Exploiting medical hierarchies for concept-based information retrieval

Search technologies are critical to enable clinical sta to rapidly and e ectively access patient information contained in free-text medical records. Medical search is challenging as terms in the query are often general but those in rel- evant documents are very speci c, leading to granularity mismatch. In this paper we propose to tackle granularity mismatch by exploiting subsumption relationships de ned in formal medical domain knowledge resources. In symbolic reasoning, a subsumption (or `is-a') relationship is a parent-child rela- tionship where one concept is a subset of another concept. Subsumed concepts are included in the retrieval function. In addition, we investigate a number of initial methods for combining weights of query concepts and those of subsumed concepts. Subsumption relationships were found to provide strong indication of relevant information; their inclusion in retrieval functions yields performance improvements. This result motivates the development of formal models of rela- tionships between medical concepts for retrieval purposes.

Exploiting SNOMED CT concepts and relationships for clinical information retrieval : Australian e-Health Research Centre and Queensland University of Technology at the TREC 2012 Medical Track

The Australian e-Health Research Centre and Queensland University of Technology recently participated in the TREC 2012 Medical Records Track. This paper reports on our methods, results and experience using an approach that exploits the concept and inter-concept relationships defined in the SNOMED CT medical ontology. Our concept-based approach is intended to overcome specific challenges in searching medical records, namely vocabulary mismatch and granularity mismatch. Queries and documents are transformed from their term-based originals into medical concepts as defined by the SNOMED CT ontology, this is done to tackle vocabulary mismatch. In addition, we make use of the SNOMED CT parent-child `is-a' relationships between concepts to weight documents that contained concept subsumed by the query concepts; this is done to tackle the problem of granularity mismatch. Finally, we experiment with other SNOMED CT relationships besides the is-a relationship to weight concepts related to query concepts. Results show our concept-based approach performed significantly above the median in all four performance metrics. Further improvements are achieved by the incorporation of weighting subsumed concepts, overall leading to improvement above the median of 28% infAP, 10% infNDCG, 12% R-prec and 7% Prec@10. The incorporation of other relations besides is-a demonstrated mixed results, more research is required to determined which SNOMED CT relationships are best employed when weighting related concepts.

Semantic judgement of medical concepts : combining syntagmatic and paradigmatic information with the tensor encoding model

This paper outlines a novel approach for modelling semantic relationships within medical documents. Medical terminologies contain a rich source of semantic information critical to a number of techniques in medical informatics, including medical information retrieval. Recent research suggests that corpus-driven approaches are effective at automatically capturing semantic similarities between medical concepts, thus making them an attractive option for accessing semantic information. Most previous corpus-driven methods only considered syntagmatic associations. In this paper, we adapt a recent approach that explicitly models both syntagmatic and paradigmatic associations. We show that the implicit similarity between certain medical concepts can only be modelled using paradigmatic associations. In addition, the inclusion of both types of associations overcomes the sensitivity to the training corpus experienced by previous approaches, making our method both more effective and more robust. This finding may have implications for researchers in the area of medical information retrieval.

Analysis of Cone-Beam CT using prior information

Treatment plans for conformal radiotherapy are based on an initial CT scan. The aim is to deliver the prescribed dose to the tumour, while minimising exposure to nearby organs. Recent advances make it possible to also obtain a Cone-Beam CT (CBCT) scan, once the patient has been positioned for treatment. A statistical model will be developed to compare these CBCT scans with the initial CT scan. Changes in the size, shape and position of the tumour and organs will be detected and quantified. Some progress has already been made in segmentation of prostate CBCT scans [1],[2],[3]. However, none of the existing approaches have taken full advantage of the prior information that is available. The planning CT scan is expertly annotated with contours of the tumour and nearby sensitive objects. This data is specific to the individual patient and can be viewed as a snapshot of spatial information at a point in time. There is an abundance of studies in the radiotherapy literature that describe the amount of variation in the relevant organs between treatments. The findings from these studies can form a basis for estimating the degree of uncertainty. All of this information can be incorporated as an informative prior into a Bayesian statistical model. This model will be developed using scans of CT phantoms, which are objects with known geometry. Thus, the accuracy of the model can be evaluated objectively. This will also enable comparison between alternative models.

