Ebook: Digital Health Innovation for Consumers, Clinicians, Connectivity and Community

There's never been a more exciting time to be involved with health informatics. In the last few decades, health informaticians have established the knowledge base and practical expertise to facilitate the development of ever-more capable technical systems, increasing connectivity, expanding access and greater mobility of e-health and information management systems. We have seen the evolution from simple computer based records to systems that allow intra-organisational, national, even international communication and information exchange. We have also seen progress in e-health and most recently m-health, facilitating access to information and advice almost anytime, anywhere. The health informatics community is now building on this strong foundation, taking a central role in the digital transformation of the healthcare sector. The Australian National Health Informatics Conference (HIC), Australia's premier health informatics event, is a key avenue for facilitating this transformation. This Conference, organised by the Health Informatics Society of Australia (HISA), with the support of the Australasian College of Health Informatics (ACHI), provides the ideal professional and social environment for clinicians, researchers, health IT professionals, industry and consumers to integrate, educate and share their knowledge to drive innovative thinking, to enhance services and allow greater consumer involvement. This is emphasised in the primary theme of the 2016 Conference: Digital Health Innovation for Consumers, Clinicians, Connectivity, Community.

The papers in this volume reflect this theme, highlighting the cutting edge research evidence, technology updates and innovations that are seeing the digital transformation of the healthcare sector. The papers are indicative of the wide spectrum of work encompassing major theoretical concepts, examples of key applications of new technologies and important new developments in the field of health informatics. They emphasise the central role that health informatics and e-health play in connecting information systems, being smart with data, and enhancing both practitioner and consumer experience in healthcare interactions. Welcome to the innovation boom.

This year's program maintains the high standard of papers for which the conference is well-known. All papers were blind-peer reviewed by three experts in the field of health informatics. These reviewers are widely considered to be prominent academics and industry specialists. The contribution of the Australasian College of Health Informatics, particularly the voluntary participation of Fellows, in supporting this review process is gratefully acknowledged. Similar contributions made by many senior and experienced members of the Health Informatics Society of Australia is also acknowledged. Forty papers underwent the initial review and feedback process. Resubmitted papers were then validated by the Scientific Program Committee to ensure that reviewers' recommendations were appropriately addressed or rebutted. In total 20 papers were selected for inclusion in this volume. Congratulations to all the authors.

Andrew Georgiou

Louise K. Schaper

Sue Whetton

An electronic Influenza like Illness surveillance system developed to support general practices to electronically notify the cases of influenza like illness (ILI) for national sentinel surveillance in New Zealand. Content analysis was performed to capture the information necessary for ILI surveillance. An online form was implemented within the patient management system to record the details of ILI cases. A middleware framework was developed to manage the information flow between GPs and national influenza surveillance coordinators. The framework used an HL7 version 2.4 messaging standard to receive the notification data and Rhapsody integration engines to parse the message and store the information in national ILI data base. This paper presents the system design and implementation details of electronic ILI notification system. It presents data model designed to capture information for ILI case along with the HL7 messages structure implemented in the system.

Low adoption and use of Australia's digital health record has driven the Australian Government to trial ‘opt-out’ registration from mid-June 2016. The assumption that automatic registration will increase use and thereby deliver benefit requires further investigation especially amongst those sections of the population in rural, regional, remote Australia living with complex chronic conditions. This paper reports on findings from a community based participatory e-health research project based on an initiative where people with complex chronic conditions and their carers attended a rural health promotion and lifestyle modification program. Through co-operative enquiry, health promotion officers and their clients were actively supported to adopt and use Australia's digital health record as an intervention. Simultaneously they were encouraged to reflect on its design and their perceptions of its overall impact on their individual ability to self-manage complex chronic conditions. The findings, ultimately contributing to a conceptual implementation and evaluation framework for Australia's digital health record that could directly avoid failure of the new ‘opt-out’ approach being adopted.

Surgeons agree over the importance of surgical audit associated with their practice especially given the benefits to patient care. Medical registration also requires audit as part of their requirements. Concerns over inefficiencies that can arise from duplication in data entry, led Eye Surgery Associates, a 16 doctor practice over 3 locations in Melbourne, to develop a new data entry and analysis system to facilitate audit as well as to maintain the practice's health records system in a way that addresses these inefficiencies. They did this in conjunction with IT professionals. Surgeons in our practice are highly positive about the new system which has attracted interest and likely future participation from the broader surgeon community.

