Deriving a preference-based measure for cancer using the EORTC QLQ-C30 : a confirmatory versus exploratory approach

Background: To derive preference-based measures from various condition-specific descriptive health-related quality of life (HRQOL) measures. A general 2-stage method is evolved: 1) an item from each domain of the HRQOL measure is selected to form a health state classification system (HSCS); 2) a sample of health states is valued and an algorithm derived for estimating the utility of all possible health states. The aim of this analysis was to determine whether confirmatory or exploratory factor analysis (CFA, EFA) should be used to derive a cancer-specific utility measure from the EORTC QLQ-C30. Methods: Data were collected with the QLQ-C30v3 from 356 patients receiving palliative radiotherapy for recurrent or metastatic cancer (various primary sites). The dimensional structure of the QLQ-C30 was tested with EFA and CFA, the latter based on a conceptual model (the established domain structure of the QLQ-C30: physical, role, emotional, social and cognitive functioning, plus several symptoms) and clinical considerations (views of both patients and clinicians about issues relevant to HRQOL in cancer). The dimensions determined by each method were then subjected to item response theory, including Rasch analysis. Results: CFA results generally supported the proposed conceptual model, with residual correlations requiring only minor adjustments (namely, introduction of two cross-loadings) to improve model fit (increment χ2(2) = 77.78, p < .001). Although EFA revealed a structure similar to the CFA, some items had loadings that were difficult to interpret. Further assessment of dimensionality with Rasch analysis aligned the EFA dimensions more closely with the CFA dimensions. Three items exhibited floor effects (>75% observation at lowest score), 6 exhibited misfit to the Rasch model (fit residual > 2.5), none exhibited disordered item response thresholds, 4 exhibited DIF by gender or cancer site. Upon inspection of the remaining items, three were considered relatively less clinically important than the remaining nine. Conclusions: CFA appears more appropriate than EFA, given the well-established structure of the QLQ-C30 and its clinical relevance. Further, the confirmatory approach produced more interpretable results than the exploratory approach. Other aspects of the general method remain largely the same. The revised method will be applied to a large number of data sets as part of the international and interdisciplinary project to develop a multi-attribute utility instrument for cancer (MAUCa).

Prediction of transcriptional regulatory interactions in bacteria : a comparative genomics approach

