Ebook: Health Informatics: The Transformative Power of Innovation

Australia has a long history of involvement in the progress of health informatics. Through substantial endeavours in theory and practice, in numerous arenas including software development, standardisation, evaluation, policy development and education, Australian contributors have made impacts on the world health informatics scene.

Much of this work has been reported annually at ‘HIC’ – the annual Health Informatics Conference series hosted by the Health Informatics Society of Australia (HISA). After 19 years, this meeting has ‘come of age’ to constitute the premier Australian academic platform for a wide range of topics in health informatics. In acknowledgement of this status, HIC 2011 offers its proceedings of full scientific papers for the first time in this monograph format, enabling international access to this highly selective showcase of current Australian health informatics research. We are proud to take our place in a publication series that caters for major international conference proceedings in health informatics, including MedInfo and Medical Informatics Europe.

The theme for HIC 2011 draws on a fundamental aspect of health informatics: its ability to transform processes and practices within healthcare through innovation. These transformations address topics over a wide range of different sectors in the health system, from primary and acute care to preventative and public health. It is a hallmark of many of the papers that they not only provide solid background and technical substance in their content, but also exhibit practical implementations and demonstrations of their worth.

All papers appearing in this collection have been subject to double blind peer review by at least three members of the panel of experts, convened specifically for this purpose. The peer review process for HIC includes detailed feedback comments from reviewers, to which authors are required to respond formally when providing the final revised versions of their papers. The Scientific Program Committee members oversaw the selection of papers from those which were ranked highly during review, and ultimately 24 papers were selected from 39 submitted. Collectively these offer a comprehensive profile of active research areas in Australian health informatics.

David P. Hansen

Anthony J. Maeder

Louise K. Schaper

Singapore is in the process of rolling out a number of national e-health initiatives, including the National Electronic Health Record (NEHR). A critical enabler in the journey towards semantic interoperability is a Logical Information Model (LIM) that harmonises the semantics of the information structure with the terminology. The Singapore LIM uses a combination of international standards, including ISO 13606-1 (a reference model for electronic health record communication), ISO 21090 (healthcare datatypes), and SNOMED CT (healthcare terminology). The LIM is accompanied by a logical design approach, used to generate interoperability artifacts, and incorporates mechanisms for achieving unidirectional and bidirectional semantic interoperability.

Currently there are no widely used systems to electronically record individual patient consultations with Traditional Chinese Medicine (TCM) practitioners. As TCM practice differs significantly from western medicine both in diagnosis and treatment, using information systems created for western medicine is not suitable. There is a need for information systems developed specifically for TCM practitioners to manage patient consultation and treatments. Such system should be designed to facilitate safe and effective practice by providing decision support, utilising existing knowledge such as known herb-drug interactions to signal safety risks. Utilising current and developing standards and vocabularies such as those developed by the World Health Organisation (WHO) is important to facilitate interoperability with other systems. To facilitate continued growth in consumer demand, this type of system should be compatible with the needs of the individual electronic health records and other medical systems, and provide interfaces to external systems such as Medicare, pathology and radiology systems, and insurance systems. This paper presents the high level design of a patient consultation system for TCM practitioners that addresses the individual practitioner's needs for health records entry, storage, retrieval, display and support in managing health care delivery to patients and be part of Australia's emerging e-health system.

Automated patient monitoring in hospital environments has gained increased attention in the last decade. An important problem is that of behaviour analysis of psychiatric patients, where adequate monitoring can minimise the risk of harm to hospital staff, property and to the patients themselves. For this task, we perform a preliminary investigation on visual-based patient monitoring using surveillance cameras. The proposed method uses statistics of optical flow vectors extracted from the patient movements to identify dangerous behaviour. In addition, the method also performs foreground segmentation followed by blob tracking in order to extract shape and temporal characteristics of blobs. Dangerous behaviour includes attempting to break out of safe-rooms, self-harm and fighting. The features considered include a temporal and multi-resolution analysis of blob coarseness, blob area, movement speed and position in the room. This information can also be used to normalise the other features according to estimated position of the patient in the room. In this preliminary study, experiments in a real hospital scenario illustrate the potential applicability of the method.

