Ebook: Digital Health: Changing the Way Healthcare is Conceptualised and Delivered

The digital journey of healthcare, has resulted in many changes in the way healthcare is conceived and delivered in Australia and internationally. With this comes challenges, but equally significant opportunities to continue to shape healthcare. Strategic planning in health informatics for the introduction and management of systems and innovations, their evaluation, along with the essential furthering education of healthcare practitioners, is essential at micro, meso and macro levels. Within Australian digital health and informatics practice, the current directional driver is Australia’s National Digital Health Strategy to be achieved by 2022. The annual Australian national Health Informatics Conference (HIC), Australia’s premier health informatics event, is a key avenue for developing, promoting and maintaining key partnerships. The 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, collaborate, educate and share their knowledge to drive innovative thinking, to enhance services, improve data-driven decision making, and allow greater consumer involvement.

This year we have focussed on the following ten key themes that underpin a fully digital healthcare sector: Analytics and the Learning Health System; Clinical Informatics; Digital Health Workforce Development; Health Policy, Ethics and Business Models; Informatics in Health Professional Education; Innovations, Informaticians and Digital Health Entrepreneurship; Integrated and Connected Care; Interoperability and Informatics Infrastructure; Participatory Medicine and Consumer Informatics; and System Implementations and Digital Hospitals.

The papers in this volume reflect these themes, highlighting the cutting-edge research evidence, technology updates, and innovations that are supporting 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 digital health plays in our current and future healthcare organisations..wherever they be.

This year’s program maintains the high-standard of papers for which the conference is well-known. All papers were double blind-peer reviewed by three experts in the field of health informatics. These volunteer reviewers are prominent academics, digital health, and industry specialists. The contribution of ACHI in supporting this review process is gratefully acknowledged. Similar contributions made by many senior and experienced members of HISA are 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 29 papers were selected for inclusion in this volume. We congratulate all the authors on their contribution and commend them to you, the reader.

Elizabeth Cummings

Mark Merolli

Louise K. Schaper

Identifying those patient groups, who have unwanted outcomes, in the early stages is crucial to providing the most appropriate level of care. In this study, we intend to find distinctive patterns in health service use (HSU) of transport accident injured patients within the first week post-injury. Aiming those patterns that are associated with the outcome of interest. To recognize these patterns, we propose a multi-objective optimization model that minimizes the k-medians cost function and regression error simultaneously. Thus, we use a semi-supervised clustering approach to identify patient groups based on HSU patterns and their association with total cost. To solve the optimization problem, we introduce an evolutionary algorithm using stochastic gradient descent and Pareto optimal solutions. As a result, we find the best optimal clusters by minimizing both objective functions. The results show that the proposed semi-supervised approach identifies distinct groups of HSUs and contributes to predict total cost. Also, the experiments prove the performance of the multi-objective approach in comparison with single- objective approaches.

“Aging in place” refers to older adults remaining in their home as they age to maintain their independence and attachment with their community. The preference to “age in place” has led to increasing use of aged care monitoring devices to monitor the health, safety and wellbeing of older adults while living alone in their home. However, these devices raise privacy concerns as they are designed to collect, use and share sensitive data from the older adults’ private life in order to provide its real-time monitoring capabilities. This study involved interviewing developers from companies that design or deploy aged care monitoring devices about how they view privacy. The study found that developers mostly link privacy to unauthorized/uncontrolled access to users’ data, data security risks and human errors. We advocate aged care monitoring devices companies to expand their view of privacy and to adopt a sociotechnical approach when addressing privacy in their developed devices. This involves considering human issues when addressing privacy, rather than focusing exclusively on technical solutions for privacy problems.

People with complex chronic conditions (CCCs), particularly those living in rural locations, experience numerous challenges in engaging with quality integrated healthcare services. The deployment of shared digital health records (SDHRs) has been promoted to lessen these issues. However, the implementation of them has actually exacerbated the problems and inhibited SDHR adoption and use with this cohort as well as amongst rural health professionals. Based on a larger study conducted with a rural community, supported to adopt and use their SDHR, this paper highlights one finding, an empowerment gap. This needs to be overcome if vulnerable healthcare users and health professionals are to be able adopt and use SDHRs and realise some of their promised benefits. Critically, the finding highlights the importance of these users being empowered as active participants in SDHR adoption and use including by overcoming the digital literacy challenges faced. The research demonstrates that traditionally marginalised people living with CCCs in rural communities can be empowered and benefit more from an SDHR in ways comparable with users from less vulnerable groups.