Encouraging, assisting and time to EAT : improved nutritional intake for older medical patients receiving Protected Mealtimes and/or additional nursing feeding assistance

Background & Aims: Inadequate feeding assistance and mealtime interruptions during hospitalisation may contribute to malnutrition and poor nutritional intake in older people. This study aimed to implement and compare three interventions designed to specifically address mealtime barriers and improve energy intakes of medical inpatients aged ≥65 years. Methods: Pre-post study compared three mealtime assistance interventions: PM: Protected Mealtimes with multidisciplinary education; AIN: additional assistant-in-nursing (AIN) with dedicated meal role; PM+AIN: combined intervention. Dietary intake of 254 patients (pre: n=115, post: n=141; mean age 80±8) was visually estimated on a single day in the first week of hospitalisation and compared with estimated energy requirements. Assistance activities were observed and recorded. Results: Mealtime assistance levels significantly increased in all interventions (p<0.01). Post-intervention participants were more likely to achieve adequate energy intake (OR=3.4, p=0.01), with no difference noted between interventions (p=0.29). Patients with cognitive impairment or feeding dependency appeared to gain substantial benefit from mealtime assistance interventions. Conclusions: Protected Mealtimes and additional AIN assistance (implemented alone or in combination) may produce modest improvements in nutritional intake. Targeted feeding assistance for certain patient groups holds promise; however, alternative strategies are required to address the complex problem of malnutrition in this population.

The relationship between quality of work life and turnover intention of primary health care nurses in Saudi Arabia

Background Quality of work life (QWL) has been found to influence the commitment of health professionals including nurses. However, reliable information on the QWL and turnover intention of primary health care (PHC) nurses is limited. The aim of this study was to examine the relationship between QWL and turnover intention of PHC nurses in Saudi Arabia. Methods A cross-sectional survey was used in this study. Data were collected using Brooks’ survey of Quality of Nursing Work life (QNWL), the Anticipated Turnover Scale and demographic data questions. A total of 508 PHC nurses in the Jazan region, Saudi Arabia completed the questionnaire (RR = 87%). Descriptive statistics, t-test, ANOVA, General Linear Model (GLM) univariate analysis, standard multiple regression (SMR), and hierarchical multiple regression (HMR) were applied for analysis using SPSS v17 for Windows. Results Findings suggested that the respondents were dissatisfied with their work life, with almost 40% indicating a turnover intention from their current PHC centres. Turnover intention was significantly related to QWL. Using SMR, 26% of the variance in turnover intention was explained by the QWL, p < 0.001, with R² = .263. Further analysis using HMR found that the total variance explained by the model as a whole (demographics and QWL) was 32.1%, p < 0.001. QWL explained an additional 19% of the variance in turnover intention, after controlling for demographic variables. Conclusions Creating and maintaining a healthy work life for PHC nurses is very important to improve their work satisfaction, reduce turnover, enhance productivity and improve nursing care outcomes.

Increasing physical activity among women with young children: Results from the Proactive Mums Project