BioGrid Australia provide infrastructure for research currently spanning 16 hospital-based clinical institutions and 50 databases across Victoria, Australia. To-date BioGrid have utilised a probabilistic record linkage engine (Sun Oracle Java CAPS eIndex) that utilises patient identifiers (albeit in a secure manner) during record linkage. BioGrid are now incorporating privacy-protecting record linkage technology from the University of Melbourne Rural Health Academic Centre (GRHANITE™). For the first time in Australia, the GRHANITE™technology is allowing primary care data linkage projects to happen on a large scale (70 sites, 200 planned to date). By utilising GRHANITE™privacy-protecting record linkage technologies, BioGrid are now able to overcome the privacy issues inherent in linking data across national jurisdictional boundaries. By utilising GRHANITE™privacy-protecting record linkage technologies all inter-jurisdictional public health and hospital clinical data collected by BioGrid can be systematically linked to primary care data for research for the first time. This paper describes the architecture of the combined BioGrid and GRHANITE™systems, provides evidence of the efficacy of the linkage technologies and heralds the start of a new era in privacy-protected, record linked research in Australia.

This paper describes a case study involving third-year undergraduate computing students and their conduct of a patient journey modeling project for the Ambulatory Care department of a Regional Hospital in New South Wales, Australia. The goal of the research was to determine if students, given minimal training in an emerging patient journey modeling tool known as Essomenic, could be an effective vehicle for the diffusion of innovation to operational staff involved in a healthcare improvement project. Under academic supervision, students interacted directly with staff to develop models of the current system of care from GP referral to the completion of the patient consultation. The methodology also included model validation, identification of opportunities for improvement, investigation of alternative solutions and solution recommendations. Outcomes of the project, conducted over a 14 week semester, demonstrate that the students found the technique quick and easy to learn and that they could transfer their new found knowledge of this innovation to healthcare staff for the purposes of developing true and accurate representations of the current state patient journey. Staff were then able to interact directly with the student team, using the models as a communication medium, to identify opportunities for improvement and understand more deeply, how changes would impact their daily tasks and increase patient satisfaction in service delivery.

This paper describes how a method for evaluating organisational change based on the theory of logical types can be used for classifying organisational change processes to understand change after the implementation of an electronic documentation system in a residential aged care facility. In this instance we assess the organisational change reflected by care staff's perceptions of the benefits of the new documentation system at one site, at pre-implementation, and at 12 months post-implementation. The results show how a coherent view from the staff as a whole of the personal benefits, the benefits for others and the benefits for the organization create a situation of positive feedback leading to embeddedness of the documentation system into the site, and a broader appreciation of the potential capabilities of the electronic documentation system.

This paper describes an approach of “visual interventions” to address the effects of social isolation imposed by independent living on the aged. This approach might be effective in situations where it is not possible to provide enough human contact or interaction to stimulate and sustain a positive outlook by the aged person. Two ICT-based visual interventions using this approach are described: a virtual “picture album” concept which can serve as a basis for positive reminiscence, and a virtual “daily assistant” concept to provide advice and reminders on health aspects encountered during daily living. A methodological approach for validating these concepts is also described.

Introduction. Electronic Health Record (EHR) systems are an increasingly important feature of the national healthcare system [1]. However, little research has investigated the impact this will have on medical students' learning. As part of an innovative technology platform for a new masters level program in medicine, we are developing a student-centred EHR system for clinical education. A prototype was trialed with medical students over several weeks during 2010. This paper reports on the findings of the trial, which had the overall aim of assisting our understanding of how trainee doctors might use an EHR system for learning and communication in a clinical setting.

Background. In primary care and hospital settings, EHR systems offer potential benefits to medical students' learning: Longitudinal tracking of clinical progress towards established learning objectives [2]; Capacity to search across a substantial body of records [3]; Integration with online medical databases [3]; Development of expertise in creating, accessing and managing high quality EHRs [4]. While concerns have been raised that EHR systems may alter the interaction between teachers and students [3], and may negatively influence physician-patient communication [6], there is general consensus that the EHR is changing the current practice environment and teaching practice needs to respond.

