Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the SNOMED CT ontology

Objective To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. Materials and Methods 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. Result Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. Discussion Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. Conclusion This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

Perceptions of online learning in an Australian university : Malaysian students’ perspectives-usability of the online learning tools

This study set out to investigate the kinds of learning difficulties encountered by the Malaysian students and how they actually coped with online learning. The modified Online Learning Environment Survey (OLES) instrument was used to collect data from the sample of 40 Malaysian students at a university in Brisbane, Australia. A controlled group of 35 Australian students was also included for comparison purposes. Contrary to assumptions from previous researches, the findings revealed that there were only a few differences between the international Asian and Australian students with regards to their perceptions of online learning. Recommendations based on the findings of this research study were applicable for Australian universities which have Asian international students enrolled to study online.

De-Identification of health records using Anonym: Effectiveness and robustness across datasets

Objective Evaluate the effectiveness and robustness of Anonym, a tool for de-identifying free-text health records based on conditional random fields classifiers informed by linguistic and lexical features, as well as features extracted by pattern matching techniques. De-identification of personal health information in electronic health records is essential for the sharing and secondary usage of clinical data. De-identification tools that adapt to different sources of clinical data are attractive as they would require minimal intervention to guarantee high effectiveness. Methods and Materials The effectiveness and robustness of Anonym are evaluated across multiple datasets, including the widely adopted Integrating Biology and the Bedside (i2b2) dataset, used for evaluation in a de-identification challenge. The datasets used here vary in type of health records, source of data, and their quality, with one of the datasets containing optical character recognition errors. Results Anonym identifies and removes up to 96.6% of personal health identifiers (recall) with a precision of up to 98.2% on the i2b2 dataset, outperforming the best system proposed in the i2b2 challenge. The effectiveness of Anonym across datasets is found to depend on the amount of information available for training. Conclusion Findings show that Anonym compares to the best approach from the 2006 i2b2 shared task. It is easy to retrain Anonym with new datasets; if retrained, the system is robust to variations of training size, data type and quality in presence of sufficient training data.

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.

Sharpening our tools – translating research into practice

Providing culturally appropriate health communication tools at a community level, whilst meeting funding objectives set by Government led initiatives, can be challenging. Literature states that a translational research framework fostering community communication can encourage the development of appropriate communication tools to facilitate transfer of health information between community and researchers. Reflections from initial Need for Feed cooking and nutrition education program trials in remote Indigenous communities across Cape York indicated program resources were neither meeting community nor researchers needs. In response, a translational research framework was modelled with collaborative partnerships formed between researchers and community with the aim of modifying current resources. Local working groups were established to facilitate communication and guide continual remodelling and retrial of resources for successive programs. Feedback from working groups indicated community members wanted resources with more pictures and less words. Partnership with Chronic Disease Resources Online (CDRO) led to the development of pictorial resources including 3 evaluation tools, 27 recipe sets and 10 education support materials. Between June to December 2012 resources were trialled across 4 Cape York communities with 69 school aged children and 4 community elders. Qualitative data has indicated high satisfaction with modified pictorial resources, proving pictorial resources to be an effective and culturally appropriate method to both communicate health messages to community and facilitate flow of evaluation data to researchers. A translational research framework fostering communication between community and researchers can potentially enhance the quality of health communication tools.

Application of machine learning technique in wind turbine fault diagnosis

In this study, a machine learning technique called anomaly detection is employed for wind turbine bearing fault detection. Basically, the anomaly detection algorithm is used to recognize the presence of unusual and potentially faulty data in a dataset, which contains two phases: a training phase and a testing phase. Two bearing datasets were used to validate the proposed technique, fault-seeded bearing from a test rig located at Case Western Reserve University to validate the accuracy of the anomaly detection method, and a test to failure data of bearings from the NSF I/UCR Center for Intelligent Maintenance Systems (IMS). The latter data set was used to compare anomaly detection with SVM, a previously well-known applied method, in rapidly finding the incipient faults.