Context Evidence from the Australian Longitudinal Study of Women's Health suggests that mothers of young children have lower levels of physical activity (PA) than women of similar age without children. Objectives The aim of the ProActive Mums project was to determine the relative efficacy of two strategies designed to increase the proportion of mothers of young children who are meeting current PA guidelines, utilising child care centres (CCCs) as the setting for recruitment. Study Design The project used a randomised (after stratification to ensure even representation of CCCs from differing socio-economic areas) design incorporating repeated data collection from women in three groups, each consisting of 7 childcare centres (CCCs). Baseline surveys were completed by 554 mothers, with follow-up data collection immediately post-Intervention (8 weeks after baseline) and again 5 months later. Women from CCCs in Group 1 (control) received only the surveys throughout the duration of the project. Women from CCCs in Group 2 (information only) were given a print intervention, and women from CCCs in Group 3 were (in addition to being given the same print intervention as women from CCCs in Group 2) invited to to contribute to the development of, and participate in, strategies for the promotion of PA among mothers of young children. The two intervention strategies were extensively evaluated through a series of surveys and interviews. The Intervention The print intervention prescribed for women from CCCs in Group 2 and Group 3 consisted of an 8-page booklet containing motivational messages and information about physical activity. Women from CCCs in Group 3 were also invited to attend meetings at their CCC to identify strategies for increasing their PA. Contacts were made with key stakeholders in the community, including managers of sporting and recreation facilities, childcare service providers, and local councils. A wide range of strategies was developed during the intervention phase of the project, which specifically focused on the need to increase partner support and self-efficacy (or the confidence to be physically active). Results The mean age of participants was 33 (+ 4.8) years, and the mean number of children per family unit was 2.2 (± 0.9). At baseline, fewer than half the women were meeting current guidelines for adequate PA for health benefit, and there were no significant differences between groups in the proportion of women who were adequately active for health benefit. Women in Group 3 were significantly more likely to meet the guidelines at post-intervention follow-up than controls [OR = 1.71 (1.05-2.77)] after controlling for age and PA at baseline. There was no significant effect of the print intervention alone on meeting guidelines at post-intervention follow-up compared with controls, after controlling for age and PA at baseline [OR = 1.15 (0.70-1.89)]. Changes in Partner Support (PS) and Self Efficacy (SE) significantly predicted meeting current PA guidelines at post-intervention follow-up after controlling for baseline PA [∆ PS: OR = 2.29 (1.46-3.58); ∆ SE: OR = 1.86 (1.17- 2.94)]. The intervention effect in Group 3 was not maintained at long-term follow-up. Conclusions The findings indicate that a community participation approach that facilitates increased partner support and self-efficacy can be effective in increasing PA among mothers of young children. Changes in physical activity were found to be mediated by changes in partner support and self-efficacy for physical activity, suggesting that the intervention successfully targeted the individual characteristics it intended to, and that these variables do play an important role in increasing physical activity among women with young children. It is clear that further work needs to be done to explore methods of translating the short-term intervention effect shown in this study into long-term changes in PA behaviour. This study also provided insight into measurement issues in PA research and raised questions about self-report measures of PA and perceived constraints to being physically active. The results from post-study qualitative interviews suggest that many women at this life-stage experience time constraints which, when accompanied by a lack of partner support and financial constraints, make leisure-time PA virtually impossible for many women. Future strategies might focus on targeting this population immediately prior to this life-stage in an attempt to encourage habitual physical activity before women have children. Increasing PA in this population should also address the entire family unit, and consider the way leisure-time is negotiated among the adults within a household. Social change and increased awareness of the range of benefits of PA for women with children are additional strategies to be considered.

Efficient safety information retrieval on construction sites : a preliminary methodology

IT-supported field data management benefits on-site construction management by improving accessibility to the information and promoting efficient communication between project team members. However, most of on-site safety inspections still heavily rely on subjective judgment and manual reporting processes and thus observers’ experiences often determine the quality of risk identification and control. This study aims to develop a methodology to efficiently retrieve safety-related information so that the safety inspectors can easily access to the relevant site safety information for safer decision making. The proposed methodology consists of three stages: (1) development of a comprehensive safety database which contains information of risk factors, accident types, impact of accidents and safety regulations; (2) identification of relationships among different risk factors based on statistical analysis methods; and (3) user-specified information retrieval using data mining techniques for safety management. This paper presents an overall methodology and preliminary results of the first stage research conducted with 101 accident investigation reports.

International students using online information resources to learn : complex experience and learning needs

This paper reports the findings of a qualitative study which investigated 25 international students’ use of online information resources for study purposes at two Australian universities. Using an expanded critical incident approach, the study viewed international students through an information literacy lens, as information-using learners. The findings are presented in two complementary parts: as a word picture that describes their whole experience of using online information resources to learn; and as a tabulated set of critical findings that summarises their associated information literacy learning needs. The word picture shows international students’ resource use as a complex interplay of eight inter-related elements: students; information-learning environment; interactions (with online resources); strengths-challenges; learning-help; affective responses; reflective responses; cultural-linguistic dimensions. In using online resources, the international students experience an array of strengths and challenges, and an apparent information literacy imbalance between their more developed information skills and less developed critical information use. The critical findings about information literacy needs provide a framework for developing an inclusive informed learning approach that responds to international students’ complex information using experiences and needs. While the study is situated in Australia, the findings are of potential interest to educators, information professionals and researchers worldwide who seek to support learning in culturally diverse higher education contexts.

Using information communication technologies to develop dynamic curriculum frameworks for diverse cohorts: a case study from event management

This article investigates the role of information communication technologies (ICTs) in establishing a well-aligned, authentic learning environment for a diverse cohort of non-cognate and cognate students studying event management in a higher education context. Based on a case study which examined the way ICTs assisted in accommodating diverse learning needs, styles and stages in an event management subject offered in the Creative Industries Faculty at Queensland University of Technology in Brisbane, Australia, the article uses an action research approach to generate grounded, empirical data on the effectiveness of the dynamic, individualised curriculum frameworks that the use of ICTs makes possible. The study provides insights into the way non-cognate and cognate students respond to different learning tools. It finds that whilst non-cognate and cognate students do respond to learning tools differently, due to a differing degree of emphasis on technical, task or theoretical competencies, the use of ICTs allows all students to improve their performance by providing multiple points of entry into the content. In this respect, whilst the article focuses on the way ICTs can be used to develop an authentic, well-aligned curriculum model that meets the needs of event management students in a higher education context, with findings relevant for event educators in Business, Hospitality, Tourism and Creative Industries, the strategies outlined may also be useful for educators in other fields who are faced with similar challenges when designing and developing curriculum for diverse cohorts.