Methods. Final year medical students on clinical placement at a large university teaching hospital were recruited for the trial. Following a four-week period of use, semi-structured interviews were conducted with 10 participants. Audio-recorded interviews were transcribed and data analysed for emerging themes. Study participants were also surveyed about the importance of EHR systems in general, their familiarity with them, and general perceptions of sharing patient records.

Conclusions. Medical students in this pilot study identified a number of educational, practical and administrative advantages that the student-centred EHR system offered over their existing ad-hoc procedures for recording patient encounters. Findings from this preliminary study point to the need to introduce and instruct students' on the use of EHR systems from their earliest clinical encounters, and to closely integrate learning activities based on the EHR system with established learning objectives. Further research is required to evaluate the impact of student-centred EHR systems on learning outcomes.

This paper examines a clinical experience portal (CEP) that was developed for critical care nurses to access on a personal digital assistant (PDA) while undertaking a 12-month postgraduate program. The increasing complexity of care provided to patients in intensive care units (ICU) in Australia and overseas requires that health care practitioners working in this area are competent and highly skilled, to prevent errors and adverse events. The CEP – unlike the traditional approach which is often lacking, antiquated or encompassed in paper records – provides opportunity for collaborative activities to occur between the learner and the teacher in an auditable environment to enhance the quality of the education provided. The CEP provided a method for the nurses to record their competencies and access educational material within the framework of a postgraduate program. The benefits of using the CEP for the education of all healthcare professionals' are also discussed.

There is a widespread consensus that we have an urgent need to improve our workforce capacity in all aspects associated with the skills and knowledge required for successful e-health and health informatics developments, associated change management and systems implementation strategies. Such activities aim to support various health reform policy initiatives. This paper considers the work being undertaken by many researchers around the globe to define the range of skills and knowledge requirements to suit this purpose. A number of requirements and areas of specialisation are detailed. This is followed by descriptions for competencies in general and more specifically descriptions of a set of high level agreed Health Informatics competencies. Collectively these competencies provide a suitable framework useful for the formal recognition of Health Informatics, including e-health, as a nationally recognised study discipline. Nationally agreed competencies for this discipline enables all education and training efforts to be consistently implemented and to fit with the Australian Qualifications Framework covering both the Vocational Education and Training (VET) and Higher Education sectors.

The ability of hospital staff to get a patient to the right bed at the right time is dependent on bed occupancy, and is a key issue in all acute hospitals. This paper seeks to identify the impact of admission and discharge timing on hospital occupancy with reference to the peak in daily admissions and discharges. Patient admissions data from 23 Queensland public hospitals was classified into categories based on the relative timing of daily admission and discharge curves. We found statistically significant differences in mean and peak occupancy and patient length of stay between categories (one-way univariate ANOVA p<0.0001). The results support early patient discharge initiatives to reduce hospital occupancy rates.

Clinical research studies offer many challenges for their supporting information systems. AIBL assembled 1112 participants who volunteered crucial information for a comprehensive study on neurodegenerative diseases. This paper discusses the shortcomings of the clinical trial management system chosen to record the results of the study. A set of guidelines was devised and a critique of five systems ensued. OpenClinica was selected as the most appropriate option. The main contribution of this paper is: (i) proposing a set of guidelines to determine the appropriateness of Clinical Trial Management Systems (CTMS) solution; (ii) providing a brief critique of existing commercial and open-sourced CTMS; and (iii) alluding to some data migration issues and providing cues on how to address them. We conclude that open-source CTMS are viable alternatives to the more expensive commercial systems to conduct, record and manage clinical studies.