Fault diagnosis of low speed bearing based on acoustic emission signal and multi-class relevance vector machine

This study presents an acoustic emission (AE) based fault diagnosis for low speed bearing using multi-class relevance vector machine (RVM). A low speed test rig was developed to simulate the various defects with shaft speeds as low as 10 rpm under several loading conditions. The data was acquired using anAEsensor with the test bearing operating at a constant loading (5 kN) andwith a speed range from20 to 80 rpm. This study is aimed at finding a reliable method/tool for low speed machines fault diagnosis based on AE signal. In the present study, component analysis was performed to extract the bearing feature and to reduce the dimensionality of original data feature. The result shows that multi-class RVM offers a promising approach for fault diagnosis of low speed machines.

Developing Co-operating Legal Knowledge Based Systems

In attempting to build intelligent litigation support tools, we have moved beyond first generation, production rule legal expert systems. Our work supplements rule-based reasoning with case based reasoning and intelligent information retrieval. This research, specifies an approach to the case based retrieval problem which relies heavily on an extended object-oriented / rule-based system architecture that is supplemented with causal background information. Machine learning techniques and a distributed agent architecture are used to help simulate the reasoning process of lawyers. In this paper, we outline our implementation of the hybrid IKBALS II Rule Based Reasoning / Case Based Reasoning system. It makes extensive use of an automated case representation editor and background information.

Development of descriptor tools for the characterisation of Australian sugar mill evaporator scale

Cleaning of sugar mill evaporators is an expensive exercise. Identifying the scale components assists in determining which chemical cleaning agents would result in effective evaporator cleaning. The current methods (based on x-ray diffraction techniques, ion exchange/high performance liquid chromatography and thermogravimetry/differential thermal analysis) used for scale characterisation are difficult, time consuming and expensive, and cannot be performed in a conventional analytical laboratory or by mill staff. The present study has examined the use of simple descriptor tests for the characterisation of Australian sugar mill evaporator scales. Scale samples were obtained from seven Australian sugar mill evaporators by mechanical means. The appearance, texture and colour of the scale were noted before the samples were characterised using x-ray fluorescence and x-ray powder diffraction to determine the compounds present. A number of commercial analytical test kits were used to determine the phosphate and calcium contents of scale samples. Dissolution experiments were carried out on the scale samples with selected cleaning agents to provide relevant information about the effect the cleaning agents have on different evaporator scales. Results have shown that by simply identifying the colour and the appearance of the scale, the elemental composition and knowing from which effect the scale originates, a prediction of the scale composition can be made. These descriptors and dissolution experiments on scale samples can be used to provide factory staff with an on-site rapid process to predict the most effective chemicals for chemical cleaning of the evaporators.

Tools for Mobile Multimedia Programming and Development

Mobile devices are rapidly developing into the primary technology for users to work, socialize, and play in a variety of settings and contexts. Their pervasiveness has provided researchers with the means to investigate innovative solutions to ever more complex user demands. Tools for Mobile Multimedia Programming and Development investigates the use of mobile platforms for research projects, focusing on the development, testing, and evaluation of prototypes rather than final products, which enables researchers to better understand the needs of users through image processing, object recognition, sensor integration, and user interactions. This book benefits researchers and professionals in multiple disciplines who utilize such techniques in the creation of prototypes for mobile devices and applications. This book is part of the Advances in Wireless Technologies and Telecommunication series collection.

Designing intelligent litigation support tools : The IKBALS perspective

In the legal domain, it is rare to find solutions to problems by simply applying algorithms or invoking deductive rules in some knowledge‐based program. Instead, expert practitioners often supplement domain‐specific knowledge with field experience. This type of expertise is often applied in the form of an analogy. This research proposes to combine both reasoning with precedents and reasoning with statutes and regulations in a way that will enhance the statutory interpretation task. This is being attempted through the integration of database and expert system technologies. Case‐based reasoning is being used to model legal precedents while rule‐based reasoning modules are being used to model the legislation and other types of causal knowledge. It is hoped to generalise these findings and to develop a formal methodology for integrating case‐based databases with rule‐based expert systems in the legal domain.

