Research UNE (University of New England)
Not a member yet
39143 research outputs found
Sort by
Comorbidity and multimorbidity prediction of major chronic diseases using machine learning and network analytics
No full textThe prevalence of chronic disease comorbidity and multimorbidity is a significant health issue worldwide. In many cases, for individuals, the occurrence of one chronic disease leads to the development of one or more other chronic conditions. This exerts a significant burden on healthcare systems globally. Disease comorbidity is defined as the simultaneous occurrence of more than one disease. And a person having more than two comorbidities is referred to as multimorbid. This study followed a machine learning and network analytics-based approach to predict major chronic disease comorbidity and multimorbidity. In doing so, this study first extracted patient networks from the research dataset. In such networks, nodes represent patients and edges between two nodes indicate that the underlying two patients had at least one common disease. This study also considered other relevant features from patients’ health trajectories. Out of the five machine learning models considered in this study (Logistic regression, k-nearest neighbours, Naïve Bayes, Random Forest and Extreme Gradient Boosting) and two deep learning models (Multilayer perceptrons and Convolutional neural networks), Extreme Gradient Boosting showed the highest accuracy (95.05%), followed by the Convolutional neural networks (91.67%). The attribute of the number of episodes from the patient trajectory had been found as the most important feature, followed by the patient network attribute of transitivity. Other relevant results (feature correlation, variable clustering, confusion matrix and kernel density estimation) were also reported and discussed. The findings and insights of this study can help healthcare stakeholders and policymakers mitigate the negative impact of disease comorbidity and multimorbidity
Video Classification Using Deep Autoencoder Network
No full textWe present a deep learning framework for video classification applicable to face recognition and dynamic texture recognition. A Deep Autoencoder Network Template (DANT) is designed whose weights are initialized by conducting unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines. In order to obtain a class specific network and fine tune the weights for each class, the pre-initialized DANT is trained for each class of video sequences, separately. A majority voting technique based on the reconstruction error is employed for the classification task. The extensive evaluation and comparisons with state-of-the-art approaches on Honda/UCSD, DynTex, and YUPPEN databases demonstrate that the proposed method significantly improves the performance of dynamic texture classification
Potential diagnostic application of a novel deep learning- based approach for COVID-19
No full textCOVID-19 is a highly communicable respiratory illness caused by the novel coronavirus SARS-CoV-2, which has had a significant impact on global public health and the economy. Detecting COVID-19 patients during a pandemic with limited medical facilities can be challenging, resulting in errors and further complications. Therefore, this study aims to develop deep learning models to facilitate automated diagnosis of COVID-19 from CT scan records of patients. The study also introduced COVIDMAH-CT, a new dataset that contains 4442 CT scan images from 133 COVID-19 patients, as well as 133 CT scan 3D volumes. We proposed and evaluated six different transfer learning models for slide-level analysis that are responsible for detecting COVID-19 in multi-slice spiral CT. Additionally, multi-head attention squeeze and excitation residual (MASERes) neural network, a novel 3D deep model was developed for patient-level analysis, which analyzes all the CT slides of a given patient as a whole and can accurately diagnose COVID-19. The codes and dataset developed in this study are available at https://github.com/alrzsdgh/COVID. The proposed transfer learning models for slide-level analysis were able to detect COVID-19 CT slides with an accuracy of more than 99%, while MASERes was able to detect COVID-19 patients from 3D CT volumes with an accuracy of 100%. These achievements demonstrate that the proposed models in this study can be useful for automatically detecting COVID-19 in both slide-level and patient-level from patients’ CT scan records, and can be applied for real-world utilization, particularly in diagnosing COVID-19 cases in areas with limited medical facilities
Reflecting on the current human enhancement drugs (HED) categorisation and new directions to consider
No full textSelf-reported behaviour change among multiple sclerosis community members and interested laypeople 6 months following participation in a free online course about multiple sclerosis
No full textIssue addressed: Evaluated the impact of the Understanding Multiple Sclerosis (MS) massive open online course, which was intended to increase understanding and awareness about MS, on self-reported health behaviour change 6 months after course completion. Methods: Observational cohort study evaluating precourse(baseline) and postcourse (immediately postcourse and six-month follow-up) survey data. The main study outcomes were self-reported health behaviour change; change type; and measurable improvement. We also collected participant characteristic data (eg, age, physical activity). We compared participants who reported health behaviour change at follow-up to those who did not and compared those who improved to those who did not using χ2 and t tests. Participant characteristics, change types and change improvement were described descriptively. Consistency between changes reported immediately postcourse and at the 6-month follow-up was assessed using χ2 tests and textual analysis. Results: N = 303 course completers were included in this study. The study cohort included MS community members (eg, people with MS, healthcare providers) and nonmembers. N = 127 (41.9%) reported behaviour change in ≥1 area at follow-up. Of these, 90 (70.9%) reported a measured change, and of these, 57 (63.3%) showed improvement. The most reported change types were knowledge, exercise/physical activity and diet. N = 81 (63.8% of those reporting a change) reported a change in both immediately and 6 months after course completion, with 72.0% of those that described both changes giving similar responses each time. Conclusion: Understanding MS encourages health behaviour change among course completers up to 6 months after course completion. So what?: An online education intervention can effectively encourage health behaviour change over a 6-month follow-up period, suggesting a transition from acute change to maintenance. The primary mechanisms underpinning this effect are information provision, including both scientific evidence and lived experience, and goal-setting activities and discussions
Preparing Pre-service Teachers to Teach Literacy in Remote Spaces