Exponential growth of genomic data in the last two decades has made manual analyses impractical for all but trial studies. As genomic analyses have become more sophisticated, and move toward comparisons across large datasets, computational approaches have become essential. One of the most important biological questions is to understand the mechanisms underlying gene regulation. Genetic regulation is commonly investigated and modelled through the use of transcriptional regulatory network (TRN) structures. These model the regulatory interactions between two key components: transcription factors (TFs) and the target genes (TGs) they regulate. Transcriptional regulatory networks have proven to be invaluable scientific tools in Bioinformatics. When used in conjunction with comparative genomics, they have provided substantial insights into the evolution of regulatory interactions. Current approaches to regulatory network inference, however, omit two additional key entities: promoters and transcription factor binding sites (TFBSs). In this study, we attempted to explore the relationships among these regulatory components in bacteria. Our primary goal was to identify relationships that can assist in reducing the high false positive rates associated with transcription factor binding site predictions and thereupon enhance the reliability of the inferred transcription regulatory networks. In our preliminary exploration of relationships between the key regulatory components in Escherichia coli transcription, we discovered a number of potentially useful features. The combination of location score and sequence dissimilarity scores increased de novo binding site prediction accuracy by 13.6%. Another important observation made was with regards to the relationship between transcription factors grouped by their regulatory role and corresponding promoter strength. Our study of E.coli ��70 promoters, found support at the 0.1 significance level for our hypothesis | that weak promoters are preferentially associated with activator binding sites to enhance gene expression, whilst strong promoters have more repressor binding sites to repress or inhibit gene transcription. Although the observations were specific to �70, they nevertheless strongly encourage additional investigations when more experimentally confirmed data are available. In our preliminary exploration of relationships between the key regulatory components in E.coli transcription, we discovered a number of potentially useful features { some of which proved successful in reducing the number of false positives when applied to re-evaluate binding site predictions. Of chief interest was the relationship observed between promoter strength and TFs with respect to their regulatory role. Based on the common assumption, where promoter homology positively correlates with transcription rate, we hypothesised that weak promoters would have more transcription factors that enhance gene expression, whilst strong promoters would have more repressor binding sites. The t-tests assessed for E.coli �70 promoters returned a p-value of 0.072, which at 0.1 significance level suggested support for our (alternative) hypothesis; albeit this trend may only be present for promoters where corresponding TFBSs are either all repressors or all activators. Nevertheless, such suggestive results strongly encourage additional investigations when more experimentally confirmed data will become available. Much of the remainder of the thesis concerns a machine learning study of binding site prediction, using the SVM and kernel methods, principally the spectrum kernel. Spectrum kernels have been successfully applied in previous studies of protein classification [91, 92], as well as the related problem of promoter predictions [59], and we have here successfully applied the technique to refining TFBS predictions. The advantages provided by the SVM classifier were best seen in `moderately'-conserved transcription factor binding sites as represented by our E.coli CRP case study. Inclusion of additional position feature attributes further increased accuracy by 9.1% but more notable was the considerable decrease in false positive rate from 0.8 to 0.5 while retaining 0.9 sensitivity. Improved prediction of transcription factor binding sites is in turn extremely valuable in improving inference of regulatory relationships, a problem notoriously prone to false positive predictions. Here, the number of false regulatory interactions inferred using the conventional two-component model was substantially reduced when we integrated de novo transcription factor binding site predictions as an additional criterion for acceptance in a case study of inference in the Fur regulon. This initial work was extended to a comparative study of the iron regulatory system across 20 Yersinia strains. This work revealed interesting, strain-specific difierences, especially between pathogenic and non-pathogenic strains. Such difierences were made clear through interactive visualisations using the TRNDifi software developed as part of this work, and would have remained undetected using conventional methods. This approach led to the nomination of the Yfe iron-uptake system as a candidate for further wet-lab experimentation due to its potential active functionality in non-pathogens and its known participation in full virulence of the bubonic plague strain. Building on this work, we introduced novel structures we have labelled as `regulatory trees', inspired by the phylogenetic tree concept. Instead of using gene or protein sequence similarity, the regulatory trees were constructed based on the number of similar regulatory interactions. While the common phylogentic trees convey information regarding changes in gene repertoire, which we might regard being analogous to `hardware', the regulatory tree informs us of the changes in regulatory circuitry, in some respects analogous to `software'. In this context, we explored the `pan-regulatory network' for the Fur system, the entire set of regulatory interactions found for the Fur transcription factor across a group of genomes. In the pan-regulatory network, emphasis is placed on how the regulatory network for each target genome is inferred from multiple sources instead of a single source, as is the common approach. The benefit of using multiple reference networks, is a more comprehensive survey of the relationships, and increased confidence in the regulatory interactions predicted. In the present study, we distinguish between relationships found across the full set of genomes as the `core-regulatory-set', and interactions found only in a subset of genomes explored as the `sub-regulatory-set'. We found nine Fur target gene clusters present across the four genomes studied, this core set potentially identifying basic regulatory processes essential for survival. Species level difierences are seen at the sub-regulatory-set level; for example the known virulence factors, YbtA and PchR were found in Y.pestis and P.aerguinosa respectively, but were not present in both E.coli and B.subtilis. Such factors and the iron-uptake systems they regulate, are ideal candidates for wet-lab investigation to determine whether or not they are pathogenic specific. In this study, we employed a broad range of approaches to address our goals and assessed these methods using the Fur regulon as our initial case study. We identified a set of promising feature attributes; demonstrated their success in increasing transcription factor binding site prediction specificity while retaining sensitivity, and showed the importance of binding site predictions in enhancing the reliability of regulatory interaction inferences. Most importantly, these outcomes led to the introduction of a range of visualisations and techniques, which are applicable across the entire bacterial spectrum and can be utilised in studies beyond the understanding of transcriptional regulatory networks.

A picture is worth a thousand words : an approach to learning about visuals

Students in the middle years encounter an increasing range of unfamiliar visuals. Visual literacy, the ability to encode and decode visuals and to think visually, is an expectation of all middle years curriculum areas and an expectation of NAPLAN literacy and numeracy tests. This article presents a multidisciplinary approach to teaching visual literacy that links the content of all learning areas and encourages students to transfer skills from familiar to unfamiliar contexts. It proposes a classification of visuals in six parts: one-dimensional; two-dimensional; map; shape; connection; and picture, based on the properties, rather than the purpose, of the visual. By placing a visual in one of these six categories, students learn to transfer the skills used to decode familiar visuals to unfamiliar cases in the same category. The article also discusses a range of other teaching strategies that can be used to complement this multi-disciplinary approach.