Using Participatory Design (PD) as youth engagement strategy to inform design and development of evidence-based wellbeing e-tools

The paper presents a participatory design research framework as a primary method for structuring youth engagement, participation and contribution to the design, development and usability evaluation of three evidencebased e-tools for wellbeing, which include smart phone mobile apps as well as e-health websites. The three projects are part of a series of six e-tools part of Safe and Supportive program under Young and Well CRC. The participatory design method, developed by Zelenko (2012) for application in design of online health promoting technologies, was further piloted in partnership with Inspire USA for specific application within the CRC, deploying a combination of creative design workshops and speculative design activities in developing e-tool prototypes with young people. This paper presents the resulting participatory research framework as it was implemented across the e-tool projects to facilitate active youth participation in co-designing the e-tools and ensuring the final designs are relevant to young people and deliver health messages in engaging ways. The principles of Participatory Design (PD) that inform the new framework include a high degree of participant agency in creative decisionmaking and a commitment to the process of co-designing, with young people working alongside designers and developers. The paper will showcase how the PD framework was applied across three projects to increase young people’s contribution to final design outcome.

Can the use of quality assurance tools reduce the impact of surgical complications on the well-being of obstetricians and gynaecologists in Australia and New Zealand?

Background While adverse events primarily affect the patient, surgeons involved can also experience considerable distress. Aims The aim of the survey was to assess the impact of complications on the day-to-day life, work and health of Australian and New Zealand obstetricians and gynaecologists and to evaluate existing support systems and coping strategies. Methods A 43-question survey on self-assessment, quality assurance (QA) tools, impact of complications on individuals’ health and relationships, and support available was emailed to fellows, trainees, subspecialists and subspecialty trainees of the Royal Australian and New Zealand College of Obstetrics and Gynaecology (RANZCOG). We collected 606 responses from a target population of 2296 (response rate 26.3%). Results When complications occur, sleep was affected of 80%, family and social relationships of 55% and physical health of 48% of respondents. The major sources of support were from colleagues (83%), family (82%) and medical defence organisations (73%), with professional bodies perceived as providing least support. Nearly 80% of respondents felt the need to talk to someone they trust during times of complications. Overall, 100% of respondents used at least one QA tool (62% used two, 26% three and 9% four QA strategies). There were significant differences between respondent groups in use of the QA tools. Conclusions Surgical complications have a significant impact on the well-being of Australian and New Zealand obstetricians and gynaecologists. Existing support comes from colleagues and family, but structured, unbiased support for surgeons from a professional source is urgently warranted.

Towards the development of 1-to-n human machine interfaces for unmanned aerial vehicles

Multi-touch interfaces across a wide range of hardware platforms are becoming pervasive. This is due to the adoption of smart phones and tablets in both the consumer and corporate market place. This paper proposes a human-machine interface to interact with unmanned aerial systems based on the philosophy of multi-touch hardware-independent high-level interaction with multiple systems simultaneously. Our approach incorporates emerging development methods for multi-touch interfaces on mobile platforms. A framework is defined for supporting multiple protocols. An open source solution is presented that demonstrates: architecture supporting different communications hardware; an extensible approach for supporting multiple protocols; and the ability to monitor and interact with multiple UAVs from multiple clients simultaneously. Validation tests were conducted to assess the performance, scalability and impact on packet latency under different client configurations.

Modeling and sensorless direct torque and flux control of a dual-airgap axial flux permanent-magnet machine with field-weakening operation

This paper presents the modeling and motion-sensorless direct torque and flux control of a novel dual-airgap axial-flux permanent-magnet machine optimized for use in flywheel energy storage system (FESS) applications. Independent closed-loop torque and stator flux regulation are performed in the stator flux ( x-y) reference frame via two PI controllers. This facilitates fast torque dynamics, which is critical as far as energy charging/discharging in the FESS is concerned. As FESS applications demand high-speed operation, a new field-weakening algorithm is proposed in this paper. Flux weakening is achieved autonomously once the y-axis voltage exceeds the available inverter voltage. An inherently speed sensorless stator flux observer immune to stator resistance variations and dc-offset effects is also proposed for accurate flux and speed estimation. The proposed observer eliminates the rotary encoder, which in turn reduces the overall weight and cost of the system while improving its reliability. The effectiveness of the proposed control scheme has been verified by simulations and experiments on a machine prototype.