We developed a machine learning model to predict 30-day readmissions using the model types; XGBoost, Random Forests and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the F1-score (0.386 ± 0.006), sensitivity (0.598 ± 0.013), positive predictive value (PPV) (0.285 ± 0.004) and negative predictive value (NPV) (0.932 ± 0.002). When compared with LACE and PARR (NZ) models, the proposed model achieved better F1-score by 12.5% compared to LACE and 22.9% compared to PARR (NZ). The mean sensitivity of the proposed model was 6.0% higher than LACE and 42.4% higher than PARR (NZ). The mean PPV was 15.9% and 13.5% higher than LACE and PARR (NZ) respectively.

A change in the behaviour of the current and future workforce in regards to how they approach the needs and challenges in the healthcare sector is necessary to transit from the current curative paradigm in health to a new one focused on prevention and rational use of resources. Digital health is instrumental in the adoption of this new paradigm as most e-health applications focus on a preventive and personalized approach, on lifestyle changes (e.g. fitness and nutrition), health literacy and self-tracking allowing consumers to manage their own heath. The Capability-Opportunity-Motivation Behaviour (COM-B) model and the Behaviour Change Wheel framework (BCW) have been applied to characterise interventions for behaviour change in health professionals. They provide a systematic way of characterising interventions and enable their outcomes to be linked to mechanisms of action. Acknowledging the potential of informatics and technologies in current and emerging health issues and the importance of focusing on care needs rather than on the development of technologies per se to achieve meaningful clinical outcomes, the College of Nursing and Health Sciences (CNHS) in Flinders University is undertaking the Care Informatics and Technologies project. This priority project aims to build capacity in digital health within the College’s students and staff, so that informatics, digitisation and technologies become part of clinical learning, research and ongoing clinical practice. We aim to report the protocol of this project and discuss it in the context of the expected change in behaviour of health professionals that is deemed necessary to address the Australian digital health agenda.

Introduction:

A great number of weight loss interventions have been delivered through digital solutions. Analysis of the effectiveness in terms of weight loss is fundamental to understand the real potential of digital technologies as tools for delivery of weight loss interventions. For this, we need accurate and reliable anthropometric data. For reasons of convenience, self-reported weight and height often replace actual measurements in these interventions. This might lead to misclassification of BMI status during selection of participants and to bias in the assessment of the outcomes. Therefore, it is fundamental to have validation studies of self-reported web-based data.

Objectives:

We aimed to validate online self-reported height, weight and BMI in a POEmaS trial subsample.

Methods:

We included 12.5% of the POEmaS’ population (n=159). Anthropometric data reported on the web-platform were compared to measured data by paired T-tests. Agreement was assessed by Bland-Altman plots. Multinomial regression was used to investigate factors associated with self-reported weight validity.

Results:

There was no significant difference between reported and measured weight (0.4 kg, SD 1.7; p=0.13) and BMI (0.03 kg/m², SD 0.87; p=0.06). Reported height was on average 0.4 cm (SD 1.2) higher than the measured ones (p<0.001). For all anthropometric data, >=95% of the cases were within the limits of agreement. Higher measured BMI was the only factor associated with low accuracy of weight report. Each unit increase in BMI increased the odds that the reported weight was lower than the one measured (OR 1.13; 95%CI 1.01-1.26).

Discussion:

Self-reported weight and BMI change showed good agreement with measured ones. Since these are the primary outcomes of the POEmaS trial, the findings of the validation study suggest that the outcomes’ accuracy is high and that it does not vary across gender, age, study group. These findings are relevant to digital health researchers and assessors and suggest that digital health interventions for weight loss might rely on self-reported assessment of outcomes. This might be particularly useful when other modes of assessment, such as anthropometry and e-scales, are not feasible or not available. However, we acknowledge that these results might not be applicable to low educated populations.

Genomic science has the potential to rapidly advance understanding of human biology in the medical context and the subsequent provision of tailored healthcare. Implementing such a disruptive and transformative technology into an existing and stretched health system will require a whole of system approach and a keen understanding of the limitations to be navigated in broadening the system to include genomic healthcare. This paper reports on the barriers to implementation faced by clinical demonstration projects in integrating into the existing infrastructure in Queensland.