One in twenty Australian children suffers from a speech disorder. Early detection of such problems can significantly improve literacy and academic outcomes for these children, reduce health and educational burden and ongoing social costs. Here we present the development of a prototype and feasibility tests of a screening and decision support tool to assess speech disorders in young children. The prototype incorporates speech signal processing, machine learning and expert knowledge to automatically classify phonemes of normal and disordered speech. We discuss these results and our future work towards the development of a mobile tool to facilitate broad, early speech disorder screening by non-experts.

Introduction: Gout is a chronic inflammatory arthritis with increasing prevalence in Australia and rates of non-adherence to therapy higher than for any other chronic disease. Electronic health interventions can increase adherence to treatment for many chronic diseases. This study set out to involve end-user patients in the design of a gout self-management eTool.

Methods: Four semi-structured focus group sessions were held in July and August 2015 with 13 patients with gout (age range 39-79 years). Focus groups involved group discussions of potential eTool features and critiquing disease self-management websites and applications. Focus group sessions were audio-taped, transcribed and analysed by two independent researchers to identify useful eTool features and patient perspectives of using technology to manage their health.

Findings: Participants were open to using a supportive gout self-management eTool and identified a number of potentially helpful features, including educational material, serum uric acid monitoring and medication reminder alerts.

Discussion: Focus groups with patients with gout revealed a number of features that should be included in a gout self-management eTool. These results will inform the design and implementation of an eTool for patients with gout and may be broadly applicable to teams designing eTools for other chronic diseases.

Accurate and valid dietary data is the basis to investigate diet-disease relationships. Potential data discrepancies may be introduced when collecting and analysing data, despite rigorous quality assurance protocols. The aim of this study was to identify at-risk areas of dietary data in a food-based clinical trial. Source data verification was performed on a 10% random sample (n=38) of paper-based baseline diet history interview records in a registered clinical trial. All items listed in the source data underwent 100% manual verification based on the food input data from FoodWorks nutrient analysis software. Food item discrepancies were explored using food categories and summarised based on meals. The differences in identified discrepancies for energy and macronutrient output generated from FoodWorks software between previously entered data and re-entered data were compared. An overall discrepancy rate of 4.88% was identified. It was found that dinner intake data were more prone to discrepancy incidences than breakfast, lunch and snacks. Furthermore, assessing intake based on reported quantity and frequency may be more effective to correct discrepancies for quality improvement. Therefore, the dinner meal appeared to be an at risk area of dietary data. The method implemented in this study offers a systematic approach to evaluating dietary data in a research setting.

To date, there is no research examining how adults with Amyotrophic Lateral Sclerosis (ALS) or Motor Neurone Disease (MND) and severe communication disability use Twitter, nor the use of Twitter in relation to ALS/MND beyond its use for fundraising and raising awareness. In this paper we (a) outline a rationale for the use of Twitter as a method of communication and information exchange for adults with ALS/MND, (b) detail multiple qualitative and quantitative methods used to analyse Twitter networks and tweet content in the our studies, and (c) present the results of two studies designed to provide insights on the use of Twitter by an adult with ALS/MND and by #ALS and #MND hashtag communities in Twitter. We will also discuss findings across the studies, implications for health service providers in Twitter, and directions for future Twitter research in relation to ALS/MND.

Current methods to promote awareness of the sun's ultraviolet (UV) radiation have focussed on delivering population level information and some location-based reporting of UV Index (UVI). However, diseases related to excessive (e.g. sunburn, skin cancer) or insufficient (e.g. vitamin D deficiency) exposure to sunlight still remain a global burden. The emergence of wearable sensors and the application of persuasive technology in health domains raise the possibility for technology to influence awareness of sufficient sun intake for vitamin D production, as well as preventing risk of skin damage. This paper presents a personalised solution to promote healthy, safe sun exposure using wearable devices and persuasive techniques.

People with neurological conditions such as Parkinson's disease and dementia are known to have difficulties in language and communication. This paper presents initial testing of an artificial conversational agent, called Harlie. Harlie runs on a smartphone and is able to converse with the user on a variety of topics. A description of the application and a sample dialog are provided to illustrate the various roles chat-bots can play in the management of neurological conditions. Harlie can be used for measuring voice and communication outcomes during the daily life of the user, and for gaining information about challenges encountered. Moreover, it is anticipated that she may also have an educational and support role.