Web-based social networking applications have become increasingly important in recent years. The current applications in the healthcare sphere can support the health management, but to date there is no patient-controlled integrator. This paper proposes a platform called Multiple Profile Manager (MPM) that enables a user to create and manage an integrated profile that can be shared across numerous social network sites. Moreover, it is able to facilitate the collection of personal healthcare data, which makes a contribution to the development of public health informatics. Here we want to illustrate how patients and physicians can be benefited from enabling the platform for online social network sites. The MPM simplifies the management of patients' profiles and allows health professionals to obtain a more complete picture of the patients' background so that they can provide better health care. To do so, we demonstrate a prototype of the platform and describe its protocol specification, which is an XMPP (Extensible Messaging and Presence Protocol) [1] extension, for sharing and synchronising profile data (vCard²) between different social networks.

An exploratory exercise in mapping approximately 8000 medication terms from the Queensland Health iPharmacy Medication File to the Australian Medicines Terminology (AMT) was carried out to determine coverage, build specialist knowledge, and inform future clinical terminology strategies. Snapper was the mapping tool selected for this exercise. The Automap function of the tool mapped 39.2% of the items that were successfully mapped, and the remainder were manually mapped. A total of 51.8% of the sample items were mapped to a semantically equivalent AMT concept with 50.0% of terms being mapped to a satisfactory fully specified term, and 1.8% of terms being mapped to a fully specified term that was considered unsuitable for QH clinical purposes. Rules and guidelines on how to deal with the emerging differences between the two terminologies were developed during the course of the project. Snapper was found to be an appropriate tool for this exercise; its functionality is being constantly refined to assist users. As a result, this exercise will provide NEHTA with input for the national scope and content for AMT, and QH will endeavour to prepare the iPharmacy medication file for future interfaces with other terminologies.

Objective: To develop a system for the automatic classification of Cancer Registry notifications data from free-text pathology reports.

Method: The underlying technology used for the extraction of cancer notification items is based on the symbolic rule-based classification methodology, whereby formal semantics are used to reason with the systematised nomenclature of medicine – clinical terms (SNOMED CT) concepts identified in the free text. Business rules for cancer notifications used by Cancer Registry coding staff were also incorporated with the aim to mimic Cancer Registry processes.

Results: The system was developed on a corpus of 239 histology and cytology reports (with 60% notifiable reports), and then evaluated on an independent set of 300 reports (with 20% notifiable reports). Results show that the system can reliably classify notifiable reports with 96% and 100% specificity, and achieve an overall accuracy of 82% and 74% for classifying notification items from notifiable reports at a unit record level from the development and evaluation set, respectively.

Conclusion: Cancer Registries collect a multitude of data that requires manual review, slowing down the flow of information. Extracting and providing an automatically coded cancer pathology notification for review can lessen the reliance on expert clinical staff, improving the efficiency and availability of cancer information.

With an astonishing amount of genomic data generated for processing in medical field, it is essential to provide an effective methodology for understanding, reasoning and supporting decision making of large information spaces. This paper presents an interactive interface that provides a mechanism to analyse large scale biological and clinical data. This aims to provide a much greater flexibility and control for the domain experts to interactively customise the visualisation according to their preferences.

Social and professional support for mental health is lacking in many rural areas – highlighting the need for innovative ways to improve access to services. This study explores the potential of online social networking as an avenue for peer support. Using a cross sectional survey, 74 secondary students answered questions relating to internet use, online social network use and perceptions of mental health support. Over half of the sample had experienced a need for mental health support with 53% of participants turning to the internet. Results indicate that online social networking sites were used regularly by 82% of the sample and 47% believed these sites could help with mental health problems. The study concluded that online social networking sites may be able to link young people together with others in similar situations. The popularity and frequency of use may allow these sites to provide information, advice and direction for those seeking help.

Effective communication in healthcare is important and especially critical in emergency situations. In this paper we propose a new comprehensive emergency system which will facilitate the communication process in emergency cases from ambulance dispatch to the patient's arrival and handover in the hospital. The proposed system has been designed to facilitate and computerise all the processes involved in an accident from finding the nearest ambulance through to accessing a patient's online health record which can assist in pre-hospital treatments. The proposed system will also locate the nearest hospital specialising in the patient's condition and will communicate patient identification to the emergency department. The components of the proposed system and the technologies used in building this system are outlined in this paper as well as the challenges expected and proposed solutions to these challenges.