There has been no empirical evidence about the health informatics workforce in Australia produced in the last ten years. This study reports the findings from an analysis of a subset of the 2018 Australian Health Informatics Workforce Census data. Analysing 420 responses that were identified as the occupational group Health Informatics, the results indicate that whilst most of the workforce is classified as aged (>45 years), many respondents are still relatively early in their health informatics careers. Furthermore, most do not possess any formal education in health informatics and almost a quarter undertake their health informatics role alongside another health-related role. The broad range of position titles and functions demonstrates the breadth within this workforce. Ongoing monitoring of this occupational group is required to inform workforce reform and renewal.

Emerging research evidence has demonstrated the potential for digital tools, such as automated language processing technology, to support parent-child interactions. Making use of digital tools can aid measurement of parent interaction metrics, additionally, providing contingent feedback to parents based on their language metrics can facilitate positive changes in their everyday input to their young children. Product innovation aside, there is a distinct lack of understanding about how best to integrate real-world, user design needs and preferences to improve deployment of technologies into routine clinical interventions. The present study explored salient requirements of a wearable language tracking device from the users’ perspectives. Mothers of young children and clinicians with experience working in paediatric settings completed a written questionnaire and rated the importance of specific functions and features of a child-worn, language tracking device on a 10-point Likert scale. There was strong rating consensus across the participants that comfort, reliability and the provision of clear and useful results were of greater importance. The need for the wearable language tracking device to ‘blend in’ with different types of clothing was rated as less important. The extended Unified Theory of Acceptance and Use of Technology (UTAUT2) model was employed as a framework for addressing these importance ratings in this population of interest. This study highlighted the need to consider user-focused service design. Addressing user’s preferences could facilitate greater technology adoption which ultimately enriches the language experiences for young children.

In recent years, the possibility of using serious gaming technology for the automation of clinical procedures for assessment of motor function have captured the interest of the research community. In this paper, a virtual version of the Box and Blocks Test (BBT) for manual dexterity assessment is presented. This game-like system combines the classical BBT mechanics with a play-centric approach to accomplish a fully automated test for assessing hand motor function, making it more accessible and easier to administer. Additionally, some variants of the traditional mechanics are proposed in order to fully exploit the advantages of the chosen technology. This ongoing research aims to provide the clinical practitioners with a customisable, intuitive, and reliable tool for the assessment and rehabilitation of hand motor function.

In recent years, the use of interactive game technology has gained much interest in the research community as a means to measure indicators associated with the risk of falling in the elderly. Input devices used for gaming offer an inexpensive but yet reliable alternative to the costly apparatuses used in clinics and medical centers. In this paper, we explore the feasibility of using virtual reality technology as a tool to assess the risk of falling in the senior community in a more immersive, intuitive and descriptive manner. Our VR-based tool captures stepping performance parameters in order to fulfill the requirements of a well-established clinical test for fall risk assessment. The use of virtual reality allows for an immersive experience where elderly users can fully concentrate on the motor and cognitive functions being assessed rather than the technology being used.

A healthy and active lifestyle can significantly improve the well-being and quality of life; however, some elderly people struggle to stay motivated and engaged with any form of exercise. The project Elaine (Elderly, AI and New Experiences) addresses this problem by seeking to improve the quality of life of the elderly through exergames. Currently, the project explores a novel approach in the field of health informatics called asynchronous exergaming. This approach, a new trend in games in the health domain, allows the elderly to workout at their own pace, and in their own time, with their physical activity linked asynchronously to a game. This paper presents the study protocol for Solitaire Fitness, a new asynchronous exergame developed by the team. The game aims at increasing the motivation of the elderly to engage in physical exercise whilst helping to maintain their cognitive abilities. It also describes the protocol for the trial. The result of this research has the potential to benefit elderly that need nudging to be motivated to exercise, health care providers treating people with sedentary lifestyles and researchers investigating ways to encourage the elderly to exercise.