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.

Exploring the information practices of people with end stage kidney disease

This small exploratory study sought to understand how people with End Stage Kidney Disease (ESKD) experience the information environment and what information practices they employ in order to inform the decisions they make in relation to treatment and care. Using a constructivist methodology, in-depth interviews were conducted with five people who were receiving haemodialysis in two small satellite dialysis units located in regional and rural communities in New South Wales, Australia. Thematic analysis revealed two types of patients. The first type appears to adopt a received view of information, who do not question their condition; and passively accept information. In the other type, patients were found to be engaged; they actively identified their information needs and quickly learned what that they needed to ask and who to ask. Knowing the information practices of people with ESKD is useful for nephrology nurses when providing patient education.

What information-related activities do people with ESKD use?

Background Information practice is an emerging area of research that seeks to reveal how people learn to connect with the complex multimodal information landscapes that informs their ability to make decisions. Previous research has identified that people with end stage kidney disease (ESKD) tend to adopt a ‘received’ or ‘engaged’ view of information but little is known about the activities of information practice. Objectives This research project sought to identify the: i) information-related activities; and ii) how information is used. Methods Using a constructivist qualitative methodology, ten people with ESKD living in a large metropolitan city were purposively selected and interviewed. Data was subject to thematic analysis by researchers from nursing and information science. Saturation of themes was achieved. Results Participants were between 38 and 72 years, had been receiving kidney replacement therapy from 2 weeks to 31 years. Eight participants reported having access to the internet but none participated in chat rooms. The activities were conceptualized into themes as listening, seeking, searching, sharing and observing. These activities enabled people to create, reflect on and evaluate the information needed to inform their decision-making Conclusion/Application to Clinical Practice The information practice research approach will enable a better understanding of the underlying relationship between information, knowledge and experience to be better understood. For renal nurses who are involved in patient education being able to recognise the way people use information will assist in individualizing educational sessions and tailoring teaching strategies to make it more meaningful.

Fast and robust stereo matching algorithms for mining automation

The mining environment, being complex, irregular and time varying, presents a challenging prospect for stereo vision. The objective is to produce a stereo vision sensor suited to close-range scenes consisting primarily of rocks. This sensor should be able to produce a dense depth map within real-time constraints. Speed and robustness are of foremost importance for this investigation. A number of area based matching metrics have been implemented, including the SAD, SSD, NCC, and their zero-meaned versions. The NCC and the zero meaned SAD and SSD were found to produce the disparity maps with the highest proportion of valid matches. The plain SAD and SSD were the least computationally expensive, due to all their operations taking place in integer arithmetic, however, they were extremely sensitive to radiometric distortion. Non-parametric techniques for matching, in particular, the rank and the census transform, have also been investigated. The rank and census transforms were found to be robust with respect to radiometric distortion, as well as being able to produce disparity maps with a high proportion of valid matches. An additional advantage of both the rank and the census transform is their amenability to fast hardware implementation.

JFA based Speaker Recognition using Delta-Phase and MFCC features

This paper investigates the use of mel-frequency deltaphase (MFDP) features in comparison to, and in fusion with, traditional mel-frequency cepstral coefficient (MFCC) features within joint factor analysis (JFA) speaker verification. MFCC features, commonly used in speaker recognition systems, are derived purely from the magnitude spectrum, with the phase spectrum completely discarded. In this paper, we investigate if features derived from the phase spectrum can provide additional speaker discriminant information to the traditional MFCC approach in a JFA based speaker verification system. Results are presented which provide a comparison of MFCC-only, MFDPonly and score fusion of the two approaches within a JFA speaker verification approach. Based upon the results presented using the NIST 2008 Speaker Recognition Evaluation (SRE) dataset, we believe that, while MFDP features alone cannot compete with MFCC features, MFDP can provide complementary information that result in improved speaker verification performance when both approaches are combined in score fusion, particularly in the case of shorter utterances.