An ingenuous Decision Support System (iDSS) approach for remote area pregnant women

This paper addresses development of an ingenious decision support system (iDSS) based on the methodology of survey instruments and identification of significant variables to be used in iDSS using statistical analysis. A survey was undertaken with pregnant women and factorial experimental design was chosen to acquire sample size. Variables with good reliability in any one of the statistical techniques such as Chi-square, Cronbach’s α and Classification Tree were incorporated in the iDSS. The ingenious decision support system was implemented with Visual Basic as front end and Microsoft SQL server management as backend. Outcome of the ingenious decision support system include advice on Symptoms, Diet and Exercise to pregnant women.

The ‘Russian doll’ approach : developing nested case-studies to support international comparative research in education

International comparison is complicated by the use of different terms, classification methods, policy frameworks and system structures, not to mention different languages and terminology. Multi-case studies can assist in the understanding of the influence wielded by cultural, social, economic, historical and political forces upon educational decisions, policy construction and changes over time. But case studies alone are not enough. In this paper, we argue for an ecological or scaled approach that travels through macro, meso and micro levels to build nested case-studies to allow for more comprehensive analysis of the external and internal factors that shape policy-making and education systems. Such an approach allows for deeper understanding of the relationship between globalizing trends and policy developments.

A picture is worth a thousand words : a cross-curricular approach to learning about visuals in STEM

Visuals are a central feature of STEM in all levels of education and many areas of employment. The wide variety of visuals that students are expected to master in STEM prevents an approach that aims to teach students about every type of visual that they may encounter. This paper proposes a pedagogy that can be applied across year levels and learning areas, allowing a school-wide, cross-curricular, approach to teaching about visual, that enhances learning in STEM and all other learning areas. Visuals are classified into six categories based on their properties, unlike traditional methods that classify visuals according to purpose. As visuals in the same category share common properties, students are able to transfer their knowledge from the familiar to unfamiliar in each category. The paper details the classification and proposes some strategies that can be can be incorporated into existing methods of teaching students about visuals in all learning areas. The approach may also assist students to see the connections between the different learning areas within and outside STEM.

A two-stage approach for generating topic models

Topic modeling has been widely utilized in the fields of information retrieval, text mining, text classification etc. Most existing statistical topic modeling methods such as LDA and pLSA generate a term based representation to represent a topic by selecting single words from multinomial word distribution over this topic. There are two main shortcomings: firstly, popular or common words occur very often across different topics that bring ambiguity to understand topics; secondly, single words lack coherent semantic meaning to accurately represent topics. In order to overcome these problems, in this paper, we propose a two-stage model that combines text mining and pattern mining with statistical modeling to generate more discriminative and semantic rich topic representations. Experiments show that the optimized topic representations generated by the proposed methods outperform the typical statistical topic modeling method LDA in terms of accuracy and certainty.

Malnutrition in Parkinson's disease and an individualised approach to its management