SRA, NCBI’s Sequence Read Archive, is a valuable resource holding a near definitive collection of the world’s collective sequenced reads for academic purposes. Increasingly, these reads are being used for both basic research and clinical investigations. When time is a critical factor in analysis, such as during bacterial outbreaks, the geographical separation between Australia and the offshore NCBI SRA servers can result in significant delays that may have adverse clinical outcomes. To address this, Queensland Genomics commissioned a pilot program for the establishment of a local Australian SRA Cache. Utilizing the hosting capabilities of the NeCTAR Research Cloud, QRIScloud’s HTC infrastructure and the MeDiCI data fabric as a storage solution, and the software stack of Cromwell for workflow management, PostgreSQL database for sample and job metadata, and a coordinator Python Flask application, a local cache of seventeen bacterial species was established. Furthermore, the workflow capabilities of Cromwell were leveraged to provide analysis solutions for cached sample data, including quality control and taxonomic profiling, and individual and multiple sample analysis. Moving forward to a broader rollout of increased bacterial species, it was found that the initial storage estimation did not keep up with the exponential increase sequencing reads uploaded to NCBI SRA, which while highlighting the increasing availability and importance in modern research, will need to be addressed.

The paper applies an artificial intelligence centered method to classify 12 clinical safety incident (CSI) classes. The paper aims to establish a taxonomy that classifies the CSI reports into their correct classes automatically and with high accuracy. The study investigates feasibility of applying the C4.5 decision tree (DT) classifier and the random forest (RF) classifier for this purpose. The classifiers were trained using randomly selected 3600 CSIs from an Incident Information Management System (IIMS) used by seven hospitals. The taxonomies investigated were the Generic Reference Model (GRM) and the World Health Organization (WHO) patient safety classification. The classifiers trained 13 GRM CSI classes and 9 WHO CSI classes using a bag-of-words approach. The overall taxonomies performance on the RF classifier was better than on the DT classifier. The performance achieved by the classifier applying the WHO taxonomy was better than the GRM taxonomy. Four of the five poorly performing classes in the GRM taxonomy significantly improved their performance on changing the taxonomy. To improve the WHO taxonomy performance the improved WHO (WHO-I) taxonomy was built by adding a new class that did not exist in WHO but existed in GRM. The performance of the RF classifier applied to the WHO-I taxonomy further improved.

We present a mobile health platform for activity pacing referred to as Pain ROADMAP (rediscover occupation achieve & develop through a monitoring app for pain). Pain ROADMAP incorporates a mobile phone application and online portal that allows for remote monitoring, integration, and analysis of objective activity data, pain intensity ratings, medication intake and daily activity participation data. In this article this platform is presented and a summary of results obtained from a pilot study (n=20).

Background:

EMRs are one of a range of digital health solutions that are key enablers of the data revolution transforming the health sector. They offer a wide range of benefits to health professionals, patients and other key stakeholders. However, effective implementation has proved challenging.

Method:

A qualitative methodology was used in the study. Interviews were conducted with members of a cancer team 12 months post-implementation of an EMR. Data from the interviews was collected via audio recording. Audio recordings were transcribed, de-identified and analyzed to identify the experiences of staff with the EMR.

Findings:

Data was categorized in to six categories: 1) Standardisation of documentation and completeness of data; 2) Effect on workload; 3) Feature completeness and functionality; 4) Interaction with technical support; 5) Learning curve; 6) Buy-in from staff.

Conclusions & implications:

Findings from this study contribute new knowledge on barriers and enablers to the implementation of EMRs in complex clinical settings. Barriers to successful implementation include lack of technical support, perceived increase in workload and a learning curve to fully familiarize with the feature set of the EMR.

Information sharing is key to integrated, collaborative, and continuous care. People with a lived experience of mental illness may access several services across the health, mental health and social care sectors, which creates challenges for information sharing. The health informatics community has traditionally not prioritised social care informatics. However, with the growing role of social care in the lives of people with complex health conditions, now is the time when we must consider the articulation between health informatics and social care informatics in Australia. This paper reports the results of a qualitative study to understand the current context of information sharing between health, mental health and social care services. Interviews and focus groups with nine clinicians, caseworkers and support workers were undertaken. Thematic analysis supported the development of several themes. These include the growing role of social care services, the importance of trust and the challenge created by the complexity of conditions people can present with when accessing social care services. To ensure the growing range of social care services do not get left behind with the increasing digitisation of the Australian health system, the health informatics community should prioritise the inclusion of social care informatics in its scope of practice.