Introduction. We aim to improve retrieval of health information from Twitter.

Background. The popularity of social media and micro-blogs has emphasised their potential for knowledge discovery and trend building. However, capturing and relating concepts in these short-spoken and lexically extensive sources of information requires search engines with increasing intelligence.

Methods. Our approach uses query expansion techniques to associate query terms with the most similar Twitter terms to capture trends in the gamut of information.

Results. We demonstrated the value, defined as improved precision, of our search engine by considering three search tasks and two independent annotators. We also showed the stability of the engine with an increasing number of tweets; this is crucial as large data sets are needed for capturing trends with high confidence. These results encourage us to continue developing the engine for discovering trends in health information available at Twitter.

Background: Electronic health records (EHR) are increasingly used for both administrative and clinical tasks with major implications for patient safety and quality of care. This study aims to determine a baseline EHR level of accuracy present on measurable information fields within an Australian general practice.

Methods: Quantitative and descriptive pilot study of patients attending a private general practice. Patients who consented to participate in the study had their patient records reviewed to determine how many items were correct, incorrect or not recorded in each EHR information field. Statistical analysis was performed on the data collected. Results: A total of 33 patients gave consent to participate in this study. High levels of accuracy were found in the area of demographic details (94%). Moderately high levels of accuracy were reported for allergies (61%) but also a considerable percentage of non-recorded information was present (36%). Inaccuracies in medication lists were reported in 51% of records reviewed with 32.1% of all medications being inaccurately recorded. While over 91% of participants had a history summary with eight or less items present, omissions were reported for one in every five participants. There were no significant associations present between inaccurate data and frequency of practice visits or those with more than five past medical conditions listed in the EHR.

Conclusion: The study has confirmed that errors and inaccuracies exist in EHR in our Australian pilot study. The pilot study has also allowed us to complete a trial ensuring that a study of this type can be done safely and with correct methodology. As health informatics plays an increasingly important role in health care, studies of this type will better inform practitioners/ researchers in designing systems to ensure quality electronic patient information.

Objective: To understand the journey of advanced prostate cancer patients for supporting development of an innovative patient journey browser. Background: Prostate cancer is one of the common cancers in Australia. Due to the chronic nature of the disease, it is important to have effective disease management strategy and care model. Multi-disciplinary care is a well-proven approach for chronic disease management. The Multi-disciplinary team (MDT) can function more effectively if all the required information is available for the clinical decision support. The development of innovative technology relies on an accurate understanding of the advanced prostate cancer patient's journey over a prolonged period. This need arises from the fact that advanced prostate cancer patients may follow various treatment paths and change their care providers. As a result of this, it is difficult to understand the actual sources of patient's clinical records and their treatment patterns. The aim of the research is to understand variable sources of clinical records, treatment patterns, alternative therapies, over the counter (OTC) medications of advanced prostate cancer patients. This study provides better and holistic understanding of advanced prostate cancer journey.

Methods: The study was conducted through an on-line survey developed to seek and analyse the responses from the participants. The on-line questionnaire was carefully developed through consultations with the clinical researchers at the Australian Prostate Cancer Research Centre-Queensland, prostate cancer support group representatives and health informaticians at the Australian E-Health Research Centre. The non-identifying questionnaire was distributed to the patients through prostate cancer support groups in Queensland, Australia. The pilot study was carried out between August 2010 and December 2010.

Results: The research made important observations about the advanced prostate cancer journey. It showed that General Practitioner (GP) was the common source of patient's clinical records (41%) followed by Urologist (14%) and other clinicians (14%). The data analysis also showed that selenium was the common complementary supplement (55%) used by the patients and about 48% patients did not use any OTC drugs. The most common OTC used by the patients was Paracetamol (about 45%). Conclusion: The results have provided a foundation to the architecture of the proposed technology solution. The outcomes of this study are incorporated in design of the proposed patient journey browser system. A basic version of the system is currently being used at the advanced prostate cancer MDT meetings.