In this work, inertial movement units were placed on people with Parkinsons disease (PwPD) who subsequently performed a standard test of walking endurance (six-minute walk test – 6MWT). Five devices were placed on each the limbs and small of the back. These devices captured the acceleration and rotational motion while the person walked as far as they can in six minutes. The wearable devices can objectively indicate the pattern and rhythmicity of limb and body movements. It is possible that this data, when subject to machine learning could provide additional objective measures that may support clinical observations related to the quality of movement. The aim of this work is two fold. First, to identify the most useful features of the captured signals; second, to identify the accuracy of using these features to predict the severity of PD as measured by standard clinical assessment.

Preventing unplanned returns, including readmissions and representations to the emergency department is increasingly becoming a performance target for hospitals across the globe. Significant successes have been reported from interventions put in to place by hospitals to reduce their incidence. However, despite several risk stratification algorithms being proposed in recent years, there is limited use of these algorithms in hospital services to identify patients for enrolment into these intervention programs. This study identifies constraints limiting the practical use of such algorithms. We also develop and validate models that focus on clinically relevant patient cohorts and are thus better suited to practical deployment in hospitals, while still offering good predictive ability.

Registered nurses providing telenursing triage and advice services record information on the medication related calls they handle. However the quality and consistency of these data were rarely examined. Our aim was to examine medication related calls made to the healthdirect advice service in November 2014, to assess their basic characteristics and how the data entry format influenced information collected and data consistency. Registered nurses selected the patient question type from a range of categories, and entered the medications involved in a free text field. Medication names were manually extracted from the free text fields. We also compared the selected patient question type with the free text description of the call, in order to gauge data consistency. Results showed that nurses provided patients with advice on medication-related queries in a timely matter (the median call duration of 9 minutes). From 1835 calls, we were able to identify and classify 2156 medications into 384 generic names. However, in 204 cases (11.2% of calls) no medication name was entered. A further 308 (15.0%) of the medication names entered were not identifiable. When we compared the selected patient question with the free text description of calls, we found that these were consistent in 63.27% of cases. Telenursing and triage advice services provide a valuable resource to the public with quick and easily accessible advice. To support nurses provide quality services and record accurate information about the queries, appropriate data entry format and design would be beneficial.

How healthcare providers distribute their time can impact on the quality and safety of care delivered, and this has been widely studied in hospitals providing care to adult patients. Children are different to adults and the workflow of healthcare providers in paediatric settings is largely unknown. The aim of this study was to quantify how clinical pharmacists working in a paediatric hospital spend their time. A direct observational time and motion study was conducted where two independent observers shadowed seven pharmacists covering eight wards for over 60 hours. Pharmacists spent the majority of time performing medication review (32.6%), followed by communication, non-clinical tasks, supply, medication discussion and in-transit. They were interrupted 3.5 times per hour and spent 4.4% of observed time multi-tasking. This is the first study to quantify how pharmacists in a paediatric hospital distribute their time. These results could act as useful baseline data against which to measure the impact of innovations, such as electronic medication management systems, on pharmacists' workflow.

The after hours GP helpline (AGPH), one of the key services provided by Healthdirect, is an extension of the existing healthdirect telephone nurse triage and advice service. It provides access to telephone health advice by GPs after hours to patients/callers who are triaged by the telephone nurse as needing to see a GP immediately, within four hours or within 24 hours. The aims of this study were to assess patient satisfaction with the AGPH service and compliance with the GP advice; and to investigate factors associated with patients' compliance. This study included 2486 patients/callers who used the AGPH and participated in a survey between February and September 2013. Over 97.1% of patients/callers were either satisfied or very satisfied with the AGPH service. Compliance was measured in two ways: i) self-reported compliance to advice provided; and ii) matching of self-reported actions with actual GP advice given: 94.0% of patients reported they followed the advice given to them by GPs and for 86.8% of patients their reported actions following consultations matched the recommended advice documented by GPs in the healthdirect database. Patients' compliance with recommended advice were associated with patient overall satisfaction with the service, the type of AGPH advice received, and the estimated severity level of the conditions. Improving patient satisfaction with the service along with patient understanding of the advice can lead to an increased compliance rate.

This paper summarises a longitudinal analysis of learning interactions occurring over three years among health professionals in an online social network. The study employs the techniques of Social Network Analysis (SNA) and statistical modeling to identify the changes in patterns of interaction over time and test associated structural network effects. SNA results indicate overall low participation in the network, although some participants became active over time and even led discussions. In particular, the analysis has shown that a change of lead contributor results in a change in learning interaction and network structure. The analysis of structural network effects demonstrates that the interaction dynamics slow down over time, indicating that interactions in the network are more stable. The health professionals may be reluctant to share knowledge and collaborate in groups but were interested in building personal learning networks or simply seeking information.