This paper describes the plan for the third stage of a longitudinal assessment of the progressive implementation of IS in an emergency department. The assessment adopts a case study approach with nested mixed methods where quantitative data will be collected through observations and qualitative data will be collected through focus group interviews. The findings from the study can inform the design of IS that is well aligned with the intended strategic outcomes of IS implementation in emergency medicine.

Recent research involving representatives from nursing professional organisations found a lack of governance regarding access and use of mobile technology has led to the maintenance of outdated safety and quality strategies. Current organisational policies and guidelines preclude nurses from aligning with the Australian National Safety and Quality in Health Service Standards. Continuance of the mobile technology paradox,where there is theinability of nurses to access and use mobile technology at point of care, hinders the promotion of positive two-way communication between consumers and nurses as the lack of connectivity impedes opportunities for nurses to partner with consumers to promote participation in their own healthcare, develop mutuality of understanding, and improve health and ehealth literacy. Legitimisation ofthe use of mobile technology at point of care is necessaryto supportmeeting consumer expectations, improve the consumer experience and promote participatory health, while contributing to delivery ofcontemporaryhealthcare.

Queensland Genomics recently undertook a number of Clinical Demonstration Projects (CDPs) to demonstrate the benefits of genomics in clinical practice. Integration of this testing requires the health system to provide the infrastructure for the appropriate ordering of these tests. Ordering of genomics tests will likely require greater exchange of information between the ordering clinician and the lab that is producing a clinical test report. The clinical demonstration projects were used to understand the information flow and the use of genomic, phenotypic and other information through the test ordering, analysis and reporting stages. This information was used to inform a set of requirements for a genomics test ordering and reporting system. A prototype of this system was developed as a SMART on FHIR application. This prototype will inform a future production system with FHIR Resources, software interfaces and interoperability requirements.

Health Smart Homes aim to assist the health and well-being of elderly people through digital technologies, by helping them to continue their daily living activities with safety and independence. This paper presents a landscape review to evaluate the effectiveness and feasibility of Health Smart Home technologies for advancing autonomy and quality of life from the perspectives of elderly users. The review was derived from an initial search of peer reviewed journals from three different data sources: PubMed (3808 papers), Google Scholar (7987 papers), and Scopus (595 papers). Of these, fourteen articles eventually met the inclusion criteria for the review and were subjected to further data extraction and quality assessment. The aim of this paper is to identify the perceptions of users by reviewing Health Smart Homes functions, services, benefits and implementation. Health Smart Homes could provide more opportunities to deliver IT-based health services by proactively monitoring and customizing the user environment, to the userâĂŹs needs and preferences.

Clinical terminologies play an essential role in enabling semantic interoperability between medical records. However, existing terminologies have several issues that impact data quality, such as content gaps and slow updates. In this study we explore the suitability of existing, community-driven resources, specifically Wikipedia, as a potential source to bootstrap an open clinical terminology, in terms of content coverage. In order to establish the extent of the coverage, a team of expert clinical terminologists manually mapped a clinically-relevant subset of SNOMED CT to Wikipedia articles. The results show that approximately 80% of the concepts are covered by Wikipedia. Most concepts that do not have a direct match in Wikipedia are composable from multiple articles. These findings are encouraging and suggest that it should be possible to bootstrap an open clinical terminology from Wikipedia.

My Health Record (MHR), which is an online health summary for Australians, was changed from the opt-in to the opt-out model, and therefore sparked a vast discussion on Twitter. In order to understand the debate, the information dissemination and the levels of engagement, we have analysed tweets posted from July 2018 to February 2019. In this paper, we report on the findings of the patterns of discussion, the hashtags and the numbers of retweets and likes from different user categories. The results show that the discussion was highly political, and the tweets from the MHR official accounts had lower propagation and engagement than other user groups. This work highlights the implications of using social networking sites (SNSs) to promote large-scale mandatory electronic health record systems.

Genomic testing is rapidly moving into healthcare practice. However it comes with informatics challenges that the healthcare system has not previously faced – the raw data can be hundreds of gigabytes per test, the compute demands can be thousands of CPU hours, and the test can reveal deeply private health-srelated information that can have implications for anyone related to the person tested. While not a panacea, cloud computing has particular properties that can ameliorate some of these difficulties. This paper presents some of the key lessons learned while deploying a set of genomic analyses on cloud computing for Queensland Genomics.