It has been reported that poor nutritional status, in the form of weight loss and resulting body mass index (BMI) changes, is an issue in people with Parkinson's disease (PWP). The symptoms resulting from Parkinson's disease (PD) and the side effects of PD medication have been implicated in the aetiology of nutritional decline. However, the evidence on which these claims are based is, on one hand, contradictory, and on the other, restricted primarily to otherwise healthy PWP. Despite the claims that PWP suffer from poor nutritional status, evidence is lacking to inform nutrition-related care for the management of malnutrition in PWP. The aims of this thesis were to better quantify the extent of poor nutritional status in PWP, determine the important factors differentiating the well-nourished from the malnourished and evaluate the effectiveness of an individualised nutrition intervention on nutritional status. Phase DBS: Nutritional status in people with Parkinson's disease scheduled for deep-brain stimulation surgery The pre-operative rate of malnutrition in a convenience sample of people with Parkinson's disease (PWP) scheduled for deep-brain stimulation (DBS) surgery was determined. Poorly controlled PD symptoms may result in a higher risk of malnutrition in this sub-group of PWP. Fifteen patients (11 male, median age 68.0 (42.0 – 78.0) years, median PD duration 6.75 (0.5 – 24.0) years) participated and data were collected during hospital admission for the DBS surgery. The scored PG-SGA was used to assess nutritional status, anthropometric measures (weight, height, mid-arm circumference, waist circumference, body mass index (BMI)) were taken, and body composition was measured using bioelectrical impedance spectroscopy (BIS). Six (40%) of the participants were malnourished (SGA-B) while 53% reported significant weight loss following diagnosis. BMI was significantly different between SGA-A and SGA-B (25.6 vs 23.0kg/m 2, p<.05). There were no differences in any other variables, including PG-SGA score and the presence of non-motor symptoms. The conclusion was that malnutrition in this group is higher than that in other studies reporting malnutrition in PWP, and it is under-recognised. As poorer surgical outcomes are associated with poorer pre-operative nutritional status in other surgeries, it might be beneficial to identify patients at nutritional risk prior to surgery so that appropriate nutrition interventions can be implemented. Phase I: Nutritional status in community-dwelling adults with Parkinson's disease The rate of malnutrition in community-dwelling adults (>18 years) with Parkinson's disease was determined. One hundred twenty-five PWP (74 male, median age 70.0 (35.0 – 92.0) years, median PD duration 6.0 (0.0 – 31.0) years) participated. The scored PG-SGA was used to assess nutritional status, anthropometric measures (weight, height, mid-arm circumference (MAC), calf circumference, waist circumference, body mass index (BMI)) were taken. Nineteen (15%) of the participants were malnourished (SGA-B). All anthropometric indices were significantly different between SGA-A and SGA-B (BMI 25.9 vs 20.0kg/m2; MAC 29.1 – 25.5cm; waist circumference 95.5 vs 82.5cm; calf circumference 36.5 vs 32.5cm; all p<.05). The PG-SGA score was also significantly lower in the malnourished (2 vs 8, p<.05). The nutrition impact symptoms which differentiated between well-nourished and malnourished were no appetite, constipation, diarrhoea, problems swallowing and feel full quickly. This study concluded that malnutrition in community-dwelling PWP is higher than that documented in community-dwelling elderly (2 – 11%), yet is likely to be under-recognised. Nutrition impact symptoms play a role in reduced intake. Appropriate screening and referral processes should be established for early detection of those at risk. Phase I: Nutrition assessment tools in people with Parkinson's disease There are a number of validated and reliable nutrition screening and assessment tools available for use. None of these tools have been evaluated in PWP. In the sample described above, the use of the World Health Organisation (WHO) cut-off (≤18.5kg/m2), age-specific BMI cut-offs (≤18.5kg/m2 for under 65 years, ≤23.5kg/m2 for 65 years and older) and the revised Mini-Nutritional Assessment short form (MNA-SF) were evaluated as nutrition screening tools. The PG-SGA (including the SGA classification) and the MNA full form were evaluated as nutrition assessment tools using the SGA classification as the gold standard. For screening, the MNA-SF performed the best with sensitivity (Sn) of 94.7% and specificity (Sp) of 78.3%. For assessment, the PG-SGA with a cut-off score of 4 (Sn 100%, Sp 69.8%) performed better than the MNA (Sn 84.2%, Sp 87.7%). As the MNA has been recommended more for use as a nutrition screening tool, the MNA-SF might be more appropriate and take less time to complete. The PG-SGA might be useful to inform and monitor nutrition interventions. Phase I: Predictors of poor nutritional status in people with Parkinson's disease A number of assessments were conducted as part of the Phase I research, including those for the severity of PD motor symptoms, cognitive function, depression, anxiety, non-motor symptoms, constipation, freezing of gait and the ability to carry out activities of daily living. A higher score in all of these assessments indicates greater impairment. In addition, information about medical conditions, medications, age, age at PD diagnosis and living situation was collected. These were compared between those classified as SGA-A and as SGA-B. Regression analysis was used to identify which factors were predictive of malnutrition (SGA-B). Differences between the groups included disease severity (4% more severe SGA-A vs 21% SGA-B, p<.05), activities of daily living score (13 SGA-A vs 18 SGA-B, p<.05), depressive symptom score (8 SGA-A vs 14 SGA-B, p<.05) and gastrointestinal symptoms (4 SGA-A vs 6 SGA-B, p<.05). Significant predictors of malnutrition according to SGA were age at diagnosis (OR 1.09, 95% CI 1.01 – 1.18), amount of dopaminergic medication per kg body weight (mg/kg) (OR 1.17, 95% CI 1.04 – 1.31), more severe motor symptoms (OR 1.10, 95% CI 1.02 – 1.19), less anxiety (OR 0.90, 95% CI 0.82 – 0.98) and more depressive symptoms (OR 1.23, 95% CI 1.07 – 1.41). Significant predictors of a higher PG-SGA score included living alone (β=0.14, 95% CI 0.01 – 0.26), more depressive symptoms (β=0.02, 95% CI 0.01 – 0.02) and more severe motor symptoms (OR 0.01, 95% CI 0.01 – 0.02). More severe disease is associated with malnutrition, and this may be compounded by lack of social support. Phase II: Nutrition intervention Nineteen of the people identified in Phase I as requiring nutrition support were included in Phase II, in which a nutrition intervention was conducted. Nine participants were in the standard care group (SC), which received an information sheet only, and the other 10 participants were in the intervention group (INT), which received individualised nutrition information and weekly follow-up. INT gained 2.2% of starting body weight over the 12 week intervention period resulting in significant increases in weight, BMI, mid-arm circumference and waist circumference. The SC group gained 1% of starting weight over the 12 weeks which did not result in any significant changes in anthropometric indices. Energy and protein intake (18.3kJ/kg vs 3.8kJ/kg and 0.3g/kg vs 0.15g/kg) increased in both groups. The increase in protein intake was only significant in the SC group. The changes in intake, when compared between the groups, were no different. There were no significant changes in any motor or non-motor symptoms or in "off" times or dyskinesias in either group. Aspects of quality of life improved over the 12 weeks as well, especially emotional well-being. This thesis makes a significant contribution to the evidence base for the presence of malnutrition in Parkinson's disease as well as for the identification of those who would potentially benefit from nutrition screening and assessment. The nutrition intervention demonstrated that a traditional high protein, high energy approach to the management of malnutrition resulted in improved nutritional status and anthropometric indices with no effect on the presence of Parkinson's disease symptoms and a positive effect on quality of life.

