulatory decision making.1 The use of transgenic plants in agriculture may be seen as an issue that could generate similar concern. Criticism has been made about the completeness of knowledge on the potential for aberrant behaviour of genetically manipulated organisms (GMO's) in release environments, and the adequacy of existing pre­‐release screening and assessment methodologies (Goldberg & Tjaden, 1990). Such comments are important because any perceived shortcomings in the pre-release assessment of GMO safety may lead to decreased public support of the technology -­‐and the industry itself...

Designing mixed species tree plantations for the tropics : balancing ecological attributes of species with landholder preferences in the Philippines

A mixed species reforestation program known as the Rainforestation Farming system was undertaken in the Philippines to develop forms of farm forestry more suitable for smallholders than the simple monocultural plantations commonly used then. In this study, we describe the subsequent changes in stand structure and floristic composition of these plantations in order to learn from the experience and develop improved prescriptions for reforestation systems likely to be attractive to smallholders. We investigated stands aged from 6 to 11 years old on three successive occasions over a 6 year period. We found the number of species originally present in the plots as trees >5 cm dbh decreased from an initial total of 76 species to 65 species at the end of study period. But, at the same time, some new species reached the size class threshold and were recruited into the canopy layer. There was a substantial decline in tree density from an estimated stocking of about 5000 trees per ha at the time of planting to 1380 trees per ha at the time of the first measurement; the density declined by a further 4.9% per year. Changes in composition and stand structure were indicated by a marked shift in the Importance Value Index of species. Over six years, shade-intolerant species became less important and the native shade-tolerant species (often Dipterocarps) increased in importance. Based on how the Rainforestation Farming plantations developed in these early years, we suggest that mixed-species plantations elsewhere in the humid tropics should be around 1000 trees per ha or less, that the proportion of fast growing (and hence early maturing) trees should be about 30–40% of this initial density and that any fruit tree component should only be planted on the plantation margin where more light and space are available for crowns to develop.

Accurately defining the reference condition for summary biotic metrics: A comparison of four approaches

Protocols for bioassessment often relate changes in summary metrics that describe aspects of biotic assemblage structure and function to environmental stress. Biotic assessment using multimetric indices now forms the basis for setting regulatory standards for stream quality and a range of other goals related to water resource management in the USA and elsewhere. Biotic metrics are typically interpreted with reference to the expected natural state to evaluate whether a site is degraded. It is critical that natural variation in biotic metrics along environmental gradients is adequately accounted for, in order to quantify human disturbance-induced change. A common approach used in the IBI is to examine scatter plots of variation in a given metric along a single stream size surrogate and a fit a line (drawn by eye) to form the upper bound, and hence define the maximum likely value of a given metric in a site of a given environmental characteristic (termed the 'maximum species richness line' - MSRL). In this paper we examine whether the use of a single environmental descriptor and the MSRL is appropriate for defining the reference condition for a biotic metric (fish species richness) and for detecting human disturbance gradients in rivers of south-eastern Queensland, Australia. We compare the accuracy and precision of the MSRL approach based on single environmental predictors, with three regression-based prediction methods (Simple Linear Regression, Generalised Linear Modelling and Regression Tree modelling) that use (either singly or in combination) a set of landscape and local scale environmental variables as predictors of species richness. We compared the frequency of classification errors from each method against set biocriteria and contrast the ability of each method to accurately reflect human disturbance gradients at a large set of test sites. The results of this study suggest that the MSRL based upon variation in a single environmental descriptor could not accurately predict species richness at minimally disturbed sites when compared with SLR's based on equivalent environmental variables. Regression-based modelling incorporating multiple environmental variables as predictors more accurately explained natural variation in species richness than did simple models using single environmental predictors. Prediction error arising from the MSRL was substantially higher than for the regression methods and led to an increased frequency of Type I errors (incorrectly classing a site as disturbed). We suggest that problems with the MSRL arise from the inherent scoring procedure used and that it is limited to predicting variation in the dependent variable along a single environmental gradient.

A Bayesian hurdle model for analysis of an insect resistance monitoring database

Motivated by the analysis of the Australian Grain Insect Resistance Database (AGIRD), we develop a Bayesian hurdle modelling approach to assess trends in strong resistance of stored grain insects to phosphine over time. The binary response variable from AGIRD indicating presence or absence of strong resistance is characterized by a majority of absence observations and the hurdle model is a two step approach that is useful when analyzing such a binary response dataset. The proposed hurdle model utilizes Bayesian classification trees to firstly identify covariates and covariate levels pertaining to possible presence or absence of strong resistance. Secondly, generalized additive models (GAMs) with spike and slab priors for variable selection are fitted to the subset of the dataset identified from the Bayesian classification tree indicating possibility of presence of strong resistance. From the GAM we assess trends, biosecurity issues and site specific variables influencing the presence of strong resistance using a variable selection approach. The proposed Bayesian hurdle model is compared to its frequentist counterpart, and also to a naive Bayesian approach which fits a GAM to the entire dataset. The Bayesian hurdle model has the benefit of providing a set of good trees for use in the first step and appears to provide enough flexibility to represent the influence of variables on strong resistance compared to the frequentist model, but also captures the subtle changes in the trend that are missed by the frequentist and naive Bayesian models.

Polarization of forecast densities : a new approach to time series classification

Time series classification has been extensively explored in many fields of study. Most methods are based on the historical or current information extracted from data. However, if interest is in a specific future time period, methods that directly relate to forecasts of time series are much more appropriate. An approach to time series classification is proposed based on a polarization measure of forecast densities of time series. By fitting autoregressive models, forecast replicates of each time series are obtained via the bias-corrected bootstrap, and a stationarity correction is considered when necessary. Kernel estimators are then employed to approximate forecast densities, and discrepancies of forecast densities of pairs of time series are estimated by a polarization measure, which evaluates the extent to which two densities overlap. Following the distributional properties of the polarization measure, a discriminant rule and a clustering method are proposed to conduct the supervised and unsupervised classification, respectively. The proposed methodology is applied to both simulated and real data sets, and the results show desirable properties.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.