Objective: To demonstrate application of data integration technology for observing the effectiveness of interventions to control pathology orders in Emergency Departments.

Background: Doctors frequently need to order blood tests in the Emergency Departments as a part of diagnostic set up in Emergency Departments. However, pathology test ordering is excessive and often unnecessary. The excessive ordering of blood test places a significant financial burden on our health care system. It also causes undue discomfort and worry to the patients. There are many interventions employed to control pathology ordering in Emergency Departments. The analysis of effectiveness of interventions is required for improving clinical practices in Emergency Departments. However, the collection and extraction of data on the effects of intervention can be very costly and time consuming. Therefore, there is a need of a technology-based solution to access, query and analyse data residing across different sources.

Methods: The research aims to determine efficacy of an intervention called the “Traffic Light System” through a pathology request form used to control the pathology ordering in one adult hospital emergency department. Health Data Integration (HDI) technology was implemented to link and query the data residing at different source systems i.e. pathology and ED information system. The data was extracted from the Emergency Department Information System at an adult tertiary hospital in Queensland. Twenty weeks of pre-intervention data was collected. Twenty weeks of post-intervention data was collected after 32-week transition interval. The data for pre-intervention, transition and post-intervention period was analysed to assess the effectiveness of the intervention in reducing commonly ordered pathology tests such as Full Blood Counts (FBC) and Erythrocyte Sedimentation Rate (ESR).

Results: The total number of FBC tests ordered in the pre-intervention period fell slightly in the post-intervention period (mean 42.3 vs 38.1 per 100 patients). The total number Erythrocyte Sedimentation Rate tests showed a significant declining trend as a result of ED intervention (2.5 vs 1.4 per 100 patients, p=0.001). HDI completed the task of data extraction, manipulation and querying in seconds. A manual check of a sample of 200 pathology test orders shows 95.5% sensitivity, which is considered accurate enough for this purpose.

Conclusion: Pathology ordering can be reduced using sustainable protocols. This work has demonstrated HDI capability to extract and link pathology data efficiently to evaluate an ED intervention.

Connecting Australian health services and the e-health initiative is a major focus in the current health environment. Many issues are presented as key to its success including solving issues with confidentiality and privacy. However, the main problem may not be these issues in sharing information but the fact that the point of origin of such records is still relatively insecure. This paper highlights why this may be the case. Research into the security of medical information has shown that many primary healthcare providers are unable to create an environment with effective information security. Numerous factors contribute to this complex situation including a trustful environment, the resultant security culture and the capability of individual healthcare organisations. Further, the growing importance of new directions in the use of patient information is considered. This paper discusses these issues and positions them within the complex environment that is healthcare. In our current health system infrastructure, the points of origin of patient information are our most vulnerable. This entwined with progressively new uses of this information expose additional security concerns, such as re-identification of information, that require attention.

Background. Physical activity classification is an objective approach to assess levels of physical activity, and indicates an individual's degree of functional ability. It is significant for a number of the disciplines, such as behavioural sciences, physiotherapy, etc. Accelerometry is found to be a practical and low cost method for activity classification that could provide an objective and efficient measurement of people's daily activities.

Methods. This paper utilises a mobile phone with a built-in tri-axial accelerometer sensor to automatically classify normal physical activities. A rule-based activity classification model, which can recognise 4 common daily activities (lying, walking, sitting, and standing) and 6 transitions between postural orientations, is introduced here. In this model, three types of statuses (walking/ transition, lying, and sitting/standing) are first classified based on the kinetic energy and upright angle. Transitions are then separated from walking and assigned to the corresponding type using upright angle algorithm. To evaluate the performance of this developed application, a trial is designed with 8 healthy adult subjects, who are required to perform a 6-minute activity routine with an iPhone fixed at the waist position.

Results. Based on the evaluation result, our application measures the length of time of each activity accurately and the achieved sensitivity of each activity classification exceeds 90% while the achieved specificity exceeds 96%. Meanwhile, regarding the transition identification, the sensitivities are high in stand-to-sit (80%) and low in sit-to-stand (56%).