No full textRemote Indigenous communities are often seen as challenging places in which to teach for a range of reasons. Student attendance is erratic, and teachers can feel that their work is not effective. Additionally, remote communities are culturally as well as geographically very isolated, with limited access to services (Price K, Teacher education for high poverty schools. Springer, New York, 2016). Hence, it is often difficult to attract and retain teachers, and those teachers who do take up jobs in remote schools may not feel they have been adequately prepared to work in those settings. In recent years, universities and education departments have put in place a number of initiatives to attract and retain “good” teachers in these communities. For example, several universities offer placement experiences for pre-service teachers to help them develop some understanding of what it means to work and live in remote communities and for them to develop their pedagogical skills to work effectively with Indigenous learners. In this chapter we examine the kinds of knowledge and skills that pre-service teachers need in order to work in the literacy space in remote schools. Our study refers to data from interviews with pre-service teachers, community members and school personnel. It focuses on preparedness for teaching literacy in remote settings, the disconnects between the pre-service curriculum and the expectations of schools and departments and pre-service teachers’ expectations versus the realities of their lived experience on community. Data is drawn from a broader study which sought to understand how we might better plan, implement and prepare pre-service teachers for remote teaching placements so that we might provide guidance for universities, jurisdictions and policy-makers
Rural Contexts: Digital Interventions and Strategies for First Responders' Mental Health
No full textThis perspective presents a discussion on digital interventions and strategies to support the mental health of first responders working in regional, rural and remote areas. First responders are often required to respond to traumatic, violent and challenging situations. Accumulative exposure to these situations can impact first responders' mental health, and symptoms of depression, anxiety, psychological distress, and post-traumatic stress disorder (PTSD) are common. Rural first responders have similar prevalence rates of trauma to their metropolitan counterparts. However, rural first responders are likely to experience psychological difficulties exacerbated by limited access to mental health interventions due to geographical isolation and limited availability of services. Geographical location and availability of services are barriers often preventing first responders working in rural areas from accessing interventions to help them manage their mental health. Digital adaptations of mental health interventions may help to fill this gap in rural health care. Despite the popularity of first responder research developing and evaluating industry-specific mental health interventions and strategies, there is limited research focussing specifically on the effectiveness of these for Australian rural first responders, and how other mental health interventions can be digitally adapted
Exploring the Transition: Determinants influencing Australian second-level nurses’ progression to Bachelor of Nursing programs
No full textAimThis study aims to reveal the relevant demographic and educational determinants in predicting a transition from being a second level to a Registered Nurse.BackgroundThe transition from a second to a first-level regulated nurse represents a significant professional and educational milestone in the nursing career pathway. Research on determinants predicting which students will attempt this transition is scant.DesignRetrospective Cohort Study using Secondary Data AnalysisMethodA large cohort of 2023 graduates of the Diploma of Nursing contained in the Australian Student Outcome Survey is analysed in this study with respect to their post-study outcomes. Weighted logistic regression is employed to estimate predictive margins for several covariates.ResultsOur study reveals several demographic and educational determinants that show substantial association with enrolment in bachelor-level nursing courses. In assessing the significance of predictors for enrollment in higher education, the following factors were identified in descending order of importance: reason for study, student age, institution type where the Diploma qualification was obtained, remoteness of study location, prior experience in the health sector, Indigeneity origin, English language status and gender.ConclusionThe present study demonstrates that the transition from a second level to a first-level regulated nurse is not random and that several factors contribute to this transition. Academics and policymakers may find this information useful when framing policy that has an impact on the nursing workforce
The “Dreaded” Daughter-in-Law in Australian Farm Business Succession
No full textGendered analyses of simple commodity production find that the flexibility of family labour and patriarchal gender relations enable the survival of the family farm. This article examines how the land holding generation perceives the role of the farm daughter-in-law in relation to family labour dynamics and broader succession processes. Drawing on interviews with 22 farm succession professionals, our analysis demonstrates that the daughter-in-law’s contribution to the family farm is perceived as producing the next generation of the farming family and providing off farm income to enable farm viability during weather and commodity price fluctuations. Egalitarian gender norms impacting legislative rights to property are seen as a threat to the successful transfer of the family farm. Attempts by the daughter-in-law to influence the farm succession process are met with discursive and material defensive mechanisms. Given the reliance of Australian family farms on women’s labour contributions, these actions may threaten rather than ensure the continuity of family farming
Local Derivative Pattern with Smart Thresholding: Local Composition Derivative Pattern for Palmprint Matching
No full textPalmprint recognition is a new biometrics system based on physiological characteristics of the palmprint, which includes rich, stable, and unique features such as lines, points, and texture. Texture is one of the most important features extracted from low resolution images. In this paper, a new local descriptor, Local Composition Derivative Pattern (LCDP) is proposed to extract smartly stronger and more distinguishing texture features from palmprint images by composition of both radial and directional derivative information among local neighbors using a threshold function with an adaptive threshold value which result from local directional derivative information. The distribution of the LCDP is modeled by local spatial histogram and histogram intersection function is used to measure the similarity between spatial histograms of two different palm print images. Then, nearest neighbor classifier is used to classify them. Experiments on the Hong Kong Polytechnic University (PolyU) 2D_3D_palmprint database demonstrate the effectiveness of the LCDP in palmprint recognition versus well-known local pattern descriptors