Since electronic healthcare records are widely implemented in the hospitals, the explosion of the clinical data brings great opportunities to secondary use. Clinical data repository (CDR) plays an important role in clinical data using, including healthcare service, research and management. With evolving of clinical knowledge, it is a challenge for CDR to meet more and more requirements with adaptability and flexibility. In order to overcome this challenge, this paper proposed a solution that implemented a CDR with openEHR approach from data model to implementation. This study modelled archetypes according actual CDR requirements and implemented a CDR system in a tertiary hospital. Furthermore, this study developed data applications to facilitate healthcare service and research based on the CDR. The results of CDR system and data application demonstrate that openEHR approach could meet the continually evolving need of systems.

Despite the fact that search engines are the primary channel to access online health information, there are better ways to find and explore health information on the web. Search engines are prone to problems when they are used to find health information. For instance, users have difficulties in expressing health scenarios with appropriate search keywords, search results are not optimised for medical queries, and the search process does not account for users' literacy levels and reading preferences. In this paper, we describe our approach to addressing these problems by introducing a novel design using a slider-based user interface for discovering health information without the need for precise search keywords. The user evaluation suggests that the interface is easy to use and able to assist users in the process of discovering new information. This study demonstrates the potential value of adopting slider controls in the user interface of health websites for navigation and information discovery.

Objectives: To develop and test an optimal ensemble configuration of two complementary probabilistic data matching techniques namely Fellegi-Sunter (FS) and Jaro-Wrinkler (JW) with the goal of improving record matching accuracy.

Methods: Experiments and comparative analyses were carried out to compare matching performance amongst the ensemble configurations combining FS and JW against the two techniques independently.

Results: Our results show that an improvement can be achieved when FS technique is applied to the remaining unsure and unmatched records after the JW technique has been applied.

Discussion: Whilst all data matching techniques rely on the quality of a diverse set of demographic data, FS technique focuses on the aggregating matching accuracy from a number of useful variables and JW looks closer into matching the data content (spelling in this case) of each field. Hence, these two techniques are shown to be complementary. In addition, the sequence of applying these two techniques is critical.

Conclusion: We have demonstrated a useful ensemble approach that has potential to improve data matching accuracy, particularly when the number of demographic variables is limited. This ensemble technique is particularly useful when there are multiple acceptable spellings in the fields, such as names and addresses.

This project enabled novel organisational insight into the comparative utility of a portfolio of consumer health information content, by measuring patterns of attrition (abandonment) in content use. The project used as a case study the event activity log of a fully automated digital information kiosk, located in a community health facility. Direct measurements of the duration of content use were derived from the user interface activity recorded in the kiosk log, thus avoiding issues in using other approaches to collecting this type of data, such as sampling and observer bias. The distribution patterns of 1,383 durations of observed abandonments of use for twenty-eight discrete modules of health information content were visualised using Kaplan-Meir survival plots. Clear patterns of abandonment of content use were exhibited. The method of analysis is cost-effective, scalable and provides deep insight into the utility of health promotion content. The impact on the content producers, platform operators and service users is to improve organisational learning and thus increase the confidence in stakeholders that the service is continuously delivering high quality health and wellbeing benefits.

Repeat and redundant procedures in medical imaging are associated with increases in resource utilisation and labour costs. Unnecessary medical imaging in some modalities, such as X-Ray (XR) and Computed Tomography (CT) is an important safety issue because it exposes patients to ionising radiation which can be carcinogenic and is associated with higher rates of cancer. The aim of this study was to assess the impact of implementing an integrated Computerised Provider Order Entry (CPOE)/Radiology Information System (RIS)/Picture Archiving and Communications System (PACS) system on the number of XR and CT imaging procedures (including repeat imaging requests) for inpatients at a large metropolitan hospital. The study found that patients had an average 0.47 fewer XR procedures and 0.07 fewer CT procedures after the implementation of the integrated system. Part of this reduction was driven by a lower rate of repeat procedures: the average inpatient had 0.13 fewer repeat XR procedures within 24-hours of the previous identical XR procedure. A similar decrease was not evident for repeat CT procedures. Reduced utilisation of imaging procedures (especially those within very short intervals from the previous identical procedure, which are more likely to be redundant) has implications for the safety of patients and the cost of medical imaging services.