Predicting fault-prone software modules with rank sum classification

The detection and correction of defects remains among the most time consuming and expensive aspects of software development. Extensive automated testing and code inspections may mitigate their effect, but some code fragments are necessarily more likely to be faulty than others, and automated identification of fault prone modules helps to focus testing and inspections, thus limiting wasted effort and potentially improving detection rates. However, software metrics data is often extremely noisy, with enormous imbalances in the size of the positive and negative classes. In this work, we present a new approach to predictive modelling of fault proneness in software modules, introducing a new feature representation to overcome some of these issues. This rank sum representation offers improved or at worst comparable performance to earlier approaches for standard data sets, and readily allows the user to choose an appropriate trade-off between precision and recall to optimise inspection effort to suit different testing environments. The method is evaluated using the NASA Metrics Data Program (MDP) data sets, and performance is compared with existing studies based on the Support Vector Machine (SVM) and Naïve Bayes (NB) Classifiers, and with our own comprehensive evaluation of these methods.

Local inter-session variability modelling for object classification

Object classification is plagued by the issue of session variation. Session variation describes any variation that makes one instance of an object look different to another, for instance due to pose or illumination variation. Recent work in the challenging task of face verification has shown that session variability modelling provides a mechanism to overcome some of these limitations. However, for computer vision purposes, it has only been applied in the limited setting of face verification. In this paper we propose a local region based intersession variability (ISV) modelling approach, and apply it to challenging real-world data. We propose a region based session variability modelling approach so that local session variations can be modelled, termed Local ISV. We then demonstrate the efficacy of this technique on a challenging real-world fish image database which includes images taken underwater, providing significant real-world session variations. This Local ISV approach provides a relative performance improvement of, on average, 23% on the challenging MOBIO, Multi-PIE and SCface face databases. It also provides a relative performance improvement of 35% on our challenging fish image dataset.

Real-time image classification for adaptive mission planning using an Autonomous Underwater Vehicle

Real-time image analysis and classification onboard robotic marine vehicles, such as AUVs, is a key step in the realisation of adaptive mission planning for large-scale habitat mapping in previously unexplored environments. This paper describes a novel technique to train, process, and classify images collected onboard an AUV used in relatively shallow waters with poor visibility and non-uniform lighting. The approach utilises Förstner feature detectors and Laws texture energy masks for image characterisation, and a bag of words approach for feature recognition. To improve classification performance we propose a usefulness gain to learn the importance of each histogram component for each class. Experimental results illustrate the performance of the system in characterisation of a variety of marine habitats and its ability to operate onboard an AUV's main processor suitable for real-time mission planning.

Classification of pathology reports for cancer registry notifications

Objective: To develop a system for the automatic classification of pathology reports for Cancer Registry notifications. Method: A two pass approach is proposed to classify whether pathology reports are cancer notifiable or not. The first pass queries pathology HL7 messages for known report types that are received by the Queensland Cancer Registry (QCR), while the second pass aims to analyse the free text reports and identify those that are cancer notifiable. Cancer Registry business rules, natural language processing and symbolic reasoning using the SNOMED CT ontology were adopted in the system. Results: The system was developed on a corpus of 500 histology and cytology reports (with 47% notifiable reports) and evaluated on an independent set of 479 reports (with 52% notifiable reports). Results show that the system can reliably classify cancer notifiable reports with a sensitivity, specificity, and positive predicted value (PPV) of 0.99, 0.95, and 0.95, respectively for the development set, and 0.98, 0.96, and 0.96 for the evaluation set. High sensitivity can be achieved at a slight expense in specificity and PPV. Conclusion: The system demonstrates how medical free-text processing enables the classification of cancer notifiable pathology reports with high reliability for potential use by Cancer Registries and pathology laboratories.

Spatially-explicit modelling of grassland classes - an improved method of integrating a climate-based classification model with interpolated climate surfaces

Spatially-explicit modelling of grassland classes is important to site-specific planning for improving grassland and environmental management over large areas. In this study, a climate-based grassland classification model, the Comprehensive and Sequential Classification System (CSCS) was integrated with spatially interpolated climate data to classify grassland in Gansu province, China. The study area is characterized by complex topographic features imposed by plateaus, high mountains, basins and deserts. To improve the quality of the interpolated climate data and the quality of the spatial classification over this complex topography, three linear regression methods, namely an analytic method based on multiple regression and residues (AMMRR), a modification of the AMMRR method through adding the effect of slope and aspect to the interpolation analysis (M-AMMRR) and a method which replaces the IDW approach for residue interpolation in M-AMMRR with an ordinary kriging approach (I-AMMRR), for interpolating climate variables were evaluated. The interpolation outcomes from the best interpolation method were then used in the CSCS model to classify the grassland in the study area. Climate variables interpolated included the annual cumulative temperature and annual total precipitation. The results indicated that the AMMRR and M-AMMRR methods generated acceptable climate surfaces but the best model fit and cross validation result were achieved by the I-AMMRR method. Twenty-six grassland classes were classified for the study area. The four grassland vegetation classes that covered more than half of the total study area were "cool temperate-arid temperate zonal semi-desert", "cool temperate-humid forest steppe and deciduous broad-leaved forest", "temperate-extra-arid temperate zonal desert", and "frigid per-humid rain tundra and alpine meadow". The vegetation classification map generated in this study provides spatial information on the locations and extents of the different grassland classes. This information can be used to facilitate government agencies' decision-making in land-use planning and environmental management, and for vegetation and biodiversity conservation. The information can also be used to assist land managers in the estimation of safe carrying capacities which will help to prevent overgrazing and land degradation.

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.

Integrated approach for diagnostics and prognostics of HP LNG pump based on health state probability estimation

Effective machine fault prognostic technologies can lead to elimination of unscheduled downtime and increase machine useful life and consequently lead to reduction of maintenance costs as well as prevention of human casualties in real engineering asset management. This paper presents a technique for accurate assessment of the remnant life of machines based on health state probability estimation technique and historical failure knowledge embedded in the closed loop diagnostic and prognostic system. To estimate a discrete machine degradation state which can represent the complex nature of machine degradation effectively, the proposed prognostic model employed a classification algorithm which can use a number of damage sensitive features compared to conventional time series analysis techniques for accurate long-term prediction. To validate the feasibility of the proposed model, the five different level data of typical four faults from High Pressure Liquefied Natural Gas (HP-LNG) pumps were used for the comparison of intelligent diagnostic test using five different classification algorithms. In addition, two sets of impeller-rub data were analysed and employed to predict the remnant life of pump based on estimation of health state probability using the Support Vector Machine (SVM) classifier. The results obtained were very encouraging and showed that the proposed prognostics system has the potential to be used as an estimation tool for machine remnant life prediction in real